diffusers/pr_12242/en/_app/immutable/nodes/10.fd4e66c0.js

import{s as KL,o as eb,n as D}from"../chunks/scheduler.8c3d61f6.js";import{S as ob,i as tb,g as s,s as r,r as f,A as ab,h as i,f as d,c as n,j as $,u as p,x as g,k as y,y as o,a as L,v as m,d as _,t as u,w as h}from"../chunks/index.da70eac4.js";import{T as C}from"../chunks/Tip.1d9b8c37.js";import{D as M}from"../chunks/Docstring.8928dec8.js";import{C as ae}from"../chunks/CodeBlock.a9c4becf.js";import{E as te}from"../chunks/ExampleCodeBlock.3d7cfea3.js";import{H as X,E as rb}from"../chunks/getInferenceSnippets.8d281f31.js";function nb(T){let t,b='To learn more about how to load LoRA weights, see the <a href="../../using-diffusers/loading_adapters#lora">LoRA</a> loading guide.';return{c(){t=s("p"),t.innerHTML=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-1fw6lx1"&&(t.innerHTML=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function sb(T){let t,b="Example:",l,c,v;return c=new ae({props:{code:"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",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image
<span class="hljs-keyword">import</span> torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>, torch_dtype=torch.float16
).to(<span class="hljs-string">&quot;cuda&quot;</span>)
pipeline.load_lora_weights(
    <span class="hljs-string">&quot;jbilcke-hf/sdxl-cinematic-1&quot;</span>, weight_name=<span class="hljs-string">&quot;pytorch_lora_weights.safetensors&quot;</span>, adapter_names=<span class="hljs-string">&quot;cinematic&quot;</span>
)
pipeline.delete_adapters(<span class="hljs-string">&quot;cinematic&quot;</span>)`,wrap:!1}}),{c(){t=s("p"),t.textContent=b,l=r(),f(c.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=b),l=n(a),p(c.$$.fragment,a)},m(a,w){L(a,t,w),L(a,l,w),m(c,a,w),v=!0},p:D,i(a){v||(_(c.$$.fragment,a),v=!0)},o(a){u(c.$$.fragment,a),v=!1},d(a){a&&(d(t),d(l)),h(c,a)}}}function ib(T){let t,b="Example:",l,c,v;return c=new ae({props:{code:"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",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image
<span class="hljs-keyword">import</span> torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>, torch_dtype=torch.float16
).to(<span class="hljs-string">&quot;cuda&quot;</span>)
pipeline.load_lora_weights(
    <span class="hljs-string">&quot;jbilcke-hf/sdxl-cinematic-1&quot;</span>, weight_name=<span class="hljs-string">&quot;pytorch_lora_weights.safetensors&quot;</span>, adapter_name=<span class="hljs-string">&quot;cinematic&quot;</span>
)
pipeline.disable_lora()`,wrap:!1}}),{c(){t=s("p"),t.textContent=b,l=r(),f(c.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=b),l=n(a),p(c.$$.fragment,a)},m(a,w){L(a,t,w),L(a,l,w),m(c,a,w),v=!0},p:D,i(a){v||(_(c.$$.fragment,a),v=!0)},o(a){u(c.$$.fragment,a),v=!1},d(a){a&&(d(t),d(l)),h(c,a)}}}function db(T){let t,b="Example:",l,c,v;return c=new ae({props:{code:"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",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image
<span class="hljs-keyword">import</span> torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>, torch_dtype=torch.float16
).to(<span class="hljs-string">&quot;cuda&quot;</span>)
pipeline.load_lora_weights(
    <span class="hljs-string">&quot;jbilcke-hf/sdxl-cinematic-1&quot;</span>, weight_name=<span class="hljs-string">&quot;pytorch_lora_weights.safetensors&quot;</span>, adapter_name=<span class="hljs-string">&quot;cinematic&quot;</span>
)
pipeline.enable_lora()`,wrap:!1}}),{c(){t=s("p"),t.textContent=b,l=r(),f(c.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=b),l=n(a),p(c.$$.fragment,a)},m(a,w){L(a,t,w),L(a,l,w),m(c,a,w),v=!0},p:D,i(a){v||(_(c.$$.fragment,a),v=!0)},o(a){u(c.$$.fragment,a),v=!1},d(a){a&&(d(t),d(l)),h(c,a)}}}function lb(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function cb(T){let t,b="Example:",l,c,v;return c=new ae({props:{code:"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",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline
<span class="hljs-keyword">import</span> torch

pipeline = DiffusionPipeline.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>, torch_dtype=torch.float16
).to(<span class="hljs-string">&quot;cuda&quot;</span>)
pipeline.load_lora_weights(<span class="hljs-string">&quot;nerijs/pixel-art-xl&quot;</span>, weight_name=<span class="hljs-string">&quot;pixel-art-xl.safetensors&quot;</span>, adapter_name=<span class="hljs-string">&quot;pixel&quot;</span>)
pipeline.fuse_lora(lora_scale=<span class="hljs-number">0.7</span>)`,wrap:!1}}),{c(){t=s("p"),t.textContent=b,l=r(),f(c.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=b),l=n(a),p(c.$$.fragment,a)},m(a,w){L(a,t,w),L(a,l,w),m(c,a,w),v=!0},p:D,i(a){v||(_(c.$$.fragment,a),v=!0)},o(a){u(c.$$.fragment,a),v=!1},d(a){a&&(d(t),d(l)),h(c,a)}}}function fb(T){let t,b="Example:",l,c,v;return c=new ae({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMERpZmZ1c2lvblBpcGVsaW5lJTBBJTBBcGlwZWxpbmUlMjAlM0QlMjBEaWZmdXNpb25QaXBlbGluZS5mcm9tX3ByZXRyYWluZWQoJTBBJTIwJTIwJTIwJTIwJTIyc3RhYmlsaXR5YWklMkZzdGFibGUtZGlmZnVzaW9uLXhsLWJhc2UtMS4wJTIyJTJDJTBBKS50byglMjJjdWRhJTIyKSUwQXBpcGVsaW5lLmxvYWRfbG9yYV93ZWlnaHRzKCUyMkNpcm9OMjAyMiUyRnRveS1mYWNlJTIyJTJDJTIwd2VpZ2h0X25hbWUlM0QlMjJ0b3lfZmFjZV9zZHhsLnNhZmV0ZW5zb3JzJTIyJTJDJTIwYWRhcHRlcl9uYW1lJTNEJTIydG95JTIyKSUwQXBpcGVsaW5lLmdldF9hY3RpdmVfYWRhcHRlcnMoKQ==",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>,
).to(<span class="hljs-string">&quot;cuda&quot;</span>)
pipeline.load_lora_weights(<span class="hljs-string">&quot;CiroN2022/toy-face&quot;</span>, weight_name=<span class="hljs-string">&quot;toy_face_sdxl.safetensors&quot;</span>, adapter_name=<span class="hljs-string">&quot;toy&quot;</span>)
pipeline.get_active_adapters()`,wrap:!1}}),{c(){t=s("p"),t.textContent=b,l=r(),f(c.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=b),l=n(a),p(c.$$.fragment,a)},m(a,w){L(a,t,w),L(a,l,w),m(c,a,w),v=!0},p:D,i(a){v||(_(c.$$.fragment,a),v=!0)},o(a){u(c.$$.fragment,a),v=!1},d(a){a&&(d(t),d(l)),h(c,a)}}}function pb(T){let t,b="Example:",l,c,v;return c=new ae({props:{code:"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",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image
<span class="hljs-keyword">import</span> torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>, torch_dtype=torch.float16
).to(<span class="hljs-string">&quot;cuda&quot;</span>)
pipeline.load_lora_weights(
    <span class="hljs-string">&quot;jbilcke-hf/sdxl-cinematic-1&quot;</span>, weight_name=<span class="hljs-string">&quot;pytorch_lora_weights.safetensors&quot;</span>, adapter_name=<span class="hljs-string">&quot;cinematic&quot;</span>
)
pipeline.load_lora_weights(<span class="hljs-string">&quot;nerijs/pixel-art-xl&quot;</span>, weight_name=<span class="hljs-string">&quot;pixel-art-xl.safetensors&quot;</span>, adapter_name=<span class="hljs-string">&quot;pixel&quot;</span>)
pipeline.set_adapters([<span class="hljs-string">&quot;cinematic&quot;</span>, <span class="hljs-string">&quot;pixel&quot;</span>], adapter_weights=[<span class="hljs-number">0.5</span>, <span class="hljs-number">0.5</span>])`,wrap:!1}}),{c(){t=s("p"),t.textContent=b,l=r(),f(c.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=b),l=n(a),p(c.$$.fragment,a)},m(a,w){L(a,t,w),L(a,l,w),m(c,a,w),v=!0},p:D,i(a){v||(_(c.$$.fragment,a),v=!0)},o(a){u(c.$$.fragment,a),v=!1},d(a){a&&(d(t),d(l)),h(c,a)}}}function mb(T){let t,b;return t=new ae({props:{code:"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",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.load_lora_weights(path_1, adapter_name=<span class="hljs-string">&quot;adapter-1&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.load_lora_weights(path_2, adapter_name=<span class="hljs-string">&quot;adapter-2&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.set_adapters(<span class="hljs-string">&quot;adapter-1&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>image_1 = pipe(**kwargs)
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># switch to adapter-2, offload adapter-1</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.set_lora_device(adapter_names=[<span class="hljs-string">&quot;adapter-1&quot;</span>], device=<span class="hljs-string">&quot;cpu&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.set_lora_device(adapter_names=[<span class="hljs-string">&quot;adapter-2&quot;</span>], device=<span class="hljs-string">&quot;cuda:0&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.set_adapters(<span class="hljs-string">&quot;adapter-2&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>image_2 = pipe(**kwargs)
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># switch back to adapter-1, offload adapter-2</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.set_lora_device(adapter_names=[<span class="hljs-string">&quot;adapter-2&quot;</span>], device=<span class="hljs-string">&quot;cpu&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.set_lora_device(adapter_names=[<span class="hljs-string">&quot;adapter-1&quot;</span>], device=<span class="hljs-string">&quot;cuda:0&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.set_adapters(<span class="hljs-string">&quot;adapter-1&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>...`,wrap:!1}}),{c(){f(t.$$.fragment)},l(l){p(t.$$.fragment,l)},m(l,c){m(t,l,c),b=!0},p:D,i(l){b||(_(t.$$.fragment,l),b=!0)},o(l){u(t.$$.fragment,l),b=!1},d(l){h(t,l)}}}function _b(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function ub(T){let t,b="Examples:",l,c,v;return c=new ae({props:{code:"JTIzJTIwQXNzdW1pbmclMjAlNjBwaXBlbGluZSU2MCUyMGlzJTIwYWxyZWFkeSUyMGxvYWRlZCUyMHdpdGglMjB0aGUlMjBMb1JBJTIwcGFyYW1ldGVycy4lMEFwaXBlbGluZS51bmxvYWRfbG9yYV93ZWlnaHRzKCklMEEuLi4=",highlighted:'<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># Assuming `pipeline` is already loaded with the LoRA parameters.</span>\n<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.unload_lora_weights()\n<span class="hljs-meta">&gt;&gt;&gt; </span>...',wrap:!1}}),{c(){t=s("p"),t.textContent=b,l=r(),f(c.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-kvfsh7"&&(t.textContent=b),l=n(a),p(c.$$.fragment,a)},m(a,w){L(a,t,w),L(a,l,w),m(c,a,w),v=!0},p:D,i(a){v||(_(c.$$.fragment,a),v=!0)},o(a){u(c.$$.fragment,a),v=!1},d(a){a&&(d(t),d(l)),h(c,a)}}}function hb(T){let t,b="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",l,c,v="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=b,l=r(),c=s("p"),c.textContent=v},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=b),l=n(a),c=i(a,"P",{"data-svelte-h":!0}),g(c)!=="svelte-3fufvn"&&(c.textContent=v)},m(a,w){L(a,t,w),L(a,l,w),L(a,c,w)},p:D,d(a){a&&(d(t),d(l),d(c))}}}function gb(T){let t,b="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",l,c,v="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=b,l=r(),c=s("p"),c.textContent=v},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=b),l=n(a),c=i(a,"P",{"data-svelte-h":!0}),g(c)!=="svelte-3fufvn"&&(c.textContent=v)},m(a,w){L(a,t,w),L(a,l,w),L(a,c,w)},p:D,d(a){a&&(d(t),d(l),d(c))}}}function xb(T){let t,b="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",l,c,v="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=b,l=r(),c=s("p"),c.textContent=v},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=b),l=n(a),c=i(a,"P",{"data-svelte-h":!0}),g(c)!=="svelte-3fufvn"&&(c.textContent=v)},m(a,w){L(a,t,w),L(a,l,w),L(a,c,w)},p:D,d(a){a&&(d(t),d(l),d(c))}}}function Lb(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function bb(T){let t,b="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",l,c,v="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=b,l=r(),c=s("p"),c.textContent=v},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=b),l=n(a),c=i(a,"P",{"data-svelte-h":!0}),g(c)!=="svelte-3fufvn"&&(c.textContent=v)},m(a,w){L(a,t,w),L(a,l,w),L(a,c,w)},p:D,d(a){a&&(d(t),d(l),d(c))}}}function wb(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function vb(T){let t,b="Examples:",l,c,v;return c=new ae({props:{code:"JTIzJTIwQXNzdW1pbmclMjAlNjBwaXBlbGluZSU2MCUyMGlzJTIwYWxyZWFkeSUyMGxvYWRlZCUyMHdpdGglMjB0aGUlMjBMb1JBJTIwcGFyYW1ldGVycy4lMEFwaXBlbGluZS51bmxvYWRfbG9yYV93ZWlnaHRzKCklMEEuLi4=",highlighted:'<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># Assuming `pipeline` is already loaded with the LoRA parameters.</span>\n<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.unload_lora_weights()\n<span class="hljs-meta">&gt;&gt;&gt; </span>...',wrap:!1}}),{c(){t=s("p"),t.textContent=b,l=r(),f(c.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-kvfsh7"&&(t.textContent=b),l=n(a),p(c.$$.fragment,a)},m(a,w){L(a,t,w),L(a,l,w),m(c,a,w),v=!0},p:D,i(a){v||(_(c.$$.fragment,a),v=!0)},o(a){u(c.$$.fragment,a),v=!1},d(a){a&&(d(t),d(l)),h(c,a)}}}function $b(T){let t,b="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",l,c,v="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=b,l=r(),c=s("p"),c.textContent=v},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=b),l=n(a),c=i(a,"P",{"data-svelte-h":!0}),g(c)!=="svelte-3fufvn"&&(c.textContent=v)},m(a,w){L(a,t,w),L(a,l,w),L(a,c,w)},p:D,d(a){a&&(d(t),d(l),d(c))}}}function yb(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function Mb(T){let t,b="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",l,c,v="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=b,l=r(),c=s("p"),c.textContent=v},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=b),l=n(a),c=i(a,"P",{"data-svelte-h":!0}),g(c)!=="svelte-3fufvn"&&(c.textContent=v)},m(a,w){L(a,t,w),L(a,l,w),L(a,c,w)},p:D,d(a){a&&(d(t),d(l),d(c))}}}function Tb(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function Db(T){let t,b="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",l,c,v="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=b,l=r(),c=s("p"),c.textContent=v},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=b),l=n(a),c=i(a,"P",{"data-svelte-h":!0}),g(c)!=="svelte-3fufvn"&&(c.textContent=v)},m(a,w){L(a,t,w),L(a,l,w),L(a,c,w)},p:D,d(a){a&&(d(t),d(l),d(c))}}}function Cb(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function Sb(T){let t,b="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",l,c,v="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=b,l=r(),c=s("p"),c.textContent=v},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=b),l=n(a),c=i(a,"P",{"data-svelte-h":!0}),g(c)!=="svelte-3fufvn"&&(c.textContent=v)},m(a,w){L(a,t,w),L(a,l,w),L(a,c,w)},p:D,d(a){a&&(d(t),d(l),d(c))}}}function kb(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function Rb(T){let t,b="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",l,c,v="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=b,l=r(),c=s("p"),c.textContent=v},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=b),l=n(a),c=i(a,"P",{"data-svelte-h":!0}),g(c)!=="svelte-3fufvn"&&(c.textContent=v)},m(a,w){L(a,t,w),L(a,l,w),L(a,c,w)},p:D,d(a){a&&(d(t),d(l),d(c))}}}function Ab(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function Ib(T){let t,b="We support loading original format HunyuanVideo LoRA checkpoints.",l,c,v="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=b,l=r(),c=s("p"),c.textContent=v},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-gyrs6h"&&(t.textContent=b),l=n(a),c=i(a,"P",{"data-svelte-h":!0}),g(c)!=="svelte-3fufvn"&&(c.textContent=v)},m(a,w){L(a,t,w),L(a,l,w),L(a,c,w)},p:D,d(a){a&&(d(t),d(l),d(c))}}}function Ub(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function Vb(T){let t,b="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",l,c,v="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=b,l=r(),c=s("p"),c.textContent=v},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=b),l=n(a),c=i(a,"P",{"data-svelte-h":!0}),g(c)!=="svelte-3fufvn"&&(c.textContent=v)},m(a,w){L(a,t,w),L(a,l,w),L(a,c,w)},p:D,d(a){a&&(d(t),d(l),d(c))}}}function Wb(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function Xb(T){let t,b="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",l,c,v="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=b,l=r(),c=s("p"),c.textContent=v},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=b),l=n(a),c=i(a,"P",{"data-svelte-h":!0}),g(c)!=="svelte-3fufvn"&&(c.textContent=v)},m(a,w){L(a,t,w),L(a,l,w),L(a,c,w)},p:D,d(a){a&&(d(t),d(l),d(c))}}}function Pb(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function Fb(T){let t,b="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",l,c,v="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=b,l=r(),c=s("p"),c.textContent=v},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=b),l=n(a),c=i(a,"P",{"data-svelte-h":!0}),g(c)!=="svelte-3fufvn"&&(c.textContent=v)},m(a,w){L(a,t,w),L(a,l,w),L(a,c,w)},p:D,d(a){a&&(d(t),d(l),d(c))}}}function Jb(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function Hb(T){let t,b="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",l,c,v="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=b,l=r(),c=s("p"),c.textContent=v},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=b),l=n(a),c=i(a,"P",{"data-svelte-h":!0}),g(c)!=="svelte-3fufvn"&&(c.textContent=v)},m(a,w){L(a,t,w),L(a,l,w),L(a,c,w)},p:D,d(a){a&&(d(t),d(l),d(c))}}}function jb(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function Zb(T){let t,b="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",l,c,v="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=b,l=r(),c=s("p"),c.textContent=v},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=b),l=n(a),c=i(a,"P",{"data-svelte-h":!0}),g(c)!=="svelte-3fufvn"&&(c.textContent=v)},m(a,w){L(a,t,w),L(a,l,w),L(a,c,w)},p:D,d(a){a&&(d(t),d(l),d(c))}}}function Gb(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function qb(T){let t,b="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",l,c,v="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=b,l=r(),c=s("p"),c.textContent=v},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=b),l=n(a),c=i(a,"P",{"data-svelte-h":!0}),g(c)!=="svelte-3fufvn"&&(c.textContent=v)},m(a,w){L(a,t,w),L(a,l,w),L(a,c,w)},p:D,d(a){a&&(d(t),d(l),d(c))}}}function Bb(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function Eb(T){let t,b="Example:",l,c,v;return c=new ae({props:{code:"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",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image
<span class="hljs-keyword">import</span> torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>, torch_dtype=torch.float16
).to(<span class="hljs-string">&quot;cuda&quot;</span>)
pipeline.load_lora_weights(
    <span class="hljs-string">&quot;jbilcke-hf/sdxl-cinematic-1&quot;</span>, weight_name=<span class="hljs-string">&quot;pytorch_lora_weights.safetensors&quot;</span>, adapter_names=<span class="hljs-string">&quot;cinematic&quot;</span>
)
pipeline.delete_adapters(<span class="hljs-string">&quot;cinematic&quot;</span>)`,wrap:!1}}),{c(){t=s("p"),t.textContent=b,l=r(),f(c.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=b),l=n(a),p(c.$$.fragment,a)},m(a,w){L(a,t,w),L(a,l,w),m(c,a,w),v=!0},p:D,i(a){v||(_(c.$$.fragment,a),v=!0)},o(a){u(c.$$.fragment,a),v=!1},d(a){a&&(d(t),d(l)),h(c,a)}}}function Nb(T){let t,b="Example:",l,c,v;return c=new ae({props:{code:"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",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image
<span class="hljs-keyword">import</span> torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>, torch_dtype=torch.float16
).to(<span class="hljs-string">&quot;cuda&quot;</span>)
pipeline.load_lora_weights(
    <span class="hljs-string">&quot;jbilcke-hf/sdxl-cinematic-1&quot;</span>, weight_name=<span class="hljs-string">&quot;pytorch_lora_weights.safetensors&quot;</span>, adapter_name=<span class="hljs-string">&quot;cinematic&quot;</span>
)
pipeline.disable_lora()`,wrap:!1}}),{c(){t=s("p"),t.textContent=b,l=r(),f(c.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=b),l=n(a),p(c.$$.fragment,a)},m(a,w){L(a,t,w),L(a,l,w),m(c,a,w),v=!0},p:D,i(a){v||(_(c.$$.fragment,a),v=!0)},o(a){u(c.$$.fragment,a),v=!1},d(a){a&&(d(t),d(l)),h(c,a)}}}function zb(T){let t,b="Example:",l,c,v;return c=new ae({props:{code:"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",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image
<span class="hljs-keyword">import</span> torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>, torch_dtype=torch.float16
).to(<span class="hljs-string">&quot;cuda&quot;</span>)
pipeline.load_lora_weights(
    <span class="hljs-string">&quot;jbilcke-hf/sdxl-cinematic-1&quot;</span>, weight_name=<span class="hljs-string">&quot;pytorch_lora_weights.safetensors&quot;</span>, adapter_name=<span class="hljs-string">&quot;cinematic&quot;</span>
)
pipeline.enable_lora()`,wrap:!1}}),{c(){t=s("p"),t.textContent=b,l=r(),f(c.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=b),l=n(a),p(c.$$.fragment,a)},m(a,w){L(a,t,w),L(a,l,w),m(c,a,w),v=!0},p:D,i(a){v||(_(c.$$.fragment,a),v=!0)},o(a){u(c.$$.fragment,a),v=!1},d(a){a&&(d(t),d(l)),h(c,a)}}}function Yb(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function Qb(T){let t,b="Example:",l,c,v;return c=new ae({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMERpZmZ1c2lvblBpcGVsaW5lJTBBaW1wb3J0JTIwdG9yY2glMEElMEFwaXBlbGluZSUyMCUzRCUyMERpZmZ1c2lvblBpcGVsaW5lLmZyb21fcHJldHJhaW5lZCglMEElMjAlMjAlMjAlMjAlMjJzdGFiaWxpdHlhaSUyRnN0YWJsZS1kaWZmdXNpb24teGwtYmFzZS0xLjAlMjIlMkMlMjB0b3JjaF9kdHlwZSUzRHRvcmNoLmZsb2F0MTYlMEEpLnRvKCUyMmN1ZGElMjIpJTBBcGlwZWxpbmUubG9hZF9sb3JhX3dlaWdodHMoJTIybmVyaWpzJTJGcGl4ZWwtYXJ0LXhsJTIyJTJDJTIwd2VpZ2h0X25hbWUlM0QlMjJwaXhlbC1hcnQteGwuc2FmZXRlbnNvcnMlMjIlMkMlMjBhZGFwdGVyX25hbWUlM0QlMjJwaXhlbCUyMiklMEFwaXBlbGluZS5mdXNlX2xvcmEobG9yYV9zY2FsZSUzRDAuNyk=",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline
<span class="hljs-keyword">import</span> torch

pipeline = DiffusionPipeline.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>, torch_dtype=torch.float16
).to(<span class="hljs-string">&quot;cuda&quot;</span>)
pipeline.load_lora_weights(<span class="hljs-string">&quot;nerijs/pixel-art-xl&quot;</span>, weight_name=<span class="hljs-string">&quot;pixel-art-xl.safetensors&quot;</span>, adapter_name=<span class="hljs-string">&quot;pixel&quot;</span>)
pipeline.fuse_lora(lora_scale=<span class="hljs-number">0.7</span>)`,wrap:!1}}),{c(){t=s("p"),t.textContent=b,l=r(),f(c.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=b),l=n(a),p(c.$$.fragment,a)},m(a,w){L(a,t,w),L(a,l,w),m(c,a,w),v=!0},p:D,i(a){v||(_(c.$$.fragment,a),v=!0)},o(a){u(c.$$.fragment,a),v=!1},d(a){a&&(d(t),d(l)),h(c,a)}}}function Ob(T){let t,b="Example:",l,c,v;return c=new ae({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMERpZmZ1c2lvblBpcGVsaW5lJTBBJTBBcGlwZWxpbmUlMjAlM0QlMjBEaWZmdXNpb25QaXBlbGluZS5mcm9tX3ByZXRyYWluZWQoJTBBJTIwJTIwJTIwJTIwJTIyc3RhYmlsaXR5YWklMkZzdGFibGUtZGlmZnVzaW9uLXhsLWJhc2UtMS4wJTIyJTJDJTBBKS50byglMjJjdWRhJTIyKSUwQXBpcGVsaW5lLmxvYWRfbG9yYV93ZWlnaHRzKCUyMkNpcm9OMjAyMiUyRnRveS1mYWNlJTIyJTJDJTIwd2VpZ2h0X25hbWUlM0QlMjJ0b3lfZmFjZV9zZHhsLnNhZmV0ZW5zb3JzJTIyJTJDJTIwYWRhcHRlcl9uYW1lJTNEJTIydG95JTIyKSUwQXBpcGVsaW5lLmdldF9hY3RpdmVfYWRhcHRlcnMoKQ==",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>,
).to(<span class="hljs-string">&quot;cuda&quot;</span>)
pipeline.load_lora_weights(<span class="hljs-string">&quot;CiroN2022/toy-face&quot;</span>, weight_name=<span class="hljs-string">&quot;toy_face_sdxl.safetensors&quot;</span>, adapter_name=<span class="hljs-string">&quot;toy&quot;</span>)
pipeline.get_active_adapters()`,wrap:!1}}),{c(){t=s("p"),t.textContent=b,l=r(),f(c.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=b),l=n(a),p(c.$$.fragment,a)},m(a,w){L(a,t,w),L(a,l,w),m(c,a,w),v=!0},p:D,i(a){v||(_(c.$$.fragment,a),v=!0)},o(a){u(c.$$.fragment,a),v=!1},d(a){a&&(d(t),d(l)),h(c,a)}}}function Kb(T){let t,b="Example:",l,c,v;return c=new ae({props:{code:"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",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image
<span class="hljs-keyword">import</span> torch

pipeline = AutoPipelineForText2Image.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>, torch_dtype=torch.float16
).to(<span class="hljs-string">&quot;cuda&quot;</span>)
pipeline.load_lora_weights(
    <span class="hljs-string">&quot;jbilcke-hf/sdxl-cinematic-1&quot;</span>, weight_name=<span class="hljs-string">&quot;pytorch_lora_weights.safetensors&quot;</span>, adapter_name=<span class="hljs-string">&quot;cinematic&quot;</span>
)
pipeline.load_lora_weights(<span class="hljs-string">&quot;nerijs/pixel-art-xl&quot;</span>, weight_name=<span class="hljs-string">&quot;pixel-art-xl.safetensors&quot;</span>, adapter_name=<span class="hljs-string">&quot;pixel&quot;</span>)
pipeline.set_adapters([<span class="hljs-string">&quot;cinematic&quot;</span>, <span class="hljs-string">&quot;pixel&quot;</span>], adapter_weights=[<span class="hljs-number">0.5</span>, <span class="hljs-number">0.5</span>])`,wrap:!1}}),{c(){t=s("p"),t.textContent=b,l=r(),f(c.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=b),l=n(a),p(c.$$.fragment,a)},m(a,w){L(a,t,w),L(a,l,w),m(c,a,w),v=!0},p:D,i(a){v||(_(c.$$.fragment,a),v=!0)},o(a){u(c.$$.fragment,a),v=!1},d(a){a&&(d(t),d(l)),h(c,a)}}}function e2(T){let t,b;return t=new ae({props:{code:"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",highlighted:`<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.load_lora_weights(path_1, adapter_name=<span class="hljs-string">&quot;adapter-1&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.load_lora_weights(path_2, adapter_name=<span class="hljs-string">&quot;adapter-2&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.set_adapters(<span class="hljs-string">&quot;adapter-1&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>image_1 = pipe(**kwargs)
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># switch to adapter-2, offload adapter-1</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.set_lora_device(adapter_names=[<span class="hljs-string">&quot;adapter-1&quot;</span>], device=<span class="hljs-string">&quot;cpu&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.set_lora_device(adapter_names=[<span class="hljs-string">&quot;adapter-2&quot;</span>], device=<span class="hljs-string">&quot;cuda:0&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.set_adapters(<span class="hljs-string">&quot;adapter-2&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>image_2 = pipe(**kwargs)
<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># switch back to adapter-1, offload adapter-2</span>
<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.set_lora_device(adapter_names=[<span class="hljs-string">&quot;adapter-2&quot;</span>], device=<span class="hljs-string">&quot;cpu&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.set_lora_device(adapter_names=[<span class="hljs-string">&quot;adapter-1&quot;</span>], device=<span class="hljs-string">&quot;cuda:0&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>pipe.set_adapters(<span class="hljs-string">&quot;adapter-1&quot;</span>)
<span class="hljs-meta">&gt;&gt;&gt; </span>...`,wrap:!1}}),{c(){f(t.$$.fragment)},l(l){p(t.$$.fragment,l)},m(l,c){m(t,l,c),b=!0},p:D,i(l){b||(_(t.$$.fragment,l),b=!0)},o(l){u(t.$$.fragment,l),b=!1},d(l){h(t,l)}}}function o2(T){let t,b="This is an experimental API.";return{c(){t=s("p"),t.textContent=b},l(l){t=i(l,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=b)},m(l,c){L(l,t,c)},p:D,d(l){l&&d(t)}}}function t2(T){let t,b="Examples:",l,c,v;return c=new ae({props:{code:"JTIzJTIwQXNzdW1pbmclMjAlNjBwaXBlbGluZSU2MCUyMGlzJTIwYWxyZWFkeSUyMGxvYWRlZCUyMHdpdGglMjB0aGUlMjBMb1JBJTIwcGFyYW1ldGVycy4lMEFwaXBlbGluZS51bmxvYWRfbG9yYV93ZWlnaHRzKCklMEEuLi4=",highlighted:'<span class="hljs-meta">&gt;&gt;&gt; </span><span class="hljs-comment"># Assuming `pipeline` is already loaded with the LoRA parameters.</span>\n<span class="hljs-meta">&gt;&gt;&gt; </span>pipeline.unload_lora_weights()\n<span class="hljs-meta">&gt;&gt;&gt; </span>...',wrap:!1}}),{c(){t=s("p"),t.textContent=b,l=r(),f(c.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-kvfsh7"&&(t.textContent=b),l=n(a),p(c.$$.fragment,a)},m(a,w){L(a,t,w),L(a,l,w),m(c,a,w),v=!0},p:D,i(a){v||(_(c.$$.fragment,a),v=!0)},o(a){u(c.$$.fragment,a),v=!1},d(a){a&&(d(t),d(l)),h(c,a)}}}function a2(T){let t,b,l,c,v,a,w,_g='LoRA is a fast and lightweight training method that inserts and trains a significantly smaller number of parameters instead of all the model parameters. This produces a smaller file (~100 MBs) and makes it easier to quickly train a model to learn a new concept. LoRA weights are typically loaded into the denoiser, text encoder or both. The denoiser usually corresponds to a UNet (<a href="/docs/diffusers/pr_12242/en/api/models/unet2d-cond#diffusers.UNet2DConditionModel">UNet2DConditionModel</a>, for example) or a Transformer (<a href="/docs/diffusers/pr_12242/en/api/models/sd3_transformer2d#diffusers.SD3Transformer2DModel">SD3Transformer2DModel</a>, for example). There are several classes for loading LoRA weights:',dc,Ha,ug='<li><code>StableDiffusionLoraLoaderMixin</code> provides functions for loading and unloading, fusing and unfusing, enabling and disabling, and more functions for managing LoRA weights. This class can be used with any model.</li> <li><code>StableDiffusionXLLoraLoaderMixin</code> is a <a href="../../api/pipelines/stable_diffusion/stable_diffusion_xl">Stable Diffusion (SDXL)</a> version of the <code>StableDiffusionLoraLoaderMixin</code> class for loading and saving LoRA weights. It can only be used with the SDXL model.</li> <li><code>SD3LoraLoaderMixin</code> provides similar functions for <a href="https://huggingface.co/blog/sd3" rel="nofollow">Stable Diffusion 3</a>.</li> <li><code>FluxLoraLoaderMixin</code> provides similar functions for <a href="https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux" rel="nofollow">Flux</a>.</li> <li><code>CogVideoXLoraLoaderMixin</code> provides similar functions for <a href="https://huggingface.co/docs/diffusers/main/en/api/pipelines/cogvideox" rel="nofollow">CogVideoX</a>.</li> <li><code>Mochi1LoraLoaderMixin</code> provides similar functions for <a href="https://huggingface.co/docs/diffusers/main/en/api/pipelines/mochi" rel="nofollow">Mochi</a>.</li> <li><code>AuraFlowLoraLoaderMixin</code> provides similar functions for <a href="https://huggingface.co/fal/AuraFlow" rel="nofollow">AuraFlow</a>.</li> <li><code>LTXVideoLoraLoaderMixin</code> provides similar functions for <a href="https://huggingface.co/docs/diffusers/main/en/api/pipelines/ltx_video" rel="nofollow">LTX-Video</a>.</li> <li><code>SanaLoraLoaderMixin</code> provides similar functions for <a href="https://huggingface.co/docs/diffusers/main/en/api/pipelines/sana" rel="nofollow">Sana</a>.</li> <li><code>HunyuanVideoLoraLoaderMixin</code> provides similar functions for <a href="https://huggingface.co/docs/diffusers/main/en/api/pipelines/hunyuan_video" rel="nofollow">HunyuanVideo</a>.</li> <li><code>Lumina2LoraLoaderMixin</code> provides similar functions for <a href="https://huggingface.co/docs/diffusers/main/en/api/pipelines/lumina2" rel="nofollow">Lumina2</a>.</li> <li><code>WanLoraLoaderMixin</code> provides similar functions for <a href="https://huggingface.co/docs/diffusers/main/en/api/pipelines/wan" rel="nofollow">Wan</a>.</li> <li><code>SkyReelsV2LoraLoaderMixin</code> provides similar functions for <a href="https://huggingface.co/docs/diffusers/main/en/api/pipelines/skyreels_v2" rel="nofollow">SkyReels-V2</a>.</li> <li><code>CogView4LoraLoaderMixin</code> provides similar functions for <a href="https://huggingface.co/docs/diffusers/main/en/api/pipelines/cogview4" rel="nofollow">CogView4</a>.</li> <li><code>AmusedLoraLoaderMixin</code> is for the <a href="/docs/diffusers/pr_12242/en/api/pipelines/amused#diffusers.AmusedPipeline">AmusedPipeline</a>.</li> <li><code>HiDreamImageLoraLoaderMixin</code> provides similar functions for <a href="https://huggingface.co/docs/diffusers/main/en/api/pipelines/hidream" rel="nofollow">HiDream Image</a></li> <li><code>QwenImageLoraLoaderMixin</code> provides similar functions for <a href="https://huggingface.co/docs/diffusers/main/en/api/pipelines/qwen" rel="nofollow">Qwen Image</a></li> <li><code>LoraBaseMixin</code> provides a base class with several utility methods to fuse, unfuse, unload, LoRAs and more.</li>',lc,Fo,cc,ja,fc,S,Za,If,Ys,hg="Utility class for handling LoRAs.",Uf,Se,Ga,Vf,Qs,gg="Delete an adapter’s LoRA layers from the pipeline.",Wf,Jo,Xf,ke,qa,Pf,Os,xg="Disables the active LoRA layers of the pipeline.",Ff,Ho,Jf,Re,Ba,Hf,Ks,Lg="Enables the active LoRA layers of the pipeline.",jf,jo,Zf,Zo,Ea,Gf,ei,bg=`Hotswap adapters without triggering recompilation of a model or if the ranks of the loaded adapters are
different.`,qf,ve,Na,Bf,oi,wg="Fuses the LoRA parameters into the original parameters of the corresponding blocks.",Ef,Go,Nf,qo,zf,Ae,za,Yf,ti,vg="Gets the list of the current active adapters.",Qf,Bo,Of,Eo,Ya,Kf,ai,$g="Gets the current list of all available adapters in the pipeline.",ep,Ie,Qa,op,ri,yg="Set the currently active adapters for use in the pipeline.",tp,No,ap,$e,Oa,rp,ni,Mg=`Moves the LoRAs listed in <code>adapter_names</code> to a target device. Useful for offloading the LoRA to the CPU in case
you want to load multiple adapters and free some GPU memory.`,np,si,Tg=`After offloading the LoRA adapters to CPU, as long as the rest of the model is still on GPU, the LoRA adapters
can no longer be used for inference, as that would cause a device mismatch. Remember to set the device back to
GPU before using those LoRA adapters for inference.`,sp,zo,ip,Ue,Ka,dp,ii,Dg=`Reverses the effect of
<a href="https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraBaseMixin.fuse_lora" rel="nofollow"><code>pipe.fuse_lora()</code></a>.`,lp,Yo,cp,Ve,er,fp,di,Cg="Unloads the LoRA parameters.",pp,Qo,mp,Oo,or,_p,li,Sg="Writes the state dict of the LoRA layers (optionally with metadata) to disk.",pc,tr,mc,P,ar,up,ci,kg=`Load LoRA layers into Stable Diffusion <a href="/docs/diffusers/pr_12242/en/api/models/unet2d-cond#diffusers.UNet2DConditionModel">UNet2DConditionModel</a> and
<a href="https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel" rel="nofollow"><code>CLIPTextModel</code></a>.`,hp,Ko,rr,gp,fi,Rg="This will load the LoRA layers specified in <code>state_dict</code> into <code>text_encoder</code>",xp,et,nr,Lp,pi,Ag="This will load the LoRA layers specified in <code>state_dict</code> into <code>unet</code>.",bp,re,sr,wp,mi,Ig=`Load LoRA weights specified in <code>pretrained_model_name_or_path_or_dict</code> into <code>self.unet</code> and
<code>self.text_encoder</code>.`,vp,_i,Ug="All kwargs are forwarded to <code>self.lora_state_dict</code>.",$p,ui,Vg=`See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is
loaded.`,yp,hi,Wg=`See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_unet">load_lora_into_unet()</a> for more details on how the state dict is
loaded into <code>self.unet</code>.`,Mp,gi,Xg=`See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_text_encoder">load_lora_into_text_encoder()</a> for more details on how the state
dict is loaded into <code>self.text_encoder</code>.`,Tp,We,ir,Dp,xi,Pg="Return state dict for lora weights and the network alphas.",Cp,ot,Sp,tt,dr,kp,Li,Fg="Save the LoRA parameters corresponding to the UNet and text encoder.",_c,lr,uc,F,cr,Rp,bi,Jg=`Load LoRA layers into Stable Diffusion XL <a href="/docs/diffusers/pr_12242/en/api/models/unet2d-cond#diffusers.UNet2DConditionModel">UNet2DConditionModel</a>,
<a href="https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel" rel="nofollow"><code>CLIPTextModel</code></a>, and
<a href="https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModelWithProjection" rel="nofollow"><code>CLIPTextModelWithProjection</code></a>.`,Ap,at,fr,Ip,wi,Hg="This will load the LoRA layers specified in <code>state_dict</code> into <code>text_encoder</code>",Up,rt,pr,Vp,vi,jg="This will load the LoRA layers specified in <code>state_dict</code> into <code>unet</code>.",Wp,ne,mr,Xp,$i,Zg=`Load LoRA weights specified in <code>pretrained_model_name_or_path_or_dict</code> into <code>self.unet</code> and
<code>self.text_encoder</code>.`,Pp,yi,Gg="All kwargs are forwarded to <code>self.lora_state_dict</code>.",Fp,Mi,qg=`See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is
loaded.`,Jp,Ti,Bg=`See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_unet">load_lora_into_unet()</a> for more details on how the state dict is
loaded into <code>self.unet</code>.`,Hp,Di,Eg=`See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_text_encoder">load_lora_into_text_encoder()</a> for more details on how the state
dict is loaded into <code>self.text_encoder</code>.`,jp,Xe,_r,Zp,Ci,Ng="Return state dict for lora weights and the network alphas.",Gp,nt,qp,st,ur,Bp,Si,zg="Save the LoRA parameters corresponding to the UNet and text encoder.",hc,hr,gc,U,gr,Ep,ki,Yg=`Load LoRA layers into <a href="/docs/diffusers/pr_12242/en/api/models/sd3_transformer2d#diffusers.SD3Transformer2DModel">SD3Transformer2DModel</a>,
<a href="https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel" rel="nofollow"><code>CLIPTextModel</code></a>, and
<a href="https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModelWithProjection" rel="nofollow"><code>CLIPTextModelWithProjection</code></a>.`,Np,Ri,Qg='Specific to <a href="/docs/diffusers/pr_12242/en/api/pipelines/stable_diffusion/stable_diffusion_3#diffusers.StableDiffusion3Pipeline">StableDiffusion3Pipeline</a>.',zp,it,xr,Yp,Ai,Og="This will load the LoRA layers specified in <code>state_dict</code> into <code>text_encoder</code>",Qp,dt,Lr,Op,Ii,Kg="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",Kp,de,br,em,Ui,ex=`Load LoRA weights specified in <code>pretrained_model_name_or_path_or_dict</code> into <code>self.unet</code> and
<code>self.text_encoder</code>.`,om,Vi,ox="All kwargs are forwarded to <code>self.lora_state_dict</code>.",tm,Wi,tx=`See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is
loaded.`,am,Xi,ax=`See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,rm,Pe,wr,nm,Pi,rx="Return state dict for lora weights and the network alphas.",sm,lt,im,ct,vr,dm,Fi,nx="Save the LoRA parameters corresponding to the UNet and text encoder.",lm,Fe,$r,cm,Ji,sx=`Reverses the effect of
<a href="https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraBaseMixin.fuse_lora" rel="nofollow"><code>pipe.fuse_lora()</code></a>.`,fm,ft,xc,yr,Lc,I,Mr,pm,Hi,ix=`Load LoRA layers into <a href="/docs/diffusers/pr_12242/en/api/models/flux_transformer#diffusers.FluxTransformer2DModel">FluxTransformer2DModel</a>,
<a href="https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel" rel="nofollow"><code>CLIPTextModel</code></a>.`,mm,ji,dx='Specific to <a href="/docs/diffusers/pr_12242/en/api/pipelines/stable_diffusion/stable_diffusion_3#diffusers.StableDiffusion3Pipeline">StableDiffusion3Pipeline</a>.',_m,pt,Tr,um,Zi,lx="This will load the LoRA layers specified in <code>state_dict</code> into <code>text_encoder</code>",hm,mt,Dr,gm,Gi,cx="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",xm,le,Cr,Lm,qi,fx=`Load LoRA weights specified in <code>pretrained_model_name_or_path_or_dict</code> into <code>self.transformer</code> and
<code>self.text_encoder</code>.`,bm,Bi,px="All kwargs are forwarded to <code>self.lora_state_dict</code>.",wm,Ei,mx=`See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is
loaded.`,vm,Ni,_x=`See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,$m,Je,Sr,ym,zi,ux="Return state dict for lora weights and the network alphas.",Mm,_t,Tm,ut,kr,Dm,Yi,hx="Save the LoRA parameters corresponding to the UNet and text encoder.",Cm,He,Rr,Sm,Qi,gx=`Reverses the effect of
<a href="https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraBaseMixin.fuse_lora" rel="nofollow"><code>pipe.fuse_lora()</code></a>.`,km,ht,Rm,je,Ar,Am,Oi,xx="Unloads the LoRA parameters.",Im,gt,bc,Ir,wc,J,Ur,Um,Ki,Lx='Load LoRA layers into <a href="/docs/diffusers/pr_12242/en/api/models/cogvideox_transformer3d#diffusers.CogVideoXTransformer3DModel">CogVideoXTransformer3DModel</a>. Specific to <a href="/docs/diffusers/pr_12242/en/api/pipelines/cogvideox#diffusers.CogVideoXPipeline">CogVideoXPipeline</a>.',Vm,xt,Vr,Wm,ed,bx="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",Xm,Lt,Wr,Pm,od,wx=`Load LoRA weights specified in <code>pretrained_model_name_or_path_or_dict</code> into <code>self.transformer</code> and
<code>self.text_encoder</code>. All kwargs are forwarded to <code>self.lora_state_dict</code>. See
<a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is loaded.
See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,Fm,Ze,Xr,Jm,td,vx="Return state dict for lora weights and the network alphas.",Hm,bt,jm,wt,Pr,Zm,ad,$x="Save the LoRA parameters corresponding to the transformer.",Gm,Ge,Fr,qm,rd,yx=`Reverses the effect of
<a href="https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraBaseMixin.fuse_lora" rel="nofollow"><code>pipe.fuse_lora()</code></a>.`,Bm,vt,vc,Jr,$c,H,Hr,Em,nd,Mx='Load LoRA layers into <a href="/docs/diffusers/pr_12242/en/api/models/mochi_transformer3d#diffusers.MochiTransformer3DModel">MochiTransformer3DModel</a>. Specific to <a href="/docs/diffusers/pr_12242/en/api/pipelines/mochi#diffusers.MochiPipeline">MochiPipeline</a>.',Nm,$t,jr,zm,sd,Tx="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",Ym,yt,Zr,Qm,id,Dx=`Load LoRA weights specified in <code>pretrained_model_name_or_path_or_dict</code> into <code>self.transformer</code> and
<code>self.text_encoder</code>. All kwargs are forwarded to <code>self.lora_state_dict</code>. See
<a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is loaded.
See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,Om,qe,Gr,Km,dd,Cx="Return state dict for lora weights and the network alphas.",e_,Mt,o_,Tt,qr,t_,ld,Sx="Save the LoRA parameters corresponding to the transformer.",a_,Be,Br,r_,cd,kx=`Reverses the effect of
<a href="https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraBaseMixin.fuse_lora" rel="nofollow"><code>pipe.fuse_lora()</code></a>.`,n_,Dt,yc,Er,Mc,j,Nr,s_,fd,Rx='Load LoRA layers into <a href="/docs/diffusers/pr_12242/en/api/models/aura_flow_transformer2d#diffusers.AuraFlowTransformer2DModel">AuraFlowTransformer2DModel</a> Specific to <a href="/docs/diffusers/pr_12242/en/api/pipelines/aura_flow#diffusers.AuraFlowPipeline">AuraFlowPipeline</a>.',i_,Ct,zr,d_,pd,Ax="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",l_,St,Yr,c_,md,Ix=`Load LoRA weights specified in <code>pretrained_model_name_or_path_or_dict</code> into <code>self.transformer</code> and
<code>self.text_encoder</code>. All kwargs are forwarded to <code>self.lora_state_dict</code>. See
<a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is loaded.
See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,f_,Ee,Qr,p_,_d,Ux="Return state dict for lora weights and the network alphas.",m_,kt,__,Rt,Or,u_,ud,Vx="Save the LoRA parameters corresponding to the transformer.",h_,Ne,Kr,g_,hd,Wx=`Reverses the effect of
<a href="https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraBaseMixin.fuse_lora" rel="nofollow"><code>pipe.fuse_lora()</code></a>.`,x_,At,Tc,en,Dc,Z,on,L_,gd,Xx='Load LoRA layers into <a href="/docs/diffusers/pr_12242/en/api/models/ltx_video_transformer3d#diffusers.LTXVideoTransformer3DModel">LTXVideoTransformer3DModel</a>. Specific to <a href="/docs/diffusers/pr_12242/en/api/pipelines/ltx_video#diffusers.LTXPipeline">LTXPipeline</a>.',b_,It,tn,w_,xd,Px="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",v_,Ut,an,$_,Ld,Fx=`Load LoRA weights specified in <code>pretrained_model_name_or_path_or_dict</code> into <code>self.transformer</code> and
<code>self.text_encoder</code>. All kwargs are forwarded to <code>self.lora_state_dict</code>. See
<a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is loaded.
See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,y_,ze,rn,M_,bd,Jx="Return state dict for lora weights and the network alphas.",T_,Vt,D_,Wt,nn,C_,wd,Hx="Save the LoRA parameters corresponding to the transformer.",S_,Ye,sn,k_,vd,jx=`Reverses the effect of
<a href="https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraBaseMixin.fuse_lora" rel="nofollow"><code>pipe.fuse_lora()</code></a>.`,R_,Xt,Cc,dn,Sc,G,ln,A_,$d,Zx='Load LoRA layers into <a href="/docs/diffusers/pr_12242/en/api/models/sana_transformer2d#diffusers.SanaTransformer2DModel">SanaTransformer2DModel</a>. Specific to <a href="/docs/diffusers/pr_12242/en/api/pipelines/sana#diffusers.SanaPipeline">SanaPipeline</a>.',I_,Pt,cn,U_,yd,Gx="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",V_,Ft,fn,W_,Md,qx=`Load LoRA weights specified in <code>pretrained_model_name_or_path_or_dict</code> into <code>self.transformer</code> and
<code>self.text_encoder</code>. All kwargs are forwarded to <code>self.lora_state_dict</code>. See
<a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is loaded.
See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,X_,Qe,pn,P_,Td,Bx="Return state dict for lora weights and the network alphas.",F_,Jt,J_,Ht,mn,H_,Dd,Ex="Save the LoRA parameters corresponding to the transformer.",j_,Oe,_n,Z_,Cd,Nx=`Reverses the effect of
<a href="https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraBaseMixin.fuse_lora" rel="nofollow"><code>pipe.fuse_lora()</code></a>.`,G_,jt,kc,un,Rc,q,hn,q_,Sd,zx='Load LoRA layers into <a href="/docs/diffusers/pr_12242/en/api/models/hunyuan_video_transformer_3d#diffusers.HunyuanVideoTransformer3DModel">HunyuanVideoTransformer3DModel</a>. Specific to <a href="/docs/diffusers/pr_12242/en/api/pipelines/hunyuan_video#diffusers.HunyuanVideoPipeline">HunyuanVideoPipeline</a>.',B_,Zt,gn,E_,kd,Yx="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",N_,Gt,xn,z_,Rd,Qx=`Load LoRA weights specified in <code>pretrained_model_name_or_path_or_dict</code> into <code>self.transformer</code> and
<code>self.text_encoder</code>. All kwargs are forwarded to <code>self.lora_state_dict</code>. See
<a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is loaded.
See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,Y_,Ke,Ln,Q_,Ad,Ox="Return state dict for lora weights and the network alphas.",O_,qt,K_,Bt,bn,eu,Id,Kx="Save the LoRA parameters corresponding to the transformer.",ou,eo,wn,tu,Ud,eL=`Reverses the effect of
<a href="https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraBaseMixin.fuse_lora" rel="nofollow"><code>pipe.fuse_lora()</code></a>.`,au,Et,Ac,vn,Ic,B,$n,ru,Vd,oL='Load LoRA layers into <a href="/docs/diffusers/pr_12242/en/api/models/lumina2_transformer2d#diffusers.Lumina2Transformer2DModel">Lumina2Transformer2DModel</a>. Specific to <code>Lumina2Text2ImgPipeline</code>.',nu,Nt,yn,su,Wd,tL="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",iu,zt,Mn,du,Xd,aL=`Load LoRA weights specified in <code>pretrained_model_name_or_path_or_dict</code> into <code>self.transformer</code> and
<code>self.text_encoder</code>. All kwargs are forwarded to <code>self.lora_state_dict</code>. See
<a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is loaded.
See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,lu,oo,Tn,cu,Pd,rL="Return state dict for lora weights and the network alphas.",fu,Yt,pu,Qt,Dn,mu,Fd,nL="Save the LoRA parameters corresponding to the transformer.",_u,to,Cn,uu,Jd,sL=`Reverses the effect of
<a href="https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraBaseMixin.fuse_lora" rel="nofollow"><code>pipe.fuse_lora()</code></a>.`,hu,Ot,Uc,Sn,Vc,E,kn,gu,Hd,iL='Load LoRA layers into <a href="/docs/diffusers/pr_12242/en/api/models/wan_transformer_3d#diffusers.WanTransformer3DModel">WanTransformer3DModel</a>. Specific to <a href="/docs/diffusers/pr_12242/en/api/pipelines/cogview4#diffusers.CogView4Pipeline">CogView4Pipeline</a>.',xu,Kt,Rn,Lu,jd,dL="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",bu,ea,An,wu,Zd,lL=`Load LoRA weights specified in <code>pretrained_model_name_or_path_or_dict</code> into <code>self.transformer</code> and
<code>self.text_encoder</code>. All kwargs are forwarded to <code>self.lora_state_dict</code>. See
<a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is loaded.
See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,vu,ao,In,$u,Gd,cL="Return state dict for lora weights and the network alphas.",yu,oa,Mu,ta,Un,Tu,qd,fL="Save the LoRA parameters corresponding to the transformer.",Du,ro,Vn,Cu,Bd,pL=`Reverses the effect of
<a href="https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraBaseMixin.fuse_lora" rel="nofollow"><code>pipe.fuse_lora()</code></a>.`,Su,aa,Wc,Wn,Xc,N,Xn,ku,Ed,mL='Load LoRA layers into <a href="/docs/diffusers/pr_12242/en/api/models/wan_transformer_3d#diffusers.WanTransformer3DModel">WanTransformer3DModel</a>. Specific to <a href="/docs/diffusers/pr_12242/en/api/pipelines/wan#diffusers.WanPipeline">WanPipeline</a> and <code>[WanImageToVideoPipeline</code>].',Ru,ra,Pn,Au,Nd,_L="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",Iu,na,Fn,Uu,zd,uL=`Load LoRA weights specified in <code>pretrained_model_name_or_path_or_dict</code> into <code>self.transformer</code> and
<code>self.text_encoder</code>. All kwargs are forwarded to <code>self.lora_state_dict</code>. See
<a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is loaded.
See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,Vu,no,Jn,Wu,Yd,hL="Return state dict for lora weights and the network alphas.",Xu,sa,Pu,ia,Hn,Fu,Qd,gL="Save the LoRA parameters corresponding to the transformer.",Ju,so,jn,Hu,Od,xL=`Reverses the effect of
<a href="https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraBaseMixin.fuse_lora" rel="nofollow"><code>pipe.fuse_lora()</code></a>.`,ju,da,Pc,Zn,Fc,z,Gn,Zu,Kd,LL='Load LoRA layers into <a href="/docs/diffusers/pr_12242/en/api/models/skyreels_v2_transformer_3d#diffusers.SkyReelsV2Transformer3DModel">SkyReelsV2Transformer3DModel</a>.',Gu,la,qn,qu,el,bL="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",Bu,ca,Bn,Eu,ol,wL=`Load LoRA weights specified in <code>pretrained_model_name_or_path_or_dict</code> into <code>self.transformer</code> and
<code>self.text_encoder</code>. All kwargs are forwarded to <code>self.lora_state_dict</code>. See
<a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is loaded.
See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,Nu,io,En,zu,tl,vL="Return state dict for lora weights and the network alphas.",Yu,fa,Qu,pa,Nn,Ou,al,$L="Save the LoRA parameters corresponding to the transformer.",Ku,lo,zn,eh,rl,yL=`Reverses the effect of
<a href="https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraBaseMixin.fuse_lora" rel="nofollow"><code>pipe.fuse_lora()</code></a>.`,oh,ma,Jc,Yn,Hc,Te,Qn,th,_a,On,ah,nl,ML="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",rh,ua,Kn,nh,sl,TL="Save the LoRA parameters corresponding to the UNet and text encoder.",jc,es,Zc,Y,os,sh,il,DL='Load LoRA layers into <a href="/docs/diffusers/pr_12242/en/api/models/hidream_image_transformer#diffusers.HiDreamImageTransformer2DModel">HiDreamImageTransformer2DModel</a>. Specific to <a href="/docs/diffusers/pr_12242/en/api/pipelines/hidream#diffusers.HiDreamImagePipeline">HiDreamImagePipeline</a>.',ih,ha,ts,dh,dl,CL="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",lh,ga,as,ch,ll,SL=`Load LoRA weights specified in <code>pretrained_model_name_or_path_or_dict</code> into <code>self.transformer</code> and
<code>self.text_encoder</code>. All kwargs are forwarded to <code>self.lora_state_dict</code>. See
<a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is loaded.
See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,fh,co,rs,ph,cl,kL="Return state dict for lora weights and the network alphas.",mh,xa,_h,La,ns,uh,fl,RL="Save the LoRA parameters corresponding to the transformer.",hh,fo,ss,gh,pl,AL=`Reverses the effect of
<a href="https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraBaseMixin.fuse_lora" rel="nofollow"><code>pipe.fuse_lora()</code></a>.`,xh,ba,Gc,is,qc,Q,ds,Lh,ml,IL='Load LoRA layers into <a href="/docs/diffusers/pr_12242/en/api/models/qwenimage_transformer2d#diffusers.QwenImageTransformer2DModel">QwenImageTransformer2DModel</a>. Specific to <a href="/docs/diffusers/pr_12242/en/api/pipelines/qwenimage#diffusers.QwenImagePipeline">QwenImagePipeline</a>.',bh,wa,ls,wh,_l,UL="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",vh,va,cs,$h,ul,VL=`Load LoRA weights specified in <code>pretrained_model_name_or_path_or_dict</code> into <code>self.transformer</code> and
<code>self.text_encoder</code>. All kwargs are forwarded to <code>self.lora_state_dict</code>. See
<a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is loaded.
See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,yh,po,fs,Mh,hl,WL="Return state dict for lora weights and the network alphas.",Th,$a,Dh,ya,ps,Ch,gl,XL="Save the LoRA parameters corresponding to the transformer.",Sh,mo,ms,kh,xl,PL=`Reverses the effect of
<a href="https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraBaseMixin.fuse_lora" rel="nofollow"><code>pipe.fuse_lora()</code></a>.`,Rh,Ma,Bc,_s,Ec,k,us,Ah,Ll,FL="Utility class for handling LoRAs.",Ih,_o,hs,Uh,bl,JL="Delete an adapter’s LoRA layers from the pipeline.",Vh,Ta,Wh,uo,gs,Xh,wl,HL="Disables the active LoRA layers of the pipeline.",Ph,Da,Fh,ho,xs,Jh,vl,jL="Enables the active LoRA layers of the pipeline.",Hh,Ca,jh,Sa,Ls,Zh,$l,ZL=`Hotswap adapters without triggering recompilation of a model or if the ranks of the loaded adapters are
different.`,Gh,ye,bs,qh,yl,GL="Fuses the LoRA parameters into the original parameters of the corresponding blocks.",Bh,ka,Eh,Ra,Nh,go,ws,zh,Ml,qL="Gets the list of the current active adapters.",Yh,Aa,Qh,Ia,vs,Oh,Tl,BL="Gets the current list of all available adapters in the pipeline.",Kh,xo,$s,eg,Dl,EL="Set the currently active adapters for use in the pipeline.",og,Ua,tg,Me,ys,ag,Cl,NL=`Moves the LoRAs listed in <code>adapter_names</code> to a target device. Useful for offloading the LoRA to the CPU in case
you want to load multiple adapters and free some GPU memory.`,rg,Sl,zL=`After offloading the LoRA adapters to CPU, as long as the rest of the model is still on GPU, the LoRA adapters
can no longer be used for inference, as that would cause a device mismatch. Remember to set the device back to
GPU before using those LoRA adapters for inference.`,ng,Va,sg,Lo,Ms,ig,kl,YL=`Reverses the effect of
<a href="https://huggingface.co/docs/diffusers/main/en/api/loaders#diffusers.loaders.LoraBaseMixin.fuse_lora" rel="nofollow"><code>pipe.fuse_lora()</code></a>.`,dg,Wa,lg,bo,Ts,cg,Rl,QL="Unloads the LoRA parameters.",fg,Xa,pg,Pa,Ds,mg,Al,OL="Writes the state dict of the LoRA layers (optionally with metadata) to disk.",Nc,Cs,zc,ic,Yc;return v=new X({props:{title:"LoRA",local:"lora",headingTag:"h1"}}),Fo=new C({props:{$$slots:{default:[nb]},$$scope:{ctx:T}}}),ja=new X({props:{title:"LoraBaseMixin",local:"diffusers.loaders.lora_base.LoraBaseMixin",headingTag:"h2"}}),Za=new M({props:{name:"class diffusers.loaders.lora_base.LoraBaseMixin",anchor:"diffusers.loaders.lora_base.LoraBaseMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L478"}}),Ga=new M({props:{name:"delete_adapters",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.delete_adapters",parameters:[{name:"adapter_names",val:": typing.Union[typing.List[str], str]"}],parametersDescription:[{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.delete_adapters.adapter_names",description:`<strong>adapter_names</strong> (<code>Union[List[str], str]</code>) &#x2014;
The names of the adapters to delete.`,name:"adapter_names"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L846"}}),Jo=new te({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.delete_adapters.example",$$slots:{default:[sb]},$$scope:{ctx:T}}}),qa=new M({props:{name:"disable_lora",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.disable_lora",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L786"}}),Ho=new te({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.disable_lora.example",$$slots:{default:[ib]},$$scope:{ctx:T}}}),Ba=new M({props:{name:"enable_lora",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.enable_lora",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L816"}}),jo=new te({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.enable_lora.example",$$slots:{default:[db]},$$scope:{ctx:T}}}),Ea=new M({props:{name:"enable_lora_hotswap",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.enable_lora_hotswap",parameters:[{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.enable_lora_hotswap.target_rank",description:`<strong>target_rank</strong> (<code>int</code>) &#x2014;
The highest rank among all the adapters that will be loaded.`,name:"target_rank"},{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.enable_lora_hotswap.check_compiled",description:`<strong>check_compiled</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;error&quot;</code>) &#x2014;
How to handle a model that is already compiled. The check can return the following messages:<ul>
<li>&#x201C;error&#x201D; (default): raise an error</li>
<li>&#x201C;warn&#x201D;: issue a warning</li>
<li>&#x201C;ignore&#x201D;: do nothing</li>
</ul>`,name:"check_compiled"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L993"}}),Na=new M({props:{name:"fuse_lora",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.fuse_lora",parameters:[{name:"components",val:": typing.List[str] = []"},{name:"lora_scale",val:": float = 1.0"},{name:"safe_fusing",val:": bool = False"},{name:"adapter_names",val:": typing.Optional[typing.List[str]] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.fuse_lora.components",description:"<strong>components</strong> &#x2014; (<code>List[str]</code>): List of LoRA-injectable components to fuse the LoRAs into.",name:"components"},{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.fuse_lora.lora_scale",description:`<strong>lora_scale</strong> (<code>float</code>, defaults to 1.0) &#x2014;
Controls how much to influence the outputs with the LoRA parameters.`,name:"lora_scale"},{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.fuse_lora.safe_fusing",description:`<strong>safe_fusing</strong> (<code>bool</code>, defaults to <code>False</code>) &#x2014;
Whether to check fused weights for NaN values before fusing and if values are NaN not fusing them.`,name:"safe_fusing"},{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.fuse_lora.adapter_names",description:`<strong>adapter_names</strong> (<code>List[str]</code>, <em>optional</em>) &#x2014;
Adapter names to be used for fusing. If nothing is passed, all active adapters will be fused.`,name:"adapter_names"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L536"}}),Go=new C({props:{warning:!0,$$slots:{default:[lb]},$$scope:{ctx:T}}}),qo=new te({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.fuse_lora.example",$$slots:{default:[cb]},$$scope:{ctx:T}}}),za=new M({props:{name:"get_active_adapters",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.get_active_adapters",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L884"}}),Bo=new te({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.get_active_adapters.example",$$slots:{default:[fb]},$$scope:{ctx:T}}}),Ya=new M({props:{name:"get_list_adapters",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.get_list_adapters",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L917"}}),Qa=new M({props:{name:"set_adapters",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_adapters",parameters:[{name:"adapter_names",val:": typing.Union[typing.List[str], str]"},{name:"adapter_weights",val:": typing.Union[float, typing.Dict, typing.List[float], typing.List[typing.Dict], NoneType] = None"}],parametersDescription:[{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_adapters.adapter_names",description:`<strong>adapter_names</strong> (<code>List[str]</code> or <code>str</code>) &#x2014;
The names of the adapters to use.`,name:"adapter_names"},{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_adapters.adapter_weights",description:`<strong>adapter_weights</strong> (<code>Union[List[float], float]</code>, <em>optional</em>) &#x2014;
The adapter(s) weights to use with the UNet. If <code>None</code>, the weights are set to <code>1.0</code> for all the
adapters.`,name:"adapter_weights"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L683"}}),No=new te({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_adapters.example",$$slots:{default:[pb]},$$scope:{ctx:T}}}),Oa=new M({props:{name:"set_lora_device",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_lora_device",parameters:[{name:"adapter_names",val:": typing.List[str]"},{name:"device",val:": typing.Union[torch.device, str, int]"}],parametersDescription:[{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_lora_device.adapter_names",description:`<strong>adapter_names</strong> (<code>List[str]</code>) &#x2014;
List of adapters to send device to.`,name:"adapter_names"},{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_lora_device.device",description:`<strong>device</strong> (<code>Union[torch.device, str, int]</code>) &#x2014;
Device to send the adapters to. Can be either a torch device, a str or an integer.`,name:"device"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L939"}}),zo=new te({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_lora_device.example",$$slots:{default:[mb]},$$scope:{ctx:T}}}),Ka=new M({props:{name:"unfuse_lora",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.unfuse_lora",parameters:[{name:"components",val:": typing.List[str] = []"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.unfuse_lora.components",description:"<strong>components</strong> (<code>List[str]</code>) &#x2014; List of LoRA-injectable components to unfuse LoRA from.",name:"components"},{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.unfuse_lora.unfuse_unet",description:"<strong>unfuse_unet</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014; Whether to unfuse the UNet LoRA parameters.",name:"unfuse_unet"},{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.unfuse_lora.unfuse_text_encoder",description:`<strong>unfuse_text_encoder</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014;
Whether to unfuse the text encoder LoRA parameters. If the text encoder wasn&#x2019;t monkey-patched with the
LoRA parameters then it won&#x2019;t have any effect.`,name:"unfuse_text_encoder"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L626"}}),Yo=new C({props:{warning:!0,$$slots:{default:[_b]},$$scope:{ctx:T}}}),er=new M({props:{name:"unload_lora_weights",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.unload_lora_weights",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L513"}}),Qo=new te({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.unload_lora_weights.example",$$slots:{default:[ub]},$$scope:{ctx:T}}}),or=new M({props:{name:"write_lora_layers",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.write_lora_layers",parameters:[{name:"state_dict",val:": typing.Dict[str, torch.Tensor]"},{name:"save_directory",val:": str"},{name:"is_main_process",val:": bool"},{name:"weight_name",val:": str"},{name:"save_function",val:": typing.Callable"},{name:"safe_serialization",val:": bool"},{name:"lora_adapter_metadata",val:": typing.Optional[dict] = None"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L1016"}}),tr=new X({props:{title:"StableDiffusionLoraLoaderMixin",local:"diffusers.loaders.StableDiffusionLoraLoaderMixin",headingTag:"h2"}}),ar=new M({props:{name:"class diffusers.loaders.StableDiffusionLoraLoaderMixin",anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L128"}}),rr=new M({props:{name:"load_lora_into_text_encoder",anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_text_encoder",parameters:[{name:"state_dict",val:""},{name:"network_alphas",val:""},{name:"text_encoder",val:""},{name:"prefix",val:" = None"},{name:"lora_scale",val:" = 1.0"},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_text_encoder.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The key should be prefixed with an
additional <code>text_encoder</code> to distinguish between unet lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_text_encoder.network_alphas",description:`<strong>network_alphas</strong> (<code>Dict[str, float]</code>) &#x2014;
The value of the network alpha used for stable learning and preventing underflow. This value has the
same meaning as the <code>--network_alpha</code> option in the kohya-ss trainer script. Refer to <a href="https://github.com/darkstorm2150/sd-scripts/blob/main/docs/train_network_README-en.md#execute-learning" rel="nofollow">this
link</a>.`,name:"network_alphas"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_text_encoder.text_encoder",description:`<strong>text_encoder</strong> (<code>CLIPTextModel</code>) &#x2014;
The text encoder model to load the LoRA layers into.`,name:"text_encoder"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_text_encoder.prefix",description:`<strong>prefix</strong> (<code>str</code>) &#x2014;
Expected prefix of the <code>text_encoder</code> in the <code>state_dict</code>.`,name:"prefix"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_text_encoder.lora_scale",description:`<strong>lora_scale</strong> (<code>float</code>) &#x2014;
How much to scale the output of the lora linear layer before it is added with the output of the regular
lora layer.`,name:"lora_scale"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_text_encoder.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_text_encoder.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_text_encoder.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_text_encoder.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L416"}}),nr=new M({props:{name:"load_lora_into_unet",anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_unet",parameters:[{name:"state_dict",val:""},{name:"network_alphas",val:""},{name:"unet",val:""},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_unet.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The keys can either be indexed directly
into the unet or prefixed with an additional <code>unet</code> which can be used to distinguish between text
encoder lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_unet.network_alphas",description:`<strong>network_alphas</strong> (<code>Dict[str, float]</code>) &#x2014;
The value of the network alpha used for stable learning and preventing underflow. This value has the
same meaning as the <code>--network_alpha</code> option in the kohya-ss trainer script. Refer to <a href="https://github.com/darkstorm2150/sd-scripts/blob/main/docs/train_network_README-en.md#execute-learning" rel="nofollow">this
link</a>.`,name:"network_alphas"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_unet.unet",description:`<strong>unet</strong> (<code>UNet2DConditionModel</code>) &#x2014;
The UNet model to load the LoRA layers into.`,name:"unet"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_unet.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_unet.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_unet.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_into_unet.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L355"}}),sr=new M({props:{name:"load_lora_weights",anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"adapter_name",val:": typing.Optional[str] = None"},{name:"hotswap",val:": bool = False"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Defaults to <code>False</code>. Whether to substitute an existing (LoRA) adapter with the newly loaded adapter
in-place. This means that, instead of loading an additional adapter, this will take the existing
adapter weights and replace them with the weights of the new adapter. This can be faster and more
memory efficient. However, the main advantage of hotswapping is that when the model is compiled with
torch.compile, loading the new adapter does not require recompilation of the model. When using
hotswapping, the passed <code>adapter_name</code> should be the name of an already loaded adapter.</p>
<p>If the new adapter and the old adapter have different ranks and/or LoRA alphas (i.e. scaling), you need
to call an additional method before loading the adapter:`,name:"hotswap"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L138"}}),ir=new M({props:{name:"lora_state_dict",anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
Can be either:</p>
<ul>
<li>A string, the <em>model id</em> (for example <code>google/ddpm-celebahq-256</code>) of a pretrained model hosted on
the Hub.</li>
<li>A path to a <em>directory</em> (for example <code>./my_model_directory</code>) containing the model weights saved
with <a href="/docs/diffusers/pr_12242/en/api/models/overview#diffusers.ModelMixin.save_pretrained">ModelMixin.save_pretrained()</a>.</li>
<li>A <a href="https://pytorch.org/tutorials/beginner/saving_loading_models.html#what-is-a-state-dict" rel="nofollow">torch state
dict</a>.</li>
</ul>`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) &#x2014;
Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
is not used.`,name:"cache_dir"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether or not to force the (re-)download of the model weights and configuration files, overriding the
cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) &#x2014;
A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{&apos;http&apos;: &apos;foo.bar:3128&apos;, &apos;http://hostname&apos;: &apos;foo.bar:4012&apos;}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
won&#x2019;t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) &#x2014;
The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;main&quot;</code>) &#x2014;
The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
allowed by Git.`,name:"revision"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict.subfolder",description:`<strong>subfolder</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;&quot;</code>) &#x2014;
The subfolder location of a model file within a larger model repository on the Hub or locally.`,name:"subfolder"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict.weight_name",description:`<strong>weight_name</strong> (<code>str</code>, <em>optional</em>, defaults to None) &#x2014;
Name of the serialized state dict file.`,name:"weight_name"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict.return_lora_metadata",description:`<strong>return_lora_metadata</strong> (<code>bool</code>, <em>optional</em>, defaults to False) &#x2014;
When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.`,name:"return_lora_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L239"}}),ot=new C({props:{warning:!0,$$slots:{default:[hb]},$$scope:{ctx:T}}}),dr=new M({props:{name:"save_lora_weights",anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.save_lora_weights",parameters:[{name:"save_directory",val:": typing.Union[str, os.PathLike]"},{name:"unet_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"text_encoder_lora_layers",val:": typing.Dict[str, torch.nn.modules.module.Module] = None"},{name:"is_main_process",val:": bool = True"},{name:"weight_name",val:": str = None"},{name:"save_function",val:": typing.Callable = None"},{name:"safe_serialization",val:": bool = True"},{name:"unet_lora_adapter_metadata",val:" = None"},{name:"text_encoder_lora_adapter_metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.save_lora_weights.save_directory",description:`<strong>save_directory</strong> (<code>str</code> or <code>os.PathLike</code>) &#x2014;
Directory to save LoRA parameters to. Will be created if it doesn&#x2019;t exist.`,name:"save_directory"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.save_lora_weights.unet_lora_layers",description:`<strong>unet_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>unet</code>.`,name:"unet_lora_layers"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.save_lora_weights.text_encoder_lora_layers",description:`<strong>text_encoder_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>text_encoder</code>. Must explicitly pass the text
encoder LoRA state dict because it comes from &#x1F917; Transformers.`,name:"text_encoder_lora_layers"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.save_lora_weights.is_main_process",description:`<strong>is_main_process</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether the process calling this is the main process or not. Useful during distributed training and you
need to call this function on all processes. In this case, set <code>is_main_process=True</code> only on the main
process to avoid race conditions.`,name:"is_main_process"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.save_lora_weights.save_function",description:`<strong>save_function</strong> (<code>Callable</code>) &#x2014;
The function to use to save the state dictionary. Useful during distributed training when you need to
replace <code>torch.save</code> with another method. Can be configured with the environment variable
<code>DIFFUSERS_SAVE_MODE</code>.`,name:"save_function"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.save_lora_weights.safe_serialization",description:`<strong>safe_serialization</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to save the model using <code>safetensors</code> or the traditional PyTorch way with <code>pickle</code>.`,name:"safe_serialization"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.save_lora_weights.unet_lora_adapter_metadata",description:`<strong>unet_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the unet to be serialized with the state dict.`,name:"unet_lora_adapter_metadata"},{anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin.save_lora_weights.text_encoder_lora_adapter_metadata",description:`<strong>text_encoder_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the text encoder to be serialized with the state dict.`,name:"text_encoder_lora_adapter_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L474"}}),lr=new X({props:{title:"StableDiffusionXLLoraLoaderMixin",local:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin",headingTag:"h2"}}),cr=new M({props:{name:"class diffusers.loaders.StableDiffusionXLLoraLoaderMixin",anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L612"}}),fr=new M({props:{name:"load_lora_into_text_encoder",anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_text_encoder",parameters:[{name:"state_dict",val:""},{name:"network_alphas",val:""},{name:"text_encoder",val:""},{name:"prefix",val:" = None"},{name:"lora_scale",val:" = 1.0"},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_text_encoder.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The key should be prefixed with an
additional <code>text_encoder</code> to distinguish between unet lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_text_encoder.network_alphas",description:`<strong>network_alphas</strong> (<code>Dict[str, float]</code>) &#x2014;
The value of the network alpha used for stable learning and preventing underflow. This value has the
same meaning as the <code>--network_alpha</code> option in the kohya-ss trainer script. Refer to <a href="https://github.com/darkstorm2150/sd-scripts/blob/main/docs/train_network_README-en.md#execute-learning" rel="nofollow">this
link</a>.`,name:"network_alphas"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_text_encoder.text_encoder",description:`<strong>text_encoder</strong> (<code>CLIPTextModel</code>) &#x2014;
The text encoder model to load the LoRA layers into.`,name:"text_encoder"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_text_encoder.prefix",description:`<strong>prefix</strong> (<code>str</code>) &#x2014;
Expected prefix of the <code>text_encoder</code> in the <code>state_dict</code>.`,name:"prefix"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_text_encoder.lora_scale",description:`<strong>lora_scale</strong> (<code>float</code>) &#x2014;
How much to scale the output of the lora linear layer before it is added with the output of the regular
lora layer.`,name:"lora_scale"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_text_encoder.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_text_encoder.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_text_encoder.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_text_encoder.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L902"}}),pr=new M({props:{name:"load_lora_into_unet",anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_unet",parameters:[{name:"state_dict",val:""},{name:"network_alphas",val:""},{name:"unet",val:""},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_unet.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The keys can either be indexed directly
into the unet or prefixed with an additional <code>unet</code> which can be used to distinguish between text
encoder lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_unet.network_alphas",description:`<strong>network_alphas</strong> (<code>Dict[str, float]</code>) &#x2014;
The value of the network alpha used for stable learning and preventing underflow. This value has the
same meaning as the <code>--network_alpha</code> option in the kohya-ss trainer script. Refer to <a href="https://github.com/darkstorm2150/sd-scripts/blob/main/docs/train_network_README-en.md#execute-learning" rel="nofollow">this
link</a>.`,name:"network_alphas"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_unet.unet",description:`<strong>unet</strong> (<code>UNet2DConditionModel</code>) &#x2014;
The UNet model to load the LoRA layers into.`,name:"unet"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_unet.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_unet.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_unet.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_into_unet.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L840"}}),mr=new M({props:{name:"load_lora_weights",anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"adapter_name",val:": typing.Optional[str] = None"},{name:"hotswap",val:": bool = False"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L623"}}),_r=new M({props:{name:"lora_state_dict",anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.lora_state_dict",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.lora_state_dict.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
Can be either:</p>
<ul>
<li>A string, the <em>model id</em> (for example <code>google/ddpm-celebahq-256</code>) of a pretrained model hosted on
the Hub.</li>
<li>A path to a <em>directory</em> (for example <code>./my_model_directory</code>) containing the model weights saved
with <a href="/docs/diffusers/pr_12242/en/api/models/overview#diffusers.ModelMixin.save_pretrained">ModelMixin.save_pretrained()</a>.</li>
<li>A <a href="https://pytorch.org/tutorials/beginner/saving_loading_models.html#what-is-a-state-dict" rel="nofollow">torch state
dict</a>.</li>
</ul>`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.lora_state_dict.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) &#x2014;
Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
is not used.`,name:"cache_dir"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.lora_state_dict.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether or not to force the (re-)download of the model weights and configuration files, overriding the
cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.lora_state_dict.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) &#x2014;
A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{&apos;http&apos;: &apos;foo.bar:3128&apos;, &apos;http://hostname&apos;: &apos;foo.bar:4012&apos;}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.lora_state_dict.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
won&#x2019;t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.lora_state_dict.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) &#x2014;
The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.lora_state_dict.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;main&quot;</code>) &#x2014;
The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
allowed by Git.`,name:"revision"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.lora_state_dict.subfolder",description:`<strong>subfolder</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;&quot;</code>) &#x2014;
The subfolder location of a model file within a larger model repository on the Hub or locally.`,name:"subfolder"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.lora_state_dict.weight_name",description:`<strong>weight_name</strong> (<code>str</code>, <em>optional</em>, defaults to None) &#x2014;
Name of the serialized state dict file.`,name:"weight_name"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.lora_state_dict.return_lora_metadata",description:`<strong>return_lora_metadata</strong> (<code>bool</code>, <em>optional</em>, defaults to False) &#x2014;
When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.`,name:"return_lora_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L723"}}),nt=new C({props:{warning:!0,$$slots:{default:[gb]},$$scope:{ctx:T}}}),ur=new M({props:{name:"save_lora_weights",anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights",parameters:[{name:"save_directory",val:": typing.Union[str, os.PathLike]"},{name:"unet_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"text_encoder_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"text_encoder_2_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"is_main_process",val:": bool = True"},{name:"weight_name",val:": str = None"},{name:"save_function",val:": typing.Callable = None"},{name:"safe_serialization",val:": bool = True"},{name:"unet_lora_adapter_metadata",val:" = None"},{name:"text_encoder_lora_adapter_metadata",val:" = None"},{name:"text_encoder_2_lora_adapter_metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights.save_directory",description:`<strong>save_directory</strong> (<code>str</code> or <code>os.PathLike</code>) &#x2014;
Directory to save LoRA parameters to. Will be created if it doesn&#x2019;t exist.`,name:"save_directory"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights.unet_lora_layers",description:`<strong>unet_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>unet</code>.`,name:"unet_lora_layers"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights.text_encoder_lora_layers",description:`<strong>text_encoder_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>text_encoder</code>. Must explicitly pass the text
encoder LoRA state dict because it comes from &#x1F917; Transformers.`,name:"text_encoder_lora_layers"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights.text_encoder_2_lora_layers",description:`<strong>text_encoder_2_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>text_encoder_2</code>. Must explicitly pass the text
encoder LoRA state dict because it comes from &#x1F917; Transformers.`,name:"text_encoder_2_lora_layers"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights.is_main_process",description:`<strong>is_main_process</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether the process calling this is the main process or not. Useful during distributed training and you
need to call this function on all processes. In this case, set <code>is_main_process=True</code> only on the main
process to avoid race conditions.`,name:"is_main_process"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights.save_function",description:`<strong>save_function</strong> (<code>Callable</code>) &#x2014;
The function to use to save the state dictionary. Useful during distributed training when you need to
replace <code>torch.save</code> with another method. Can be configured with the environment variable
<code>DIFFUSERS_SAVE_MODE</code>.`,name:"save_function"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights.safe_serialization",description:`<strong>safe_serialization</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to save the model using <code>safetensors</code> or the traditional PyTorch way with <code>pickle</code>.`,name:"safe_serialization"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights.unet_lora_adapter_metadata",description:`<strong>unet_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the unet to be serialized with the state dict.`,name:"unet_lora_adapter_metadata"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights.text_encoder_lora_adapter_metadata",description:`<strong>text_encoder_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the text encoder to be serialized with the state dict.`,name:"text_encoder_lora_adapter_metadata"},{anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights.text_encoder_2_lora_adapter_metadata",description:`<strong>text_encoder_2_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the second text encoder to be serialized with the state dict.`,name:"text_encoder_2_lora_adapter_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L961"}}),hr=new X({props:{title:"SD3LoraLoaderMixin",local:"diffusers.loaders.SD3LoraLoaderMixin",headingTag:"h2"}}),gr=new M({props:{name:"class diffusers.loaders.SD3LoraLoaderMixin",anchor:"diffusers.loaders.SD3LoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L1115"}}),xr=new M({props:{name:"load_lora_into_text_encoder",anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_into_text_encoder",parameters:[{name:"state_dict",val:""},{name:"network_alphas",val:""},{name:"text_encoder",val:""},{name:"prefix",val:" = None"},{name:"lora_scale",val:" = 1.0"},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_into_text_encoder.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The key should be prefixed with an
additional <code>text_encoder</code> to distinguish between unet lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_into_text_encoder.network_alphas",description:`<strong>network_alphas</strong> (<code>Dict[str, float]</code>) &#x2014;
The value of the network alpha used for stable learning and preventing underflow. This value has the
same meaning as the <code>--network_alpha</code> option in the kohya-ss trainer script. Refer to <a href="https://github.com/darkstorm2150/sd-scripts/blob/main/docs/train_network_README-en.md#execute-learning" rel="nofollow">this
link</a>.`,name:"network_alphas"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_into_text_encoder.text_encoder",description:`<strong>text_encoder</strong> (<code>CLIPTextModel</code>) &#x2014;
The text encoder model to load the LoRA layers into.`,name:"text_encoder"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_into_text_encoder.prefix",description:`<strong>prefix</strong> (<code>str</code>) &#x2014;
Expected prefix of the <code>text_encoder</code> in the <code>state_dict</code>.`,name:"prefix"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_into_text_encoder.lora_scale",description:`<strong>lora_scale</strong> (<code>float</code>) &#x2014;
How much to scale the output of the lora linear layer before it is added with the output of the regular
lora layer.`,name:"lora_scale"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_into_text_encoder.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_into_text_encoder.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_into_text_encoder.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_into_text_encoder.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L1364"}}),Lr=new M({props:{name:"load_lora_into_transformer",anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_into_transformer",parameters:[{name:"state_dict",val:""},{name:"transformer",val:""},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_into_transformer.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The keys can either be indexed directly
into the unet or prefixed with an additional <code>unet</code> which can be used to distinguish between text
encoder lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_into_transformer.transformer",description:`<strong>transformer</strong> (<code>SD3Transformer2DModel</code>) &#x2014;
The Transformer model to load the LoRA layers into.`,name:"transformer"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_into_transformer.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_into_transformer.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_into_transformer.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_into_transformer.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L1314"}}),br=new M({props:{name:"load_lora_weights",anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_weights",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"adapter_name",val:" = None"},{name:"hotswap",val:": bool = False"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_weights.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_weights.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_weights.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_weights.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.load_lora_weights.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L1226"}}),wr=new M({props:{name:"lora_state_dict",anchor:"diffusers.loaders.SD3LoraLoaderMixin.lora_state_dict",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.SD3LoraLoaderMixin.lora_state_dict.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
Can be either:</p>
<ul>
<li>A string, the <em>model id</em> (for example <code>google/ddpm-celebahq-256</code>) of a pretrained model hosted on
the Hub.</li>
<li>A path to a <em>directory</em> (for example <code>./my_model_directory</code>) containing the model weights saved
with <a href="/docs/diffusers/pr_12242/en/api/models/overview#diffusers.ModelMixin.save_pretrained">ModelMixin.save_pretrained()</a>.</li>
<li>A <a href="https://pytorch.org/tutorials/beginner/saving_loading_models.html#what-is-a-state-dict" rel="nofollow">torch state
dict</a>.</li>
</ul>`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.lora_state_dict.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) &#x2014;
Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
is not used.`,name:"cache_dir"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.lora_state_dict.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether or not to force the (re-)download of the model weights and configuration files, overriding the
cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.lora_state_dict.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) &#x2014;
A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{&apos;http&apos;: &apos;foo.bar:3128&apos;, &apos;http://hostname&apos;: &apos;foo.bar:4012&apos;}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.lora_state_dict.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
won&#x2019;t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.lora_state_dict.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) &#x2014;
The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.lora_state_dict.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;main&quot;</code>) &#x2014;
The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
allowed by Git.`,name:"revision"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.lora_state_dict.subfolder",description:`<strong>subfolder</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;&quot;</code>) &#x2014;
The subfolder location of a model file within a larger model repository on the Hub or locally.`,name:"subfolder"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.lora_state_dict.return_lora_metadata",description:`<strong>return_lora_metadata</strong> (<code>bool</code>, <em>optional</em>, defaults to False) &#x2014;
When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.`,name:"return_lora_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L1128"}}),lt=new C({props:{warning:!0,$$slots:{default:[xb]},$$scope:{ctx:T}}}),vr=new M({props:{name:"save_lora_weights",anchor:"diffusers.loaders.SD3LoraLoaderMixin.save_lora_weights",parameters:[{name:"save_directory",val:": typing.Union[str, os.PathLike]"},{name:"transformer_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"text_encoder_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"text_encoder_2_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"is_main_process",val:": bool = True"},{name:"weight_name",val:": str = None"},{name:"save_function",val:": typing.Callable = None"},{name:"safe_serialization",val:": bool = True"},{name:"transformer_lora_adapter_metadata",val:" = None"},{name:"text_encoder_lora_adapter_metadata",val:" = None"},{name:"text_encoder_2_lora_adapter_metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.SD3LoraLoaderMixin.save_lora_weights.save_directory",description:`<strong>save_directory</strong> (<code>str</code> or <code>os.PathLike</code>) &#x2014;
Directory to save LoRA parameters to. Will be created if it doesn&#x2019;t exist.`,name:"save_directory"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.save_lora_weights.transformer_lora_layers",description:`<strong>transformer_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>transformer</code>.`,name:"transformer_lora_layers"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.save_lora_weights.text_encoder_lora_layers",description:`<strong>text_encoder_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>text_encoder</code>. Must explicitly pass the text
encoder LoRA state dict because it comes from &#x1F917; Transformers.`,name:"text_encoder_lora_layers"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.save_lora_weights.text_encoder_2_lora_layers",description:`<strong>text_encoder_2_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>text_encoder_2</code>. Must explicitly pass the text
encoder LoRA state dict because it comes from &#x1F917; Transformers.`,name:"text_encoder_2_lora_layers"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.save_lora_weights.is_main_process",description:`<strong>is_main_process</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether the process calling this is the main process or not. Useful during distributed training and you
need to call this function on all processes. In this case, set <code>is_main_process=True</code> only on the main
process to avoid race conditions.`,name:"is_main_process"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.save_lora_weights.save_function",description:`<strong>save_function</strong> (<code>Callable</code>) &#x2014;
The function to use to save the state dictionary. Useful during distributed training when you need to
replace <code>torch.save</code> with another method. Can be configured with the environment variable
<code>DIFFUSERS_SAVE_MODE</code>.`,name:"save_function"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.save_lora_weights.safe_serialization",description:`<strong>safe_serialization</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to save the model using <code>safetensors</code> or the traditional PyTorch way with <code>pickle</code>.`,name:"safe_serialization"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.save_lora_weights.transformer_lora_adapter_metadata",description:`<strong>transformer_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the transformer to be serialized with the state dict.`,name:"transformer_lora_adapter_metadata"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.save_lora_weights.text_encoder_lora_adapter_metadata",description:`<strong>text_encoder_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the text encoder to be serialized with the state dict.`,name:"text_encoder_lora_adapter_metadata"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.save_lora_weights.text_encoder_2_lora_adapter_metadata",description:`<strong>text_encoder_2_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the second text encoder to be serialized with the state dict.`,name:"text_encoder_2_lora_adapter_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L1423"}}),$r=new M({props:{name:"unfuse_lora",anchor:"diffusers.loaders.SD3LoraLoaderMixin.unfuse_lora",parameters:[{name:"components",val:": typing.List[str] = ['transformer', 'text_encoder', 'text_encoder_2']"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.SD3LoraLoaderMixin.unfuse_lora.components",description:"<strong>components</strong> (<code>List[str]</code>) &#x2014; List of LoRA-injectable components to unfuse LoRA from.",name:"components"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.unfuse_lora.unfuse_transformer",description:"<strong>unfuse_transformer</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014; Whether to unfuse the UNet LoRA parameters.",name:"unfuse_transformer"},{anchor:"diffusers.loaders.SD3LoraLoaderMixin.unfuse_lora.unfuse_text_encoder",description:`<strong>unfuse_text_encoder</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014;
Whether to unfuse the text encoder LoRA parameters. If the text encoder wasn&#x2019;t monkey-patched with the
LoRA parameters then it won&#x2019;t have any effect.`,name:"unfuse_text_encoder"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L1561"}}),ft=new C({props:{warning:!0,$$slots:{default:[Lb]},$$scope:{ctx:T}}}),yr=new X({props:{title:"FluxLoraLoaderMixin",local:"diffusers.loaders.FluxLoraLoaderMixin",headingTag:"h2"}}),Mr=new M({props:{name:"class diffusers.loaders.FluxLoraLoaderMixin",anchor:"diffusers.loaders.FluxLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L1924"}}),Tr=new M({props:{name:"load_lora_into_text_encoder",anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_text_encoder",parameters:[{name:"state_dict",val:""},{name:"network_alphas",val:""},{name:"text_encoder",val:""},{name:"prefix",val:" = None"},{name:"lora_scale",val:" = 1.0"},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_text_encoder.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The key should be prefixed with an
additional <code>text_encoder</code> to distinguish between unet lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_text_encoder.network_alphas",description:`<strong>network_alphas</strong> (<code>Dict[str, float]</code>) &#x2014;
The value of the network alpha used for stable learning and preventing underflow. This value has the
same meaning as the <code>--network_alpha</code> option in the kohya-ss trainer script. Refer to <a href="https://github.com/darkstorm2150/sd-scripts/blob/main/docs/train_network_README-en.md#execute-learning" rel="nofollow">this
link</a>.`,name:"network_alphas"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_text_encoder.text_encoder",description:`<strong>text_encoder</strong> (<code>CLIPTextModel</code>) &#x2014;
The text encoder model to load the LoRA layers into.`,name:"text_encoder"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_text_encoder.prefix",description:`<strong>prefix</strong> (<code>str</code>) &#x2014;
Expected prefix of the <code>text_encoder</code> in the <code>state_dict</code>.`,name:"prefix"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_text_encoder.lora_scale",description:`<strong>lora_scale</strong> (<code>float</code>) &#x2014;
How much to scale the output of the lora linear layer before it is added with the output of the regular
lora layer.`,name:"lora_scale"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_text_encoder.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_text_encoder.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_text_encoder.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_text_encoder.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L2339"}}),Dr=new M({props:{name:"load_lora_into_transformer",anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_transformer",parameters:[{name:"state_dict",val:""},{name:"network_alphas",val:""},{name:"transformer",val:""},{name:"adapter_name",val:" = None"},{name:"metadata",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"}],parametersDescription:[{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_transformer.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The keys can either be indexed directly
into the unet or prefixed with an additional <code>unet</code> which can be used to distinguish between text
encoder lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_transformer.network_alphas",description:`<strong>network_alphas</strong> (<code>Dict[str, float]</code>) &#x2014;
The value of the network alpha used for stable learning and preventing underflow. This value has the
same meaning as the <code>--network_alpha</code> option in the kohya-ss trainer script. Refer to <a href="https://github.com/darkstorm2150/sd-scripts/blob/main/docs/train_network_README-en.md#execute-learning" rel="nofollow">this
link</a>.`,name:"network_alphas"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_transformer.transformer",description:`<strong>transformer</strong> (<code>FluxTransformer2DModel</code>) &#x2014;
The Transformer model to load the LoRA layers into.`,name:"transformer"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_transformer.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_transformer.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_transformer.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_into_transformer.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L2230"}}),Cr=new M({props:{name:"load_lora_weights",anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_weights",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"adapter_name",val:": typing.Optional[str] = None"},{name:"hotswap",val:": bool = False"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_weights.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_weights.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_weights.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
\`Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_weights.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.load_lora_weights.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L2105"}}),Sr=new M({props:{name:"lora_state_dict",anchor:"diffusers.loaders.FluxLoraLoaderMixin.lora_state_dict",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"return_alphas",val:": bool = False"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.FluxLoraLoaderMixin.lora_state_dict.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
Can be either:</p>
<ul>
<li>A string, the <em>model id</em> (for example <code>google/ddpm-celebahq-256</code>) of a pretrained model hosted on
the Hub.</li>
<li>A path to a <em>directory</em> (for example <code>./my_model_directory</code>) containing the model weights saved
with <a href="/docs/diffusers/pr_12242/en/api/models/overview#diffusers.ModelMixin.save_pretrained">ModelMixin.save_pretrained()</a>.</li>
<li>A <a href="https://pytorch.org/tutorials/beginner/saving_loading_models.html#what-is-a-state-dict" rel="nofollow">torch state
dict</a>.</li>
</ul>`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.lora_state_dict.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) &#x2014;
Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
is not used.`,name:"cache_dir"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.lora_state_dict.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether or not to force the (re-)download of the model weights and configuration files, overriding the
cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.lora_state_dict.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) &#x2014;
A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{&apos;http&apos;: &apos;foo.bar:3128&apos;, &apos;http://hostname&apos;: &apos;foo.bar:4012&apos;}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.lora_state_dict.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
won&#x2019;t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.lora_state_dict.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) &#x2014;
The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.lora_state_dict.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;main&quot;</code>) &#x2014;
The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
allowed by Git.`,name:"revision"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.lora_state_dict.subfolder",description:`<strong>subfolder</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;&quot;</code>) &#x2014;
The subfolder location of a model file within a larger model repository on the Hub or locally.`,name:"subfolder"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.lora_state_dict.return_lora_metadata",description:`<strong>return_lora_metadata</strong> (<code>bool</code>, <em>optional</em>, defaults to False) &#x2014;
When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.`,name:"return_lora_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L1937"}}),_t=new C({props:{warning:!0,$$slots:{default:[bb]},$$scope:{ctx:T}}}),kr=new M({props:{name:"save_lora_weights",anchor:"diffusers.loaders.FluxLoraLoaderMixin.save_lora_weights",parameters:[{name:"save_directory",val:": typing.Union[str, os.PathLike]"},{name:"transformer_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"text_encoder_lora_layers",val:": typing.Dict[str, torch.nn.modules.module.Module] = None"},{name:"is_main_process",val:": bool = True"},{name:"weight_name",val:": str = None"},{name:"save_function",val:": typing.Callable = None"},{name:"safe_serialization",val:": bool = True"},{name:"transformer_lora_adapter_metadata",val:" = None"},{name:"text_encoder_lora_adapter_metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.FluxLoraLoaderMixin.save_lora_weights.save_directory",description:`<strong>save_directory</strong> (<code>str</code> or <code>os.PathLike</code>) &#x2014;
Directory to save LoRA parameters to. Will be created if it doesn&#x2019;t exist.`,name:"save_directory"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.save_lora_weights.transformer_lora_layers",description:`<strong>transformer_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>transformer</code>.`,name:"transformer_lora_layers"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.save_lora_weights.text_encoder_lora_layers",description:`<strong>text_encoder_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>text_encoder</code>. Must explicitly pass the text
encoder LoRA state dict because it comes from &#x1F917; Transformers.`,name:"text_encoder_lora_layers"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.save_lora_weights.is_main_process",description:`<strong>is_main_process</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether the process calling this is the main process or not. Useful during distributed training and you
need to call this function on all processes. In this case, set <code>is_main_process=True</code> only on the main
process to avoid race conditions.`,name:"is_main_process"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.save_lora_weights.save_function",description:`<strong>save_function</strong> (<code>Callable</code>) &#x2014;
The function to use to save the state dictionary. Useful during distributed training when you need to
replace <code>torch.save</code> with another method. Can be configured with the environment variable
<code>DIFFUSERS_SAVE_MODE</code>.`,name:"save_function"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.save_lora_weights.safe_serialization",description:`<strong>safe_serialization</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to save the model using <code>safetensors</code> or the traditional PyTorch way with <code>pickle</code>.`,name:"safe_serialization"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.save_lora_weights.transformer_lora_adapter_metadata",description:`<strong>transformer_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the transformer to be serialized with the state dict.`,name:"transformer_lora_adapter_metadata"},{anchor:"diffusers.loaders.FluxLoraLoaderMixin.save_lora_weights.text_encoder_lora_adapter_metadata",description:`<strong>text_encoder_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the text encoder to be serialized with the state dict.`,name:"text_encoder_lora_adapter_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L2398"}}),Rr=new M({props:{name:"unfuse_lora",anchor:"diffusers.loaders.FluxLoraLoaderMixin.unfuse_lora",parameters:[{name:"components",val:": typing.List[str] = ['transformer', 'text_encoder']"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.FluxLoraLoaderMixin.unfuse_lora.components",description:"<strong>components</strong> (<code>List[str]</code>) &#x2014; List of LoRA-injectable components to unfuse LoRA from.",name:"components"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L2531"}}),ht=new C({props:{warning:!0,$$slots:{default:[wb]},$$scope:{ctx:T}}}),Ar=new M({props:{name:"unload_lora_weights",anchor:"diffusers.loaders.FluxLoraLoaderMixin.unload_lora_weights",parameters:[{name:"reset_to_overwritten_params",val:" = False"}],parametersDescription:[{anchor:"diffusers.loaders.FluxLoraLoaderMixin.unload_lora_weights.reset_to_overwritten_params",description:`<strong>reset_to_overwritten_params</strong> (<code>bool</code>, defaults to <code>False</code>) &#x2014; Whether to reset the LoRA-loaded modules
to their original params. Refer to the <a href="https://huggingface.co/docs/diffusers/main/en/api/pipelines/flux" rel="nofollow">Flux
documentation</a> to learn more.`,name:"reset_to_overwritten_params"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L2552"}}),gt=new te({props:{anchor:"diffusers.loaders.FluxLoraLoaderMixin.unload_lora_weights.example",$$slots:{default:[vb]},$$scope:{ctx:T}}}),Ir=new X({props:{title:"CogVideoXLoraLoaderMixin",local:"diffusers.loaders.CogVideoXLoraLoaderMixin",headingTag:"h2"}}),Ur=new M({props:{name:"class diffusers.loaders.CogVideoXLoraLoaderMixin",anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L3007"}}),Vr=new M({props:{name:"load_lora_into_transformer",anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.load_lora_into_transformer",parameters:[{name:"state_dict",val:""},{name:"transformer",val:""},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.load_lora_into_transformer.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The keys can either be indexed directly
into the unet or prefixed with an additional <code>unet</code> which can be used to distinguish between text
encoder lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.load_lora_into_transformer.transformer",description:`<strong>transformer</strong> (<code>CogVideoXTransformer3DModel</code>) &#x2014;
The Transformer model to load the LoRA layers into.`,name:"transformer"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.load_lora_into_transformer.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.load_lora_into_transformer.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.load_lora_into_transformer.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.load_lora_into_transformer.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L3173"}}),Wr=new M({props:{name:"load_lora_weights",anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.load_lora_weights",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"adapter_name",val:": typing.Optional[str] = None"},{name:"hotswap",val:": bool = False"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.load_lora_weights.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.load_lora_weights.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.load_lora_weights.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.load_lora_weights.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.load_lora_weights.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L3114"}}),Xr=new M({props:{name:"lora_state_dict",anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.lora_state_dict",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.lora_state_dict.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
Can be either:</p>
<ul>
<li>A string, the <em>model id</em> (for example <code>google/ddpm-celebahq-256</code>) of a pretrained model hosted on
the Hub.</li>
<li>A path to a <em>directory</em> (for example <code>./my_model_directory</code>) containing the model weights saved
with <a href="/docs/diffusers/pr_12242/en/api/models/overview#diffusers.ModelMixin.save_pretrained">ModelMixin.save_pretrained()</a>.</li>
<li>A <a href="https://pytorch.org/tutorials/beginner/saving_loading_models.html#what-is-a-state-dict" rel="nofollow">torch state
dict</a>.</li>
</ul>`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.lora_state_dict.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) &#x2014;
Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
is not used.`,name:"cache_dir"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.lora_state_dict.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether or not to force the (re-)download of the model weights and configuration files, overriding the
cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.lora_state_dict.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) &#x2014;
A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{&apos;http&apos;: &apos;foo.bar:3128&apos;, &apos;http://hostname&apos;: &apos;foo.bar:4012&apos;}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.lora_state_dict.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
won&#x2019;t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.lora_state_dict.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) &#x2014;
The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.lora_state_dict.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;main&quot;</code>) &#x2014;
The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
allowed by Git.`,name:"revision"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.lora_state_dict.subfolder",description:`<strong>subfolder</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;&quot;</code>) &#x2014;
The subfolder location of a model file within a larger model repository on the Hub or locally.`,name:"subfolder"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.lora_state_dict.return_lora_metadata",description:`<strong>return_lora_metadata</strong> (<code>bool</code>, <em>optional</em>, defaults to False) &#x2014;
When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.`,name:"return_lora_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L3015"}}),bt=new C({props:{warning:!0,$$slots:{default:[$b]},$$scope:{ctx:T}}}),Pr=new M({props:{name:"save_lora_weights",anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.save_lora_weights",parameters:[{name:"save_directory",val:": typing.Union[str, os.PathLike]"},{name:"transformer_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"is_main_process",val:": bool = True"},{name:"weight_name",val:": str = None"},{name:"save_function",val:": typing.Callable = None"},{name:"safe_serialization",val:": bool = True"},{name:"transformer_lora_adapter_metadata",val:": typing.Optional[dict] = None"}],parametersDescription:[{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.save_lora_weights.save_directory",description:`<strong>save_directory</strong> (<code>str</code> or <code>os.PathLike</code>) &#x2014;
Directory to save LoRA parameters to. Will be created if it doesn&#x2019;t exist.`,name:"save_directory"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.save_lora_weights.transformer_lora_layers",description:`<strong>transformer_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>transformer</code>.`,name:"transformer_lora_layers"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.save_lora_weights.is_main_process",description:`<strong>is_main_process</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether the process calling this is the main process or not. Useful during distributed training and you
need to call this function on all processes. In this case, set <code>is_main_process=True</code> only on the main
process to avoid race conditions.`,name:"is_main_process"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.save_lora_weights.save_function",description:`<strong>save_function</strong> (<code>Callable</code>) &#x2014;
The function to use to save the state dictionary. Useful during distributed training when you need to
replace <code>torch.save</code> with another method. Can be configured with the environment variable
<code>DIFFUSERS_SAVE_MODE</code>.`,name:"save_function"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.save_lora_weights.safe_serialization",description:`<strong>safe_serialization</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to save the model using <code>safetensors</code> or the traditional PyTorch way with <code>pickle</code>.`,name:"safe_serialization"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.save_lora_weights.transformer_lora_adapter_metadata",description:`<strong>transformer_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the transformer to be serialized with the state dict.`,name:"transformer_lora_adapter_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L3224"}}),Fr=new M({props:{name:"unfuse_lora",anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.unfuse_lora",parameters:[{name:"components",val:": typing.List[str] = ['transformer']"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.unfuse_lora.components",description:"<strong>components</strong> (<code>List[str]</code>) &#x2014; List of LoRA-injectable components to unfuse LoRA from.",name:"components"},{anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin.unfuse_lora.unfuse_transformer",description:"<strong>unfuse_transformer</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014; Whether to unfuse the UNet LoRA parameters.",name:"unfuse_transformer"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L3328"}}),vt=new C({props:{warning:!0,$$slots:{default:[yb]},$$scope:{ctx:T}}}),Jr=new X({props:{title:"Mochi1LoraLoaderMixin",local:"diffusers.loaders.Mochi1LoraLoaderMixin",headingTag:"h2"}}),Hr=new M({props:{name:"class diffusers.loaders.Mochi1LoraLoaderMixin",anchor:"diffusers.loaders.Mochi1LoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L3346"}}),jr=new M({props:{name:"load_lora_into_transformer",anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.load_lora_into_transformer",parameters:[{name:"state_dict",val:""},{name:"transformer",val:""},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.load_lora_into_transformer.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The keys can either be indexed directly
into the unet or prefixed with an additional <code>unet</code> which can be used to distinguish between text
encoder lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.load_lora_into_transformer.transformer",description:`<strong>transformer</strong> (<code>MochiTransformer3DModel</code>) &#x2014;
The Transformer model to load the LoRA layers into.`,name:"transformer"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.load_lora_into_transformer.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.load_lora_into_transformer.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.load_lora_into_transformer.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.load_lora_into_transformer.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L3513"}}),Zr=new M({props:{name:"load_lora_weights",anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.load_lora_weights",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"adapter_name",val:": typing.Optional[str] = None"},{name:"hotswap",val:": bool = False"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.load_lora_weights.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.load_lora_weights.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.load_lora_weights.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.load_lora_weights.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.load_lora_weights.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L3454"}}),Gr=new M({props:{name:"lora_state_dict",anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.lora_state_dict",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.lora_state_dict.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
Can be either:</p>
<ul>
<li>A string, the <em>model id</em> (for example <code>google/ddpm-celebahq-256</code>) of a pretrained model hosted on
the Hub.</li>
<li>A path to a <em>directory</em> (for example <code>./my_model_directory</code>) containing the model weights saved
with <a href="/docs/diffusers/pr_12242/en/api/models/overview#diffusers.ModelMixin.save_pretrained">ModelMixin.save_pretrained()</a>.</li>
<li>A <a href="https://pytorch.org/tutorials/beginner/saving_loading_models.html#what-is-a-state-dict" rel="nofollow">torch state
dict</a>.</li>
</ul>`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.lora_state_dict.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) &#x2014;
Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
is not used.`,name:"cache_dir"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.lora_state_dict.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether or not to force the (re-)download of the model weights and configuration files, overriding the
cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.lora_state_dict.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) &#x2014;
A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{&apos;http&apos;: &apos;foo.bar:3128&apos;, &apos;http://hostname&apos;: &apos;foo.bar:4012&apos;}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.lora_state_dict.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
won&#x2019;t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.lora_state_dict.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) &#x2014;
The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.lora_state_dict.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;main&quot;</code>) &#x2014;
The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
allowed by Git.`,name:"revision"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.lora_state_dict.subfolder",description:`<strong>subfolder</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;&quot;</code>) &#x2014;
The subfolder location of a model file within a larger model repository on the Hub or locally.`,name:"subfolder"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.lora_state_dict.return_lora_metadata",description:`<strong>return_lora_metadata</strong> (<code>bool</code>, <em>optional</em>, defaults to False) &#x2014;
When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.`,name:"return_lora_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L3354"}}),Mt=new C({props:{warning:!0,$$slots:{default:[Mb]},$$scope:{ctx:T}}}),qr=new M({props:{name:"save_lora_weights",anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.save_lora_weights",parameters:[{name:"save_directory",val:": typing.Union[str, os.PathLike]"},{name:"transformer_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"is_main_process",val:": bool = True"},{name:"weight_name",val:": str = None"},{name:"save_function",val:": typing.Callable = None"},{name:"safe_serialization",val:": bool = True"},{name:"transformer_lora_adapter_metadata",val:": typing.Optional[dict] = None"}],parametersDescription:[{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.save_lora_weights.save_directory",description:`<strong>save_directory</strong> (<code>str</code> or <code>os.PathLike</code>) &#x2014;
Directory to save LoRA parameters to. Will be created if it doesn&#x2019;t exist.`,name:"save_directory"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.save_lora_weights.transformer_lora_layers",description:`<strong>transformer_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>transformer</code>.`,name:"transformer_lora_layers"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.save_lora_weights.is_main_process",description:`<strong>is_main_process</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether the process calling this is the main process or not. Useful during distributed training and you
need to call this function on all processes. In this case, set <code>is_main_process=True</code> only on the main
process to avoid race conditions.`,name:"is_main_process"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.save_lora_weights.save_function",description:`<strong>save_function</strong> (<code>Callable</code>) &#x2014;
The function to use to save the state dictionary. Useful during distributed training when you need to
replace <code>torch.save</code> with another method. Can be configured with the environment variable
<code>DIFFUSERS_SAVE_MODE</code>.`,name:"save_function"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.save_lora_weights.safe_serialization",description:`<strong>safe_serialization</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to save the model using <code>safetensors</code> or the traditional PyTorch way with <code>pickle</code>.`,name:"safe_serialization"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.save_lora_weights.transformer_lora_adapter_metadata",description:`<strong>transformer_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the transformer to be serialized with the state dict.`,name:"transformer_lora_adapter_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L3564"}}),Br=new M({props:{name:"unfuse_lora",anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.unfuse_lora",parameters:[{name:"components",val:": typing.List[str] = ['transformer']"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.unfuse_lora.components",description:"<strong>components</strong> (<code>List[str]</code>) &#x2014; List of LoRA-injectable components to unfuse LoRA from.",name:"components"},{anchor:"diffusers.loaders.Mochi1LoraLoaderMixin.unfuse_lora.unfuse_transformer",description:"<strong>unfuse_transformer</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014; Whether to unfuse the UNet LoRA parameters.",name:"unfuse_transformer"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L3670"}}),Dt=new C({props:{warning:!0,$$slots:{default:[Tb]},$$scope:{ctx:T}}}),Er=new X({props:{title:"AuraFlowLoraLoaderMixin",local:"diffusers.loaders.AuraFlowLoraLoaderMixin",headingTag:"h2"}}),Nr=new M({props:{name:"class diffusers.loaders.AuraFlowLoraLoaderMixin",anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L1582"}}),zr=new M({props:{name:"load_lora_into_transformer",anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.load_lora_into_transformer",parameters:[{name:"state_dict",val:""},{name:"transformer",val:""},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.load_lora_into_transformer.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The keys can either be indexed directly
into the unet or prefixed with an additional <code>unet</code> which can be used to distinguish between text
encoder lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.load_lora_into_transformer.transformer",description:`<strong>transformer</strong> (<code>AuraFlowTransformer2DModel</code>) &#x2014;
The Transformer model to load the LoRA layers into.`,name:"transformer"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.load_lora_into_transformer.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.load_lora_into_transformer.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.load_lora_into_transformer.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.load_lora_into_transformer.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L1749"}}),Yr=new M({props:{name:"load_lora_weights",anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.load_lora_weights",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"adapter_name",val:": typing.Optional[str] = None"},{name:"hotswap",val:": bool = False"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.load_lora_weights.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.load_lora_weights.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.load_lora_weights.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.load_lora_weights.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.load_lora_weights.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L1690"}}),Qr=new M({props:{name:"lora_state_dict",anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.lora_state_dict",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.lora_state_dict.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
Can be either:</p>
<ul>
<li>A string, the <em>model id</em> (for example <code>google/ddpm-celebahq-256</code>) of a pretrained model hosted on
the Hub.</li>
<li>A path to a <em>directory</em> (for example <code>./my_model_directory</code>) containing the model weights saved
with <a href="/docs/diffusers/pr_12242/en/api/models/overview#diffusers.ModelMixin.save_pretrained">ModelMixin.save_pretrained()</a>.</li>
<li>A <a href="https://pytorch.org/tutorials/beginner/saving_loading_models.html#what-is-a-state-dict" rel="nofollow">torch state
dict</a>.</li>
</ul>`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.lora_state_dict.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) &#x2014;
Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
is not used.`,name:"cache_dir"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.lora_state_dict.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether or not to force the (re-)download of the model weights and configuration files, overriding the
cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.lora_state_dict.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) &#x2014;
A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{&apos;http&apos;: &apos;foo.bar:3128&apos;, &apos;http://hostname&apos;: &apos;foo.bar:4012&apos;}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.lora_state_dict.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
won&#x2019;t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.lora_state_dict.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) &#x2014;
The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.lora_state_dict.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;main&quot;</code>) &#x2014;
The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
allowed by Git.`,name:"revision"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.lora_state_dict.subfolder",description:`<strong>subfolder</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;&quot;</code>) &#x2014;
The subfolder location of a model file within a larger model repository on the Hub or locally.`,name:"subfolder"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.lora_state_dict.return_lora_metadata",description:`<strong>return_lora_metadata</strong> (<code>bool</code>, <em>optional</em>, defaults to False) &#x2014;
When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.`,name:"return_lora_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L1590"}}),kt=new C({props:{warning:!0,$$slots:{default:[Db]},$$scope:{ctx:T}}}),Or=new M({props:{name:"save_lora_weights",anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.save_lora_weights",parameters:[{name:"save_directory",val:": typing.Union[str, os.PathLike]"},{name:"transformer_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"is_main_process",val:": bool = True"},{name:"weight_name",val:": str = None"},{name:"save_function",val:": typing.Callable = None"},{name:"safe_serialization",val:": bool = True"},{name:"transformer_lora_adapter_metadata",val:": typing.Optional[dict] = None"}],parametersDescription:[{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.save_lora_weights.save_directory",description:`<strong>save_directory</strong> (<code>str</code> or <code>os.PathLike</code>) &#x2014;
Directory to save LoRA parameters to. Will be created if it doesn&#x2019;t exist.`,name:"save_directory"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.save_lora_weights.transformer_lora_layers",description:`<strong>transformer_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>transformer</code>.`,name:"transformer_lora_layers"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.save_lora_weights.is_main_process",description:`<strong>is_main_process</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether the process calling this is the main process or not. Useful during distributed training and you
need to call this function on all processes. In this case, set <code>is_main_process=True</code> only on the main
process to avoid race conditions.`,name:"is_main_process"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.save_lora_weights.save_function",description:`<strong>save_function</strong> (<code>Callable</code>) &#x2014;
The function to use to save the state dictionary. Useful during distributed training when you need to
replace <code>torch.save</code> with another method. Can be configured with the environment variable
<code>DIFFUSERS_SAVE_MODE</code>.`,name:"save_function"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.save_lora_weights.safe_serialization",description:`<strong>safe_serialization</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to save the model using <code>safetensors</code> or the traditional PyTorch way with <code>pickle</code>.`,name:"safe_serialization"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.save_lora_weights.transformer_lora_adapter_metadata",description:`<strong>transformer_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the transformer to be serialized with the state dict.`,name:"transformer_lora_adapter_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L1800"}}),Kr=new M({props:{name:"unfuse_lora",anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.unfuse_lora",parameters:[{name:"components",val:": typing.List[str] = ['transformer', 'text_encoder']"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.unfuse_lora.components",description:"<strong>components</strong> (<code>List[str]</code>) &#x2014; List of LoRA-injectable components to unfuse LoRA from.",name:"components"},{anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin.unfuse_lora.unfuse_transformer",description:"<strong>unfuse_transformer</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014; Whether to unfuse the UNet LoRA parameters.",name:"unfuse_transformer"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L1906"}}),At=new C({props:{warning:!0,$$slots:{default:[Cb]},$$scope:{ctx:T}}}),en=new X({props:{title:"LTXVideoLoraLoaderMixin",local:"diffusers.loaders.LTXVideoLoraLoaderMixin",headingTag:"h2"}}),on=new M({props:{name:"class diffusers.loaders.LTXVideoLoraLoaderMixin",anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L3688"}}),tn=new M({props:{name:"load_lora_into_transformer",anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.load_lora_into_transformer",parameters:[{name:"state_dict",val:""},{name:"transformer",val:""},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.load_lora_into_transformer.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The keys can either be indexed directly
into the unet or prefixed with an additional <code>unet</code> which can be used to distinguish between text
encoder lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.load_lora_into_transformer.transformer",description:`<strong>transformer</strong> (<code>LTXVideoTransformer3DModel</code>) &#x2014;
The Transformer model to load the LoRA layers into.`,name:"transformer"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.load_lora_into_transformer.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.load_lora_into_transformer.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.load_lora_into_transformer.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.load_lora_into_transformer.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L3857"}}),an=new M({props:{name:"load_lora_weights",anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.load_lora_weights",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"adapter_name",val:": typing.Optional[str] = None"},{name:"hotswap",val:": bool = False"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.load_lora_weights.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.load_lora_weights.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.load_lora_weights.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.load_lora_weights.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.load_lora_weights.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L3798"}}),rn=new M({props:{name:"lora_state_dict",anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.lora_state_dict",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.lora_state_dict.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
Can be either:</p>
<ul>
<li>A string, the <em>model id</em> (for example <code>google/ddpm-celebahq-256</code>) of a pretrained model hosted on
the Hub.</li>
<li>A path to a <em>directory</em> (for example <code>./my_model_directory</code>) containing the model weights saved
with <a href="/docs/diffusers/pr_12242/en/api/models/overview#diffusers.ModelMixin.save_pretrained">ModelMixin.save_pretrained()</a>.</li>
<li>A <a href="https://pytorch.org/tutorials/beginner/saving_loading_models.html#what-is-a-state-dict" rel="nofollow">torch state
dict</a>.</li>
</ul>`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.lora_state_dict.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) &#x2014;
Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
is not used.`,name:"cache_dir"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.lora_state_dict.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether or not to force the (re-)download of the model weights and configuration files, overriding the
cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.lora_state_dict.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) &#x2014;
A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{&apos;http&apos;: &apos;foo.bar:3128&apos;, &apos;http://hostname&apos;: &apos;foo.bar:4012&apos;}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.lora_state_dict.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
won&#x2019;t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.lora_state_dict.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) &#x2014;
The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.lora_state_dict.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;main&quot;</code>) &#x2014;
The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
allowed by Git.`,name:"revision"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.lora_state_dict.subfolder",description:`<strong>subfolder</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;&quot;</code>) &#x2014;
The subfolder location of a model file within a larger model repository on the Hub or locally.`,name:"subfolder"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.lora_state_dict.return_lora_metadata",description:`<strong>return_lora_metadata</strong> (<code>bool</code>, <em>optional</em>, defaults to False) &#x2014;
When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.`,name:"return_lora_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L3696"}}),Vt=new C({props:{warning:!0,$$slots:{default:[Sb]},$$scope:{ctx:T}}}),nn=new M({props:{name:"save_lora_weights",anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.save_lora_weights",parameters:[{name:"save_directory",val:": typing.Union[str, os.PathLike]"},{name:"transformer_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"is_main_process",val:": bool = True"},{name:"weight_name",val:": str = None"},{name:"save_function",val:": typing.Callable = None"},{name:"safe_serialization",val:": bool = True"},{name:"transformer_lora_adapter_metadata",val:": typing.Optional[dict] = None"}],parametersDescription:[{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.save_lora_weights.save_directory",description:`<strong>save_directory</strong> (<code>str</code> or <code>os.PathLike</code>) &#x2014;
Directory to save LoRA parameters to. Will be created if it doesn&#x2019;t exist.`,name:"save_directory"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.save_lora_weights.transformer_lora_layers",description:`<strong>transformer_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>transformer</code>.`,name:"transformer_lora_layers"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.save_lora_weights.is_main_process",description:`<strong>is_main_process</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether the process calling this is the main process or not. Useful during distributed training and you
need to call this function on all processes. In this case, set <code>is_main_process=True</code> only on the main
process to avoid race conditions.`,name:"is_main_process"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.save_lora_weights.save_function",description:`<strong>save_function</strong> (<code>Callable</code>) &#x2014;
The function to use to save the state dictionary. Useful during distributed training when you need to
replace <code>torch.save</code> with another method. Can be configured with the environment variable
<code>DIFFUSERS_SAVE_MODE</code>.`,name:"save_function"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.save_lora_weights.safe_serialization",description:`<strong>safe_serialization</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to save the model using <code>safetensors</code> or the traditional PyTorch way with <code>pickle</code>.`,name:"safe_serialization"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.save_lora_weights.transformer_lora_adapter_metadata",description:`<strong>transformer_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the transformer to be serialized with the state dict.`,name:"transformer_lora_adapter_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L3908"}}),sn=new M({props:{name:"unfuse_lora",anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.unfuse_lora",parameters:[{name:"components",val:": typing.List[str] = ['transformer']"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.unfuse_lora.components",description:"<strong>components</strong> (<code>List[str]</code>) &#x2014; List of LoRA-injectable components to unfuse LoRA from.",name:"components"},{anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin.unfuse_lora.unfuse_transformer",description:"<strong>unfuse_transformer</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014; Whether to unfuse the UNet LoRA parameters.",name:"unfuse_transformer"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4014"}}),Xt=new C({props:{warning:!0,$$slots:{default:[kb]},$$scope:{ctx:T}}}),dn=new X({props:{title:"SanaLoraLoaderMixin",local:"diffusers.loaders.SanaLoraLoaderMixin",headingTag:"h2"}}),ln=new M({props:{name:"class diffusers.loaders.SanaLoraLoaderMixin",anchor:"diffusers.loaders.SanaLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4032"}}),cn=new M({props:{name:"load_lora_into_transformer",anchor:"diffusers.loaders.SanaLoraLoaderMixin.load_lora_into_transformer",parameters:[{name:"state_dict",val:""},{name:"transformer",val:""},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.SanaLoraLoaderMixin.load_lora_into_transformer.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The keys can either be indexed directly
into the unet or prefixed with an additional <code>unet</code> which can be used to distinguish between text
encoder lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.load_lora_into_transformer.transformer",description:`<strong>transformer</strong> (<code>SanaTransformer2DModel</code>) &#x2014;
The Transformer model to load the LoRA layers into.`,name:"transformer"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.load_lora_into_transformer.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.load_lora_into_transformer.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.load_lora_into_transformer.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.load_lora_into_transformer.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4199"}}),fn=new M({props:{name:"load_lora_weights",anchor:"diffusers.loaders.SanaLoraLoaderMixin.load_lora_weights",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"adapter_name",val:": typing.Optional[str] = None"},{name:"hotswap",val:": bool = False"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.SanaLoraLoaderMixin.load_lora_weights.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.load_lora_weights.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.load_lora_weights.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.load_lora_weights.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.load_lora_weights.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4140"}}),pn=new M({props:{name:"lora_state_dict",anchor:"diffusers.loaders.SanaLoraLoaderMixin.lora_state_dict",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.SanaLoraLoaderMixin.lora_state_dict.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
Can be either:</p>
<ul>
<li>A string, the <em>model id</em> (for example <code>google/ddpm-celebahq-256</code>) of a pretrained model hosted on
the Hub.</li>
<li>A path to a <em>directory</em> (for example <code>./my_model_directory</code>) containing the model weights saved
with <a href="/docs/diffusers/pr_12242/en/api/models/overview#diffusers.ModelMixin.save_pretrained">ModelMixin.save_pretrained()</a>.</li>
<li>A <a href="https://pytorch.org/tutorials/beginner/saving_loading_models.html#what-is-a-state-dict" rel="nofollow">torch state
dict</a>.</li>
</ul>`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.lora_state_dict.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) &#x2014;
Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
is not used.`,name:"cache_dir"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.lora_state_dict.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether or not to force the (re-)download of the model weights and configuration files, overriding the
cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.lora_state_dict.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) &#x2014;
A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{&apos;http&apos;: &apos;foo.bar:3128&apos;, &apos;http://hostname&apos;: &apos;foo.bar:4012&apos;}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.lora_state_dict.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
won&#x2019;t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.lora_state_dict.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) &#x2014;
The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.lora_state_dict.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;main&quot;</code>) &#x2014;
The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
allowed by Git.`,name:"revision"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.lora_state_dict.subfolder",description:`<strong>subfolder</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;&quot;</code>) &#x2014;
The subfolder location of a model file within a larger model repository on the Hub or locally.`,name:"subfolder"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.lora_state_dict.return_lora_metadata",description:`<strong>return_lora_metadata</strong> (<code>bool</code>, <em>optional</em>, defaults to False) &#x2014;
When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.`,name:"return_lora_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4040"}}),Jt=new C({props:{warning:!0,$$slots:{default:[Rb]},$$scope:{ctx:T}}}),mn=new M({props:{name:"save_lora_weights",anchor:"diffusers.loaders.SanaLoraLoaderMixin.save_lora_weights",parameters:[{name:"save_directory",val:": typing.Union[str, os.PathLike]"},{name:"transformer_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"is_main_process",val:": bool = True"},{name:"weight_name",val:": str = None"},{name:"save_function",val:": typing.Callable = None"},{name:"safe_serialization",val:": bool = True"},{name:"transformer_lora_adapter_metadata",val:": typing.Optional[dict] = None"}],parametersDescription:[{anchor:"diffusers.loaders.SanaLoraLoaderMixin.save_lora_weights.save_directory",description:`<strong>save_directory</strong> (<code>str</code> or <code>os.PathLike</code>) &#x2014;
Directory to save LoRA parameters to. Will be created if it doesn&#x2019;t exist.`,name:"save_directory"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.save_lora_weights.transformer_lora_layers",description:`<strong>transformer_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>transformer</code>.`,name:"transformer_lora_layers"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.save_lora_weights.is_main_process",description:`<strong>is_main_process</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether the process calling this is the main process or not. Useful during distributed training and you
need to call this function on all processes. In this case, set <code>is_main_process=True</code> only on the main
process to avoid race conditions.`,name:"is_main_process"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.save_lora_weights.save_function",description:`<strong>save_function</strong> (<code>Callable</code>) &#x2014;
The function to use to save the state dictionary. Useful during distributed training when you need to
replace <code>torch.save</code> with another method. Can be configured with the environment variable
<code>DIFFUSERS_SAVE_MODE</code>.`,name:"save_function"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.save_lora_weights.safe_serialization",description:`<strong>safe_serialization</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to save the model using <code>safetensors</code> or the traditional PyTorch way with <code>pickle</code>.`,name:"safe_serialization"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.save_lora_weights.transformer_lora_adapter_metadata",description:`<strong>transformer_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the transformer to be serialized with the state dict.`,name:"transformer_lora_adapter_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4250"}}),_n=new M({props:{name:"unfuse_lora",anchor:"diffusers.loaders.SanaLoraLoaderMixin.unfuse_lora",parameters:[{name:"components",val:": typing.List[str] = ['transformer']"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.SanaLoraLoaderMixin.unfuse_lora.components",description:"<strong>components</strong> (<code>List[str]</code>) &#x2014; List of LoRA-injectable components to unfuse LoRA from.",name:"components"},{anchor:"diffusers.loaders.SanaLoraLoaderMixin.unfuse_lora.unfuse_transformer",description:"<strong>unfuse_transformer</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014; Whether to unfuse the UNet LoRA parameters.",name:"unfuse_transformer"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4356"}}),jt=new C({props:{warning:!0,$$slots:{default:[Ab]},$$scope:{ctx:T}}}),un=new X({props:{title:"HunyuanVideoLoraLoaderMixin",local:"diffusers.loaders.HunyuanVideoLoraLoaderMixin",headingTag:"h2"}}),hn=new M({props:{name:"class diffusers.loaders.HunyuanVideoLoraLoaderMixin",anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4374"}}),gn=new M({props:{name:"load_lora_into_transformer",anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.load_lora_into_transformer",parameters:[{name:"state_dict",val:""},{name:"transformer",val:""},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.load_lora_into_transformer.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The keys can either be indexed directly
into the unet or prefixed with an additional <code>unet</code> which can be used to distinguish between text
encoder lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.load_lora_into_transformer.transformer",description:`<strong>transformer</strong> (<code>HunyuanVideoTransformer3DModel</code>) &#x2014;
The Transformer model to load the LoRA layers into.`,name:"transformer"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.load_lora_into_transformer.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.load_lora_into_transformer.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.load_lora_into_transformer.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.load_lora_into_transformer.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4543"}}),xn=new M({props:{name:"load_lora_weights",anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.load_lora_weights",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"adapter_name",val:": typing.Optional[str] = None"},{name:"hotswap",val:": bool = False"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.load_lora_weights.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.load_lora_weights.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.load_lora_weights.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.load_lora_weights.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.load_lora_weights.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4484"}}),Ln=new M({props:{name:"lora_state_dict",anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.lora_state_dict",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.lora_state_dict.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
Can be either:</p>
<ul>
<li>A string, the <em>model id</em> (for example <code>google/ddpm-celebahq-256</code>) of a pretrained model hosted on
the Hub.</li>
<li>A path to a <em>directory</em> (for example <code>./my_model_directory</code>) containing the model weights saved
with <a href="/docs/diffusers/pr_12242/en/api/models/overview#diffusers.ModelMixin.save_pretrained">ModelMixin.save_pretrained()</a>.</li>
<li>A <a href="https://pytorch.org/tutorials/beginner/saving_loading_models.html#what-is-a-state-dict" rel="nofollow">torch state
dict</a>.</li>
</ul>`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.lora_state_dict.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) &#x2014;
Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
is not used.`,name:"cache_dir"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.lora_state_dict.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether or not to force the (re-)download of the model weights and configuration files, overriding the
cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.lora_state_dict.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) &#x2014;
A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{&apos;http&apos;: &apos;foo.bar:3128&apos;, &apos;http://hostname&apos;: &apos;foo.bar:4012&apos;}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.lora_state_dict.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
won&#x2019;t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.lora_state_dict.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) &#x2014;
The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.lora_state_dict.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;main&quot;</code>) &#x2014;
The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
allowed by Git.`,name:"revision"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.lora_state_dict.subfolder",description:`<strong>subfolder</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;&quot;</code>) &#x2014;
The subfolder location of a model file within a larger model repository on the Hub or locally.`,name:"subfolder"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.lora_state_dict.return_lora_metadata",description:`<strong>return_lora_metadata</strong> (<code>bool</code>, <em>optional</em>, defaults to False) &#x2014;
When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.`,name:"return_lora_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4382"}}),qt=new C({props:{warning:!0,$$slots:{default:[Ib]},$$scope:{ctx:T}}}),bn=new M({props:{name:"save_lora_weights",anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.save_lora_weights",parameters:[{name:"save_directory",val:": typing.Union[str, os.PathLike]"},{name:"transformer_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"is_main_process",val:": bool = True"},{name:"weight_name",val:": str = None"},{name:"save_function",val:": typing.Callable = None"},{name:"safe_serialization",val:": bool = True"},{name:"transformer_lora_adapter_metadata",val:": typing.Optional[dict] = None"}],parametersDescription:[{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.save_lora_weights.save_directory",description:`<strong>save_directory</strong> (<code>str</code> or <code>os.PathLike</code>) &#x2014;
Directory to save LoRA parameters to. Will be created if it doesn&#x2019;t exist.`,name:"save_directory"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.save_lora_weights.transformer_lora_layers",description:`<strong>transformer_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>transformer</code>.`,name:"transformer_lora_layers"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.save_lora_weights.is_main_process",description:`<strong>is_main_process</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether the process calling this is the main process or not. Useful during distributed training and you
need to call this function on all processes. In this case, set <code>is_main_process=True</code> only on the main
process to avoid race conditions.`,name:"is_main_process"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.save_lora_weights.save_function",description:`<strong>save_function</strong> (<code>Callable</code>) &#x2014;
The function to use to save the state dictionary. Useful during distributed training when you need to
replace <code>torch.save</code> with another method. Can be configured with the environment variable
<code>DIFFUSERS_SAVE_MODE</code>.`,name:"save_function"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.save_lora_weights.safe_serialization",description:`<strong>safe_serialization</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to save the model using <code>safetensors</code> or the traditional PyTorch way with <code>pickle</code>.`,name:"safe_serialization"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.save_lora_weights.transformer_lora_adapter_metadata",description:`<strong>transformer_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the transformer to be serialized with the state dict.`,name:"transformer_lora_adapter_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4594"}}),wn=new M({props:{name:"unfuse_lora",anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.unfuse_lora",parameters:[{name:"components",val:": typing.List[str] = ['transformer']"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.unfuse_lora.components",description:"<strong>components</strong> (<code>List[str]</code>) &#x2014; List of LoRA-injectable components to unfuse LoRA from.",name:"components"},{anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin.unfuse_lora.unfuse_transformer",description:"<strong>unfuse_transformer</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014; Whether to unfuse the UNet LoRA parameters.",name:"unfuse_transformer"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4700"}}),Et=new C({props:{warning:!0,$$slots:{default:[Ub]},$$scope:{ctx:T}}}),vn=new X({props:{title:"Lumina2LoraLoaderMixin",local:"diffusers.loaders.Lumina2LoraLoaderMixin",headingTag:"h2"}}),$n=new M({props:{name:"class diffusers.loaders.Lumina2LoraLoaderMixin",anchor:"diffusers.loaders.Lumina2LoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4718"}}),yn=new M({props:{name:"load_lora_into_transformer",anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.load_lora_into_transformer",parameters:[{name:"state_dict",val:""},{name:"transformer",val:""},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.load_lora_into_transformer.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The keys can either be indexed directly
into the unet or prefixed with an additional <code>unet</code> which can be used to distinguish between text
encoder lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.load_lora_into_transformer.transformer",description:`<strong>transformer</strong> (<code>Lumina2Transformer2DModel</code>) &#x2014;
The Transformer model to load the LoRA layers into.`,name:"transformer"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.load_lora_into_transformer.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.load_lora_into_transformer.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.load_lora_into_transformer.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.load_lora_into_transformer.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4888"}}),Mn=new M({props:{name:"load_lora_weights",anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.load_lora_weights",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"adapter_name",val:": typing.Optional[str] = None"},{name:"hotswap",val:": bool = False"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.load_lora_weights.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.load_lora_weights.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.load_lora_weights.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.load_lora_weights.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.load_lora_weights.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4829"}}),Tn=new M({props:{name:"lora_state_dict",anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.lora_state_dict",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.lora_state_dict.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
Can be either:</p>
<ul>
<li>A string, the <em>model id</em> (for example <code>google/ddpm-celebahq-256</code>) of a pretrained model hosted on
the Hub.</li>
<li>A path to a <em>directory</em> (for example <code>./my_model_directory</code>) containing the model weights saved
with <a href="/docs/diffusers/pr_12242/en/api/models/overview#diffusers.ModelMixin.save_pretrained">ModelMixin.save_pretrained()</a>.</li>
<li>A <a href="https://pytorch.org/tutorials/beginner/saving_loading_models.html#what-is-a-state-dict" rel="nofollow">torch state
dict</a>.</li>
</ul>`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.lora_state_dict.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) &#x2014;
Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
is not used.`,name:"cache_dir"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.lora_state_dict.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether or not to force the (re-)download of the model weights and configuration files, overriding the
cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.lora_state_dict.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) &#x2014;
A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{&apos;http&apos;: &apos;foo.bar:3128&apos;, &apos;http://hostname&apos;: &apos;foo.bar:4012&apos;}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.lora_state_dict.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
won&#x2019;t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.lora_state_dict.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) &#x2014;
The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.lora_state_dict.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;main&quot;</code>) &#x2014;
The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
allowed by Git.`,name:"revision"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.lora_state_dict.subfolder",description:`<strong>subfolder</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;&quot;</code>) &#x2014;
The subfolder location of a model file within a larger model repository on the Hub or locally.`,name:"subfolder"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.lora_state_dict.return_lora_metadata",description:`<strong>return_lora_metadata</strong> (<code>bool</code>, <em>optional</em>, defaults to False) &#x2014;
When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.`,name:"return_lora_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4726"}}),Yt=new C({props:{warning:!0,$$slots:{default:[Vb]},$$scope:{ctx:T}}}),Dn=new M({props:{name:"save_lora_weights",anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.save_lora_weights",parameters:[{name:"save_directory",val:": typing.Union[str, os.PathLike]"},{name:"transformer_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"is_main_process",val:": bool = True"},{name:"weight_name",val:": str = None"},{name:"save_function",val:": typing.Callable = None"},{name:"safe_serialization",val:": bool = True"},{name:"transformer_lora_adapter_metadata",val:": typing.Optional[dict] = None"}],parametersDescription:[{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.save_lora_weights.save_directory",description:`<strong>save_directory</strong> (<code>str</code> or <code>os.PathLike</code>) &#x2014;
Directory to save LoRA parameters to. Will be created if it doesn&#x2019;t exist.`,name:"save_directory"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.save_lora_weights.transformer_lora_layers",description:`<strong>transformer_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>transformer</code>.`,name:"transformer_lora_layers"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.save_lora_weights.is_main_process",description:`<strong>is_main_process</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether the process calling this is the main process or not. Useful during distributed training and you
need to call this function on all processes. In this case, set <code>is_main_process=True</code> only on the main
process to avoid race conditions.`,name:"is_main_process"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.save_lora_weights.save_function",description:`<strong>save_function</strong> (<code>Callable</code>) &#x2014;
The function to use to save the state dictionary. Useful during distributed training when you need to
replace <code>torch.save</code> with another method. Can be configured with the environment variable
<code>DIFFUSERS_SAVE_MODE</code>.`,name:"save_function"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.save_lora_weights.safe_serialization",description:`<strong>safe_serialization</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to save the model using <code>safetensors</code> or the traditional PyTorch way with <code>pickle</code>.`,name:"safe_serialization"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.save_lora_weights.transformer_lora_adapter_metadata",description:`<strong>transformer_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the transformer to be serialized with the state dict.`,name:"transformer_lora_adapter_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L4939"}}),Cn=new M({props:{name:"unfuse_lora",anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.unfuse_lora",parameters:[{name:"components",val:": typing.List[str] = ['transformer']"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.unfuse_lora.components",description:"<strong>components</strong> (<code>List[str]</code>) &#x2014; List of LoRA-injectable components to unfuse LoRA from.",name:"components"},{anchor:"diffusers.loaders.Lumina2LoraLoaderMixin.unfuse_lora.unfuse_transformer",description:"<strong>unfuse_transformer</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014; Whether to unfuse the UNet LoRA parameters.",name:"unfuse_transformer"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L5045"}}),Ot=new C({props:{warning:!0,$$slots:{default:[Wb]},$$scope:{ctx:T}}}),Sn=new X({props:{title:"CogView4LoraLoaderMixin",local:"diffusers.loaders.CogView4LoraLoaderMixin",headingTag:"h2"}}),kn=new M({props:{name:"class diffusers.loaders.CogView4LoraLoaderMixin",anchor:"diffusers.loaders.CogView4LoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L5896"}}),Rn=new M({props:{name:"load_lora_into_transformer",anchor:"diffusers.loaders.CogView4LoraLoaderMixin.load_lora_into_transformer",parameters:[{name:"state_dict",val:""},{name:"transformer",val:""},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.load_lora_into_transformer.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The keys can either be indexed directly
into the unet or prefixed with an additional <code>unet</code> which can be used to distinguish between text
encoder lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.load_lora_into_transformer.transformer",description:`<strong>transformer</strong> (<code>CogView4Transformer2DModel</code>) &#x2014;
The Transformer model to load the LoRA layers into.`,name:"transformer"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.load_lora_into_transformer.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.load_lora_into_transformer.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.load_lora_into_transformer.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.load_lora_into_transformer.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L6063"}}),An=new M({props:{name:"load_lora_weights",anchor:"diffusers.loaders.CogView4LoraLoaderMixin.load_lora_weights",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"adapter_name",val:": typing.Optional[str] = None"},{name:"hotswap",val:": bool = False"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.load_lora_weights.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.load_lora_weights.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.load_lora_weights.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.load_lora_weights.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.load_lora_weights.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L6004"}}),In=new M({props:{name:"lora_state_dict",anchor:"diffusers.loaders.CogView4LoraLoaderMixin.lora_state_dict",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.lora_state_dict.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
Can be either:</p>
<ul>
<li>A string, the <em>model id</em> (for example <code>google/ddpm-celebahq-256</code>) of a pretrained model hosted on
the Hub.</li>
<li>A path to a <em>directory</em> (for example <code>./my_model_directory</code>) containing the model weights saved
with <a href="/docs/diffusers/pr_12242/en/api/models/overview#diffusers.ModelMixin.save_pretrained">ModelMixin.save_pretrained()</a>.</li>
<li>A <a href="https://pytorch.org/tutorials/beginner/saving_loading_models.html#what-is-a-state-dict" rel="nofollow">torch state
dict</a>.</li>
</ul>`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.lora_state_dict.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) &#x2014;
Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
is not used.`,name:"cache_dir"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.lora_state_dict.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether or not to force the (re-)download of the model weights and configuration files, overriding the
cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.lora_state_dict.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) &#x2014;
A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{&apos;http&apos;: &apos;foo.bar:3128&apos;, &apos;http://hostname&apos;: &apos;foo.bar:4012&apos;}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.lora_state_dict.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
won&#x2019;t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.lora_state_dict.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) &#x2014;
The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.lora_state_dict.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;main&quot;</code>) &#x2014;
The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
allowed by Git.`,name:"revision"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.lora_state_dict.subfolder",description:`<strong>subfolder</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;&quot;</code>) &#x2014;
The subfolder location of a model file within a larger model repository on the Hub or locally.`,name:"subfolder"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.lora_state_dict.return_lora_metadata",description:`<strong>return_lora_metadata</strong> (<code>bool</code>, <em>optional</em>, defaults to False) &#x2014;
When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.`,name:"return_lora_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L5904"}}),oa=new C({props:{warning:!0,$$slots:{default:[Xb]},$$scope:{ctx:T}}}),Un=new M({props:{name:"save_lora_weights",anchor:"diffusers.loaders.CogView4LoraLoaderMixin.save_lora_weights",parameters:[{name:"save_directory",val:": typing.Union[str, os.PathLike]"},{name:"transformer_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"is_main_process",val:": bool = True"},{name:"weight_name",val:": str = None"},{name:"save_function",val:": typing.Callable = None"},{name:"safe_serialization",val:": bool = True"},{name:"transformer_lora_adapter_metadata",val:": typing.Optional[dict] = None"}],parametersDescription:[{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.save_lora_weights.save_directory",description:`<strong>save_directory</strong> (<code>str</code> or <code>os.PathLike</code>) &#x2014;
Directory to save LoRA parameters to. Will be created if it doesn&#x2019;t exist.`,name:"save_directory"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.save_lora_weights.transformer_lora_layers",description:`<strong>transformer_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>transformer</code>.`,name:"transformer_lora_layers"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.save_lora_weights.is_main_process",description:`<strong>is_main_process</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether the process calling this is the main process or not. Useful during distributed training and you
need to call this function on all processes. In this case, set <code>is_main_process=True</code> only on the main
process to avoid race conditions.`,name:"is_main_process"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.save_lora_weights.save_function",description:`<strong>save_function</strong> (<code>Callable</code>) &#x2014;
The function to use to save the state dictionary. Useful during distributed training when you need to
replace <code>torch.save</code> with another method. Can be configured with the environment variable
<code>DIFFUSERS_SAVE_MODE</code>.`,name:"save_function"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.save_lora_weights.safe_serialization",description:`<strong>safe_serialization</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to save the model using <code>safetensors</code> or the traditional PyTorch way with <code>pickle</code>.`,name:"safe_serialization"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.save_lora_weights.transformer_lora_adapter_metadata",description:`<strong>transformer_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the transformer to be serialized with the state dict.`,name:"transformer_lora_adapter_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L6114"}}),Vn=new M({props:{name:"unfuse_lora",anchor:"diffusers.loaders.CogView4LoraLoaderMixin.unfuse_lora",parameters:[{name:"components",val:": typing.List[str] = ['transformer']"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.unfuse_lora.components",description:"<strong>components</strong> (<code>List[str]</code>) &#x2014; List of LoRA-injectable components to unfuse LoRA from.",name:"components"},{anchor:"diffusers.loaders.CogView4LoraLoaderMixin.unfuse_lora.unfuse_transformer",description:"<strong>unfuse_transformer</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014; Whether to unfuse the UNet LoRA parameters.",name:"unfuse_transformer"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L6220"}}),aa=new C({props:{warning:!0,$$slots:{default:[Pb]},$$scope:{ctx:T}}}),Wn=new X({props:{title:"WanLoraLoaderMixin",local:"diffusers.loaders.WanLoraLoaderMixin",headingTag:"h2"}}),Xn=new M({props:{name:"class diffusers.loaders.WanLoraLoaderMixin",anchor:"diffusers.loaders.WanLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L5063"}}),Pn=new M({props:{name:"load_lora_into_transformer",anchor:"diffusers.loaders.WanLoraLoaderMixin.load_lora_into_transformer",parameters:[{name:"state_dict",val:""},{name:"transformer",val:""},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.WanLoraLoaderMixin.load_lora_into_transformer.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The keys can either be indexed directly
into the unet or prefixed with an additional <code>unet</code> which can be used to distinguish between text
encoder lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.load_lora_into_transformer.transformer",description:`<strong>transformer</strong> (<code>WanTransformer3DModel</code>) &#x2014;
The Transformer model to load the LoRA layers into.`,name:"transformer"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.load_lora_into_transformer.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.load_lora_into_transformer.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.load_lora_into_transformer.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.load_lora_into_transformer.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L5303"}}),Fn=new M({props:{name:"load_lora_weights",anchor:"diffusers.loaders.WanLoraLoaderMixin.load_lora_weights",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"adapter_name",val:": typing.Optional[str] = None"},{name:"hotswap",val:": bool = False"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.WanLoraLoaderMixin.load_lora_weights.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.load_lora_weights.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.load_lora_weights.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.load_lora_weights.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.load_lora_weights.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L5220"}}),Jn=new M({props:{name:"lora_state_dict",anchor:"diffusers.loaders.WanLoraLoaderMixin.lora_state_dict",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.WanLoraLoaderMixin.lora_state_dict.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
Can be either:</p>
<ul>
<li>A string, the <em>model id</em> (for example <code>google/ddpm-celebahq-256</code>) of a pretrained model hosted on
the Hub.</li>
<li>A path to a <em>directory</em> (for example <code>./my_model_directory</code>) containing the model weights saved
with <a href="/docs/diffusers/pr_12242/en/api/models/overview#diffusers.ModelMixin.save_pretrained">ModelMixin.save_pretrained()</a>.</li>
<li>A <a href="https://pytorch.org/tutorials/beginner/saving_loading_models.html#what-is-a-state-dict" rel="nofollow">torch state
dict</a>.</li>
</ul>`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.lora_state_dict.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) &#x2014;
Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
is not used.`,name:"cache_dir"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.lora_state_dict.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether or not to force the (re-)download of the model weights and configuration files, overriding the
cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.lora_state_dict.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) &#x2014;
A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{&apos;http&apos;: &apos;foo.bar:3128&apos;, &apos;http://hostname&apos;: &apos;foo.bar:4012&apos;}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.lora_state_dict.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
won&#x2019;t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.lora_state_dict.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) &#x2014;
The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.lora_state_dict.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;main&quot;</code>) &#x2014;
The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
allowed by Git.`,name:"revision"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.lora_state_dict.subfolder",description:`<strong>subfolder</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;&quot;</code>) &#x2014;
The subfolder location of a model file within a larger model repository on the Hub or locally.`,name:"subfolder"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.lora_state_dict.return_lora_metadata",description:`<strong>return_lora_metadata</strong> (<code>bool</code>, <em>optional</em>, defaults to False) &#x2014;
When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.`,name:"return_lora_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L5071"}}),sa=new C({props:{warning:!0,$$slots:{default:[Fb]},$$scope:{ctx:T}}}),Hn=new M({props:{name:"save_lora_weights",anchor:"diffusers.loaders.WanLoraLoaderMixin.save_lora_weights",parameters:[{name:"save_directory",val:": typing.Union[str, os.PathLike]"},{name:"transformer_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"is_main_process",val:": bool = True"},{name:"weight_name",val:": str = None"},{name:"save_function",val:": typing.Callable = None"},{name:"safe_serialization",val:": bool = True"},{name:"transformer_lora_adapter_metadata",val:": typing.Optional[dict] = None"}],parametersDescription:[{anchor:"diffusers.loaders.WanLoraLoaderMixin.save_lora_weights.save_directory",description:`<strong>save_directory</strong> (<code>str</code> or <code>os.PathLike</code>) &#x2014;
Directory to save LoRA parameters to. Will be created if it doesn&#x2019;t exist.`,name:"save_directory"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.save_lora_weights.transformer_lora_layers",description:`<strong>transformer_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>transformer</code>.`,name:"transformer_lora_layers"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.save_lora_weights.is_main_process",description:`<strong>is_main_process</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether the process calling this is the main process or not. Useful during distributed training and you
need to call this function on all processes. In this case, set <code>is_main_process=True</code> only on the main
process to avoid race conditions.`,name:"is_main_process"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.save_lora_weights.save_function",description:`<strong>save_function</strong> (<code>Callable</code>) &#x2014;
The function to use to save the state dictionary. Useful during distributed training when you need to
replace <code>torch.save</code> with another method. Can be configured with the environment variable
<code>DIFFUSERS_SAVE_MODE</code>.`,name:"save_function"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.save_lora_weights.safe_serialization",description:`<strong>safe_serialization</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to save the model using <code>safetensors</code> or the traditional PyTorch way with <code>pickle</code>.`,name:"safe_serialization"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.save_lora_weights.transformer_lora_adapter_metadata",description:`<strong>transformer_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the transformer to be serialized with the state dict.`,name:"transformer_lora_adapter_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L5354"}}),jn=new M({props:{name:"unfuse_lora",anchor:"diffusers.loaders.WanLoraLoaderMixin.unfuse_lora",parameters:[{name:"components",val:": typing.List[str] = ['transformer']"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.WanLoraLoaderMixin.unfuse_lora.components",description:"<strong>components</strong> (<code>List[str]</code>) &#x2014; List of LoRA-injectable components to unfuse LoRA from.",name:"components"},{anchor:"diffusers.loaders.WanLoraLoaderMixin.unfuse_lora.unfuse_transformer",description:"<strong>unfuse_transformer</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014; Whether to unfuse the UNet LoRA parameters.",name:"unfuse_transformer"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L5460"}}),da=new C({props:{warning:!0,$$slots:{default:[Jb]},$$scope:{ctx:T}}}),Zn=new X({props:{title:"SkyReelsV2LoraLoaderMixin",local:"diffusers.loaders.SkyReelsV2LoraLoaderMixin",headingTag:"h2"}}),Gn=new M({props:{name:"class diffusers.loaders.SkyReelsV2LoraLoaderMixin",anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L5478"}}),qn=new M({props:{name:"load_lora_into_transformer",anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.load_lora_into_transformer",parameters:[{name:"state_dict",val:""},{name:"transformer",val:""},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.load_lora_into_transformer.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The keys can either be indexed directly
into the unet or prefixed with an additional <code>unet</code> which can be used to distinguish between text
encoder lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.load_lora_into_transformer.transformer",description:`<strong>transformer</strong> (<code>SkyReelsV2Transformer3DModel</code>) &#x2014;
The Transformer model to load the LoRA layers into.`,name:"transformer"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.load_lora_into_transformer.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.load_lora_into_transformer.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.load_lora_into_transformer.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.load_lora_into_transformer.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L5721"}}),Bn=new M({props:{name:"load_lora_weights",anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.load_lora_weights",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"adapter_name",val:": typing.Optional[str] = None"},{name:"hotswap",val:": bool = False"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.load_lora_weights.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.load_lora_weights.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.load_lora_weights.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.load_lora_weights.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.load_lora_weights.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L5638"}}),En=new M({props:{name:"lora_state_dict",anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.lora_state_dict",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.lora_state_dict.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
Can be either:</p>
<ul>
<li>A string, the <em>model id</em> (for example <code>google/ddpm-celebahq-256</code>) of a pretrained model hosted on
the Hub.</li>
<li>A path to a <em>directory</em> (for example <code>./my_model_directory</code>) containing the model weights saved
with <a href="/docs/diffusers/pr_12242/en/api/models/overview#diffusers.ModelMixin.save_pretrained">ModelMixin.save_pretrained()</a>.</li>
<li>A <a href="https://pytorch.org/tutorials/beginner/saving_loading_models.html#what-is-a-state-dict" rel="nofollow">torch state
dict</a>.</li>
</ul>`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.lora_state_dict.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) &#x2014;
Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
is not used.`,name:"cache_dir"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.lora_state_dict.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether or not to force the (re-)download of the model weights and configuration files, overriding the
cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.lora_state_dict.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) &#x2014;
A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{&apos;http&apos;: &apos;foo.bar:3128&apos;, &apos;http://hostname&apos;: &apos;foo.bar:4012&apos;}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.lora_state_dict.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
won&#x2019;t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.lora_state_dict.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) &#x2014;
The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.lora_state_dict.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;main&quot;</code>) &#x2014;
The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
allowed by Git.`,name:"revision"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.lora_state_dict.subfolder",description:`<strong>subfolder</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;&quot;</code>) &#x2014;
The subfolder location of a model file within a larger model repository on the Hub or locally.`,name:"subfolder"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.lora_state_dict.return_lora_metadata",description:`<strong>return_lora_metadata</strong> (<code>bool</code>, <em>optional</em>, defaults to False) &#x2014;
When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.`,name:"return_lora_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L5486"}}),fa=new C({props:{warning:!0,$$slots:{default:[Hb]},$$scope:{ctx:T}}}),Nn=new M({props:{name:"save_lora_weights",anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.save_lora_weights",parameters:[{name:"save_directory",val:": typing.Union[str, os.PathLike]"},{name:"transformer_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"is_main_process",val:": bool = True"},{name:"weight_name",val:": str = None"},{name:"save_function",val:": typing.Callable = None"},{name:"safe_serialization",val:": bool = True"},{name:"transformer_lora_adapter_metadata",val:": typing.Optional[dict] = None"}],parametersDescription:[{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.save_lora_weights.save_directory",description:`<strong>save_directory</strong> (<code>str</code> or <code>os.PathLike</code>) &#x2014;
Directory to save LoRA parameters to. Will be created if it doesn&#x2019;t exist.`,name:"save_directory"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.save_lora_weights.transformer_lora_layers",description:`<strong>transformer_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>transformer</code>.`,name:"transformer_lora_layers"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.save_lora_weights.is_main_process",description:`<strong>is_main_process</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether the process calling this is the main process or not. Useful during distributed training and you
need to call this function on all processes. In this case, set <code>is_main_process=True</code> only on the main
process to avoid race conditions.`,name:"is_main_process"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.save_lora_weights.save_function",description:`<strong>save_function</strong> (<code>Callable</code>) &#x2014;
The function to use to save the state dictionary. Useful during distributed training when you need to
replace <code>torch.save</code> with another method. Can be configured with the environment variable
<code>DIFFUSERS_SAVE_MODE</code>.`,name:"save_function"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.save_lora_weights.safe_serialization",description:`<strong>safe_serialization</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to save the model using <code>safetensors</code> or the traditional PyTorch way with <code>pickle</code>.`,name:"safe_serialization"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.save_lora_weights.transformer_lora_adapter_metadata",description:`<strong>transformer_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the transformer to be serialized with the state dict.`,name:"transformer_lora_adapter_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L5772"}}),zn=new M({props:{name:"unfuse_lora",anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.unfuse_lora",parameters:[{name:"components",val:": typing.List[str] = ['transformer']"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.unfuse_lora.components",description:"<strong>components</strong> (<code>List[str]</code>) &#x2014; List of LoRA-injectable components to unfuse LoRA from.",name:"components"},{anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin.unfuse_lora.unfuse_transformer",description:"<strong>unfuse_transformer</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014; Whether to unfuse the UNet LoRA parameters.",name:"unfuse_transformer"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L5878"}}),ma=new C({props:{warning:!0,$$slots:{default:[jb]},$$scope:{ctx:T}}}),Yn=new X({props:{title:"AmusedLoraLoaderMixin",local:"diffusers.loaders.AmusedLoraLoaderMixin",headingTag:"h2"}}),Qn=new M({props:{name:"class diffusers.loaders.AmusedLoraLoaderMixin",anchor:"diffusers.loaders.AmusedLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L2832"}}),On=new M({props:{name:"load_lora_into_transformer",anchor:"diffusers.loaders.AmusedLoraLoaderMixin.load_lora_into_transformer",parameters:[{name:"state_dict",val:""},{name:"network_alphas",val:""},{name:"transformer",val:""},{name:"adapter_name",val:" = None"},{name:"metadata",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"}],parametersDescription:[{anchor:"diffusers.loaders.AmusedLoraLoaderMixin.load_lora_into_transformer.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The keys can either be indexed directly
into the unet or prefixed with an additional <code>unet</code> which can be used to distinguish between text
encoder lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.AmusedLoraLoaderMixin.load_lora_into_transformer.network_alphas",description:`<strong>network_alphas</strong> (<code>Dict[str, float]</code>) &#x2014;
The value of the network alpha used for stable learning and preventing underflow. This value has the
same meaning as the <code>--network_alpha</code> option in the kohya-ss trainer script. Refer to <a href="https://github.com/darkstorm2150/sd-scripts/blob/main/docs/train_network_README-en.md#execute-learning" rel="nofollow">this
link</a>.`,name:"network_alphas"},{anchor:"diffusers.loaders.AmusedLoraLoaderMixin.load_lora_into_transformer.transformer",description:`<strong>transformer</strong> (<code>UVit2DModel</code>) &#x2014;
The Transformer model to load the LoRA layers into.`,name:"transformer"},{anchor:"diffusers.loaders.AmusedLoraLoaderMixin.load_lora_into_transformer.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.AmusedLoraLoaderMixin.load_lora_into_transformer.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.AmusedLoraLoaderMixin.load_lora_into_transformer.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.AmusedLoraLoaderMixin.load_lora_into_transformer.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L2837"}}),Kn=new M({props:{name:"save_lora_weights",anchor:"diffusers.loaders.AmusedLoraLoaderMixin.save_lora_weights",parameters:[{name:"save_directory",val:": typing.Union[str, os.PathLike]"},{name:"text_encoder_lora_layers",val:": typing.Dict[str, torch.nn.modules.module.Module] = None"},{name:"transformer_lora_layers",val:": typing.Dict[str, torch.nn.modules.module.Module] = None"},{name:"is_main_process",val:": bool = True"},{name:"weight_name",val:": str = None"},{name:"save_function",val:": typing.Callable = None"},{name:"safe_serialization",val:": bool = True"}],parametersDescription:[{anchor:"diffusers.loaders.AmusedLoraLoaderMixin.save_lora_weights.save_directory",description:`<strong>save_directory</strong> (<code>str</code> or <code>os.PathLike</code>) &#x2014;
Directory to save LoRA parameters to. Will be created if it doesn&#x2019;t exist.`,name:"save_directory"},{anchor:"diffusers.loaders.AmusedLoraLoaderMixin.save_lora_weights.unet_lora_layers",description:`<strong>unet_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>unet</code>.`,name:"unet_lora_layers"},{anchor:"diffusers.loaders.AmusedLoraLoaderMixin.save_lora_weights.text_encoder_lora_layers",description:`<strong>text_encoder_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>text_encoder</code>. Must explicitly pass the text
encoder LoRA state dict because it comes from &#x1F917; Transformers.`,name:"text_encoder_lora_layers"},{anchor:"diffusers.loaders.AmusedLoraLoaderMixin.save_lora_weights.is_main_process",description:`<strong>is_main_process</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether the process calling this is the main process or not. Useful during distributed training and you
need to call this function on all processes. In this case, set <code>is_main_process=True</code> only on the main
process to avoid race conditions.`,name:"is_main_process"},{anchor:"diffusers.loaders.AmusedLoraLoaderMixin.save_lora_weights.save_function",description:`<strong>save_function</strong> (<code>Callable</code>) &#x2014;
The function to use to save the state dictionary. Useful during distributed training when you need to
replace <code>torch.save</code> with another method. Can be configured with the environment variable
<code>DIFFUSERS_SAVE_MODE</code>.`,name:"save_function"},{anchor:"diffusers.loaders.AmusedLoraLoaderMixin.save_lora_weights.safe_serialization",description:`<strong>safe_serialization</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to save the model using <code>safetensors</code> or the traditional PyTorch way with <code>pickle</code>.`,name:"safe_serialization"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L2952"}}),es=new X({props:{title:"HiDreamImageLoraLoaderMixin",local:"diffusers.loaders.HiDreamImageLoraLoaderMixin",headingTag:"h2"}}),os=new M({props:{name:"class diffusers.loaders.HiDreamImageLoraLoaderMixin",anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L6238"}}),ts=new M({props:{name:"load_lora_into_transformer",anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.load_lora_into_transformer",parameters:[{name:"state_dict",val:""},{name:"transformer",val:""},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.load_lora_into_transformer.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The keys can either be indexed directly
into the unet or prefixed with an additional <code>unet</code> which can be used to distinguish between text
encoder lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.load_lora_into_transformer.transformer",description:`<strong>transformer</strong> (<code>HiDreamImageTransformer2DModel</code>) &#x2014;
The Transformer model to load the LoRA layers into.`,name:"transformer"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.load_lora_into_transformer.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.load_lora_into_transformer.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.load_lora_into_transformer.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.load_lora_into_transformer.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L6407"}}),as=new M({props:{name:"load_lora_weights",anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.load_lora_weights",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"adapter_name",val:": typing.Optional[str] = None"},{name:"hotswap",val:": bool = False"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.load_lora_weights.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.load_lora_weights.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.load_lora_weights.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.load_lora_weights.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.load_lora_weights.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L6348"}}),rs=new M({props:{name:"lora_state_dict",anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.lora_state_dict",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.lora_state_dict.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
Can be either:</p>
<ul>
<li>A string, the <em>model id</em> (for example <code>google/ddpm-celebahq-256</code>) of a pretrained model hosted on
the Hub.</li>
<li>A path to a <em>directory</em> (for example <code>./my_model_directory</code>) containing the model weights saved
with <a href="/docs/diffusers/pr_12242/en/api/models/overview#diffusers.ModelMixin.save_pretrained">ModelMixin.save_pretrained()</a>.</li>
<li>A <a href="https://pytorch.org/tutorials/beginner/saving_loading_models.html#what-is-a-state-dict" rel="nofollow">torch state
dict</a>.</li>
</ul>`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.lora_state_dict.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) &#x2014;
Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
is not used.`,name:"cache_dir"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.lora_state_dict.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether or not to force the (re-)download of the model weights and configuration files, overriding the
cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.lora_state_dict.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) &#x2014;
A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{&apos;http&apos;: &apos;foo.bar:3128&apos;, &apos;http://hostname&apos;: &apos;foo.bar:4012&apos;}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.lora_state_dict.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
won&#x2019;t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.lora_state_dict.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) &#x2014;
The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.lora_state_dict.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;main&quot;</code>) &#x2014;
The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
allowed by Git.`,name:"revision"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.lora_state_dict.subfolder",description:`<strong>subfolder</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;&quot;</code>) &#x2014;
The subfolder location of a model file within a larger model repository on the Hub or locally.`,name:"subfolder"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.lora_state_dict.return_lora_metadata",description:`<strong>return_lora_metadata</strong> (<code>bool</code>, <em>optional</em>, defaults to False) &#x2014;
When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.`,name:"return_lora_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L6246"}}),xa=new C({props:{warning:!0,$$slots:{default:[Zb]},$$scope:{ctx:T}}}),ns=new M({props:{name:"save_lora_weights",anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.save_lora_weights",parameters:[{name:"save_directory",val:": typing.Union[str, os.PathLike]"},{name:"transformer_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"is_main_process",val:": bool = True"},{name:"weight_name",val:": str = None"},{name:"save_function",val:": typing.Callable = None"},{name:"safe_serialization",val:": bool = True"},{name:"transformer_lora_adapter_metadata",val:": typing.Optional[dict] = None"}],parametersDescription:[{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.save_lora_weights.save_directory",description:`<strong>save_directory</strong> (<code>str</code> or <code>os.PathLike</code>) &#x2014;
Directory to save LoRA parameters to. Will be created if it doesn&#x2019;t exist.`,name:"save_directory"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.save_lora_weights.transformer_lora_layers",description:`<strong>transformer_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>transformer</code>.`,name:"transformer_lora_layers"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.save_lora_weights.is_main_process",description:`<strong>is_main_process</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether the process calling this is the main process or not. Useful during distributed training and you
need to call this function on all processes. In this case, set <code>is_main_process=True</code> only on the main
process to avoid race conditions.`,name:"is_main_process"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.save_lora_weights.save_function",description:`<strong>save_function</strong> (<code>Callable</code>) &#x2014;
The function to use to save the state dictionary. Useful during distributed training when you need to
replace <code>torch.save</code> with another method. Can be configured with the environment variable
<code>DIFFUSERS_SAVE_MODE</code>.`,name:"save_function"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.save_lora_weights.safe_serialization",description:`<strong>safe_serialization</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to save the model using <code>safetensors</code> or the traditional PyTorch way with <code>pickle</code>.`,name:"safe_serialization"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.save_lora_weights.transformer_lora_adapter_metadata",description:`<strong>transformer_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the transformer to be serialized with the state dict.`,name:"transformer_lora_adapter_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L6458"}}),ss=new M({props:{name:"unfuse_lora",anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.unfuse_lora",parameters:[{name:"components",val:": typing.List[str] = ['transformer']"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.unfuse_lora.components",description:"<strong>components</strong> (<code>List[str]</code>) &#x2014; List of LoRA-injectable components to unfuse LoRA from.",name:"components"},{anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin.unfuse_lora.unfuse_transformer",description:"<strong>unfuse_transformer</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014; Whether to unfuse the UNet LoRA parameters.",name:"unfuse_transformer"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L6564"}}),ba=new C({props:{warning:!0,$$slots:{default:[Gb]},$$scope:{ctx:T}}}),is=new X({props:{title:"QwenImageLoraLoaderMixin",local:"diffusers.loaders.QwenImageLoraLoaderMixin",headingTag:"h2"}}),ds=new M({props:{name:"class diffusers.loaders.QwenImageLoraLoaderMixin",anchor:"diffusers.loaders.QwenImageLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L6582"}}),ls=new M({props:{name:"load_lora_into_transformer",anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.load_lora_into_transformer",parameters:[{name:"state_dict",val:""},{name:"transformer",val:""},{name:"adapter_name",val:" = None"},{name:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = False"},{name:"hotswap",val:": bool = False"},{name:"metadata",val:" = None"}],parametersDescription:[{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.load_lora_into_transformer.state_dict",description:`<strong>state_dict</strong> (<code>dict</code>) &#x2014;
A standard state dict containing the lora layer parameters. The keys can either be indexed directly
into the unet or prefixed with an additional <code>unet</code> which can be used to distinguish between text
encoder lora layers.`,name:"state_dict"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.load_lora_into_transformer.transformer",description:`<strong>transformer</strong> (<code>QwenImageTransformer2DModel</code>) &#x2014;
The Transformer model to load the LoRA layers into.`,name:"transformer"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.load_lora_into_transformer.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.load_lora_into_transformer.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.load_lora_into_transformer.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.load_lora_into_transformer.metadata",description:`<strong>metadata</strong> (<code>dict</code>) &#x2014;
Optional LoRA adapter metadata. When supplied, the <code>LoraConfig</code> arguments of <code>peft</code> won&#x2019;t be derived
from the state dict.`,name:"metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L6754"}}),cs=new M({props:{name:"load_lora_weights",anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.load_lora_weights",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"adapter_name",val:": typing.Optional[str] = None"},{name:"hotswap",val:": bool = False"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.load_lora_weights.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.load_lora_weights.adapter_name",description:`<strong>adapter_name</strong> (<code>str</code>, <em>optional</em>) &#x2014;
Adapter name to be used for referencing the loaded adapter model. If not specified, it will use
<code>default_{i}</code> where i is the total number of adapters being loaded.`,name:"adapter_name"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.load_lora_weights.low_cpu_mem_usage",description:`<strong>low_cpu_mem_usage</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
Speed up model loading by only loading the pretrained LoRA weights and not initializing the random
weights.`,name:"low_cpu_mem_usage"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.load_lora_weights.hotswap",description:`<strong>hotswap</strong> (<code>bool</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a>.`,name:"hotswap"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.load_lora_weights.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_12242/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L6695"}}),fs=new M({props:{name:"lora_state_dict",anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.lora_state_dict",parameters:[{name:"pretrained_model_name_or_path_or_dict",val:": typing.Union[str, typing.Dict[str, torch.Tensor]]"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.lora_state_dict.pretrained_model_name_or_path_or_dict",description:`<strong>pretrained_model_name_or_path_or_dict</strong> (<code>str</code> or <code>os.PathLike</code> or <code>dict</code>) &#x2014;
Can be either:</p>
<ul>
<li>A string, the <em>model id</em> (for example <code>google/ddpm-celebahq-256</code>) of a pretrained model hosted on
the Hub.</li>
<li>A path to a <em>directory</em> (for example <code>./my_model_directory</code>) containing the model weights saved
with <a href="/docs/diffusers/pr_12242/en/api/models/overview#diffusers.ModelMixin.save_pretrained">ModelMixin.save_pretrained()</a>.</li>
<li>A <a href="https://pytorch.org/tutorials/beginner/saving_loading_models.html#what-is-a-state-dict" rel="nofollow">torch state
dict</a>.</li>
</ul>`,name:"pretrained_model_name_or_path_or_dict"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.lora_state_dict.cache_dir",description:`<strong>cache_dir</strong> (<code>Union[str, os.PathLike]</code>, <em>optional</em>) &#x2014;
Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
is not used.`,name:"cache_dir"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.lora_state_dict.force_download",description:`<strong>force_download</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether or not to force the (re-)download of the model weights and configuration files, overriding the
cached versions if they exist.`,name:"force_download"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.lora_state_dict.proxies",description:`<strong>proxies</strong> (<code>Dict[str, str]</code>, <em>optional</em>) &#x2014;
A dictionary of proxy servers to use by protocol or endpoint, for example, <code>{&apos;http&apos;: &apos;foo.bar:3128&apos;, &apos;http://hostname&apos;: &apos;foo.bar:4012&apos;}</code>. The proxies are used on each request.`,name:"proxies"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.lora_state_dict.local_files_only",description:`<strong>local_files_only</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>False</code>) &#x2014;
Whether to only load local model weights and configuration files or not. If set to <code>True</code>, the model
won&#x2019;t be downloaded from the Hub.`,name:"local_files_only"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.lora_state_dict.token",description:`<strong>token</strong> (<code>str</code> or <em>bool</em>, <em>optional</em>) &#x2014;
The token to use as HTTP bearer authorization for remote files. If <code>True</code>, the token generated from
<code>diffusers-cli login</code> (stored in <code>~/.huggingface</code>) is used.`,name:"token"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.lora_state_dict.revision",description:`<strong>revision</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;main&quot;</code>) &#x2014;
The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
allowed by Git.`,name:"revision"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.lora_state_dict.subfolder",description:`<strong>subfolder</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;&quot;</code>) &#x2014;
The subfolder location of a model file within a larger model repository on the Hub or locally.`,name:"subfolder"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.lora_state_dict.return_lora_metadata",description:`<strong>return_lora_metadata</strong> (<code>bool</code>, <em>optional</em>, defaults to False) &#x2014;
When enabled, additionally return the LoRA adapter metadata, typically found in the state dict.`,name:"return_lora_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L6590"}}),$a=new C({props:{warning:!0,$$slots:{default:[qb]},$$scope:{ctx:T}}}),ps=new M({props:{name:"save_lora_weights",anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.save_lora_weights",parameters:[{name:"save_directory",val:": typing.Union[str, os.PathLike]"},{name:"transformer_lora_layers",val:": typing.Dict[str, typing.Union[torch.nn.modules.module.Module, torch.Tensor]] = None"},{name:"is_main_process",val:": bool = True"},{name:"weight_name",val:": str = None"},{name:"save_function",val:": typing.Callable = None"},{name:"safe_serialization",val:": bool = True"},{name:"transformer_lora_adapter_metadata",val:": typing.Optional[dict] = None"}],parametersDescription:[{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.save_lora_weights.save_directory",description:`<strong>save_directory</strong> (<code>str</code> or <code>os.PathLike</code>) &#x2014;
Directory to save LoRA parameters to. Will be created if it doesn&#x2019;t exist.`,name:"save_directory"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.save_lora_weights.transformer_lora_layers",description:`<strong>transformer_lora_layers</strong> (<code>Dict[str, torch.nn.Module]</code> or <code>Dict[str, torch.Tensor]</code>) &#x2014;
State dict of the LoRA layers corresponding to the <code>transformer</code>.`,name:"transformer_lora_layers"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.save_lora_weights.is_main_process",description:`<strong>is_main_process</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether the process calling this is the main process or not. Useful during distributed training and you
need to call this function on all processes. In this case, set <code>is_main_process=True</code> only on the main
process to avoid race conditions.`,name:"is_main_process"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.save_lora_weights.save_function",description:`<strong>save_function</strong> (<code>Callable</code>) &#x2014;
The function to use to save the state dictionary. Useful during distributed training when you need to
replace <code>torch.save</code> with another method. Can be configured with the environment variable
<code>DIFFUSERS_SAVE_MODE</code>.`,name:"save_function"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.save_lora_weights.safe_serialization",description:`<strong>safe_serialization</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) &#x2014;
Whether to save the model using <code>safetensors</code> or the traditional PyTorch way with <code>pickle</code>.`,name:"safe_serialization"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.save_lora_weights.transformer_lora_adapter_metadata",description:`<strong>transformer_lora_adapter_metadata</strong> &#x2014;
LoRA adapter metadata associated with the transformer to be serialized with the state dict.`,name:"transformer_lora_adapter_metadata"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L6805"}}),ms=new M({props:{name:"unfuse_lora",anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.unfuse_lora",parameters:[{name:"components",val:": typing.List[str] = ['transformer']"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.unfuse_lora.components",description:"<strong>components</strong> (<code>List[str]</code>) &#x2014; List of LoRA-injectable components to unfuse LoRA from.",name:"components"},{anchor:"diffusers.loaders.QwenImageLoraLoaderMixin.unfuse_lora.unfuse_transformer",description:"<strong>unfuse_transformer</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014; Whether to unfuse the UNet LoRA parameters.",name:"unfuse_transformer"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_pipeline.py#L6911"}}),Ma=new C({props:{warning:!0,$$slots:{default:[Bb]},$$scope:{ctx:T}}}),_s=new X({props:{title:"LoraBaseMixin",local:"diffusers.loaders.lora_base.LoraBaseMixin",headingTag:"h2"}}),us=new M({props:{name:"class diffusers.loaders.lora_base.LoraBaseMixin",anchor:"diffusers.loaders.lora_base.LoraBaseMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L478"}}),hs=new M({props:{name:"delete_adapters",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.delete_adapters",parameters:[{name:"adapter_names",val:": typing.Union[typing.List[str], str]"}],parametersDescription:[{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.delete_adapters.adapter_names",description:`<strong>adapter_names</strong> (<code>Union[List[str], str]</code>) &#x2014;
The names of the adapters to delete.`,name:"adapter_names"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L846"}}),Ta=new te({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.delete_adapters.example",$$slots:{default:[Eb]},$$scope:{ctx:T}}}),gs=new M({props:{name:"disable_lora",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.disable_lora",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L786"}}),Da=new te({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.disable_lora.example",$$slots:{default:[Nb]},$$scope:{ctx:T}}}),xs=new M({props:{name:"enable_lora",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.enable_lora",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L816"}}),Ca=new te({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.enable_lora.example",$$slots:{default:[zb]},$$scope:{ctx:T}}}),Ls=new M({props:{name:"enable_lora_hotswap",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.enable_lora_hotswap",parameters:[{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.enable_lora_hotswap.target_rank",description:`<strong>target_rank</strong> (<code>int</code>) &#x2014;
The highest rank among all the adapters that will be loaded.`,name:"target_rank"},{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.enable_lora_hotswap.check_compiled",description:`<strong>check_compiled</strong> (<code>str</code>, <em>optional</em>, defaults to <code>&quot;error&quot;</code>) &#x2014;
How to handle a model that is already compiled. The check can return the following messages:<ul>
<li>&#x201C;error&#x201D; (default): raise an error</li>
<li>&#x201C;warn&#x201D;: issue a warning</li>
<li>&#x201C;ignore&#x201D;: do nothing</li>
</ul>`,name:"check_compiled"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L993"}}),bs=new M({props:{name:"fuse_lora",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.fuse_lora",parameters:[{name:"components",val:": typing.List[str] = []"},{name:"lora_scale",val:": float = 1.0"},{name:"safe_fusing",val:": bool = False"},{name:"adapter_names",val:": typing.Optional[typing.List[str]] = None"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.fuse_lora.components",description:"<strong>components</strong> &#x2014; (<code>List[str]</code>): List of LoRA-injectable components to fuse the LoRAs into.",name:"components"},{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.fuse_lora.lora_scale",description:`<strong>lora_scale</strong> (<code>float</code>, defaults to 1.0) &#x2014;
Controls how much to influence the outputs with the LoRA parameters.`,name:"lora_scale"},{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.fuse_lora.safe_fusing",description:`<strong>safe_fusing</strong> (<code>bool</code>, defaults to <code>False</code>) &#x2014;
Whether to check fused weights for NaN values before fusing and if values are NaN not fusing them.`,name:"safe_fusing"},{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.fuse_lora.adapter_names",description:`<strong>adapter_names</strong> (<code>List[str]</code>, <em>optional</em>) &#x2014;
Adapter names to be used for fusing. If nothing is passed, all active adapters will be fused.`,name:"adapter_names"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L536"}}),ka=new C({props:{warning:!0,$$slots:{default:[Yb]},$$scope:{ctx:T}}}),Ra=new te({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.fuse_lora.example",$$slots:{default:[Qb]},$$scope:{ctx:T}}}),ws=new M({props:{name:"get_active_adapters",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.get_active_adapters",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L884"}}),Aa=new te({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.get_active_adapters.example",$$slots:{default:[Ob]},$$scope:{ctx:T}}}),vs=new M({props:{name:"get_list_adapters",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.get_list_adapters",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L917"}}),$s=new M({props:{name:"set_adapters",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_adapters",parameters:[{name:"adapter_names",val:": typing.Union[typing.List[str], str]"},{name:"adapter_weights",val:": typing.Union[float, typing.Dict, typing.List[float], typing.List[typing.Dict], NoneType] = None"}],parametersDescription:[{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_adapters.adapter_names",description:`<strong>adapter_names</strong> (<code>List[str]</code> or <code>str</code>) &#x2014;
The names of the adapters to use.`,name:"adapter_names"},{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_adapters.adapter_weights",description:`<strong>adapter_weights</strong> (<code>Union[List[float], float]</code>, <em>optional</em>) &#x2014;
The adapter(s) weights to use with the UNet. If <code>None</code>, the weights are set to <code>1.0</code> for all the
adapters.`,name:"adapter_weights"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L683"}}),Ua=new te({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_adapters.example",$$slots:{default:[Kb]},$$scope:{ctx:T}}}),ys=new M({props:{name:"set_lora_device",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_lora_device",parameters:[{name:"adapter_names",val:": typing.List[str]"},{name:"device",val:": typing.Union[torch.device, str, int]"}],parametersDescription:[{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_lora_device.adapter_names",description:`<strong>adapter_names</strong> (<code>List[str]</code>) &#x2014;
List of adapters to send device to.`,name:"adapter_names"},{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_lora_device.device",description:`<strong>device</strong> (<code>Union[torch.device, str, int]</code>) &#x2014;
Device to send the adapters to. Can be either a torch device, a str or an integer.`,name:"device"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L939"}}),Va=new te({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_lora_device.example",$$slots:{default:[e2]},$$scope:{ctx:T}}}),Ms=new M({props:{name:"unfuse_lora",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.unfuse_lora",parameters:[{name:"components",val:": typing.List[str] = []"},{name:"**kwargs",val:""}],parametersDescription:[{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.unfuse_lora.components",description:"<strong>components</strong> (<code>List[str]</code>) &#x2014; List of LoRA-injectable components to unfuse LoRA from.",name:"components"},{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.unfuse_lora.unfuse_unet",description:"<strong>unfuse_unet</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014; Whether to unfuse the UNet LoRA parameters.",name:"unfuse_unet"},{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.unfuse_lora.unfuse_text_encoder",description:`<strong>unfuse_text_encoder</strong> (<code>bool</code>, defaults to <code>True</code>) &#x2014;
Whether to unfuse the text encoder LoRA parameters. If the text encoder wasn&#x2019;t monkey-patched with the
LoRA parameters then it won&#x2019;t have any effect.`,name:"unfuse_text_encoder"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L626"}}),Wa=new C({props:{warning:!0,$$slots:{default:[o2]},$$scope:{ctx:T}}}),Ts=new M({props:{name:"unload_lora_weights",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.unload_lora_weights",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L513"}}),Xa=new te({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.unload_lora_weights.example",$$slots:{default:[t2]},$$scope:{ctx:T}}}),Ds=new M({props:{name:"write_lora_layers",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.write_lora_layers",parameters:[{name:"state_dict",val:": typing.Dict[str, torch.Tensor]"},{name:"save_directory",val:": str"},{name:"is_main_process",val:": bool"},{name:"weight_name",val:": str"},{name:"save_function",val:": typing.Callable"},{name:"safe_serialization",val:": bool"},{name:"lora_adapter_metadata",val:": typing.Optional[dict] = None"}],source:"https://github.com/huggingface/diffusers/blob/vr_12242/src/diffusers/loaders/lora_base.py#L1016"}}),Cs=new rb({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/loaders/lora.md"}}),{c(){t=s("meta"),b=r(),l=s("p"),c=r(),f(v.$$.fragment),a=r(),w=s("p"),w.innerHTML=_g,dc=r(),Ha=s("ul"),Ha.innerHTML=ug,lc=r(),f(Fo.$$.fragment),cc=r(),f(ja.$$.fragment),fc=r(),S=s("div"),f(Za.$$.fragment),If=r(),Ys=s("p"),Ys.textContent=hg,Uf=r(),Se=s("div"),f(Ga.$$.fragment),Vf=r(),Qs=s("p"),Qs.textContent=gg,Wf=r(),f(Jo.$$.fragment),Xf=r(),ke=s("div"),f(qa.$$.fragment),Pf=r(),Os=s("p"),Os.textContent=xg,Ff=r(),f(Ho.$$.fragment),Jf=r(),Re=s("div"),f(Ba.$$.fragment),Hf=r(),Ks=s("p"),Ks.textContent=Lg,jf=r(),f(jo.$$.fragment),Zf=r(),Zo=s("div"),f(Ea.$$.fragment),Gf=r(),ei=s("p"),ei.textContent=bg,qf=r(),ve=s("div"),f(Na.$$.fragment),Bf=r(),oi=s("p"),oi.textContent=wg,Ef=r(),f(Go.$$.fragment),Nf=r(),f(qo.$$.fragment),zf=r(),Ae=s("div"),f(za.$$.fragment),Yf=r(),ti=s("p"),ti.textContent=vg,Qf=r(),f(Bo.$$.fragment),Of=r(),Eo=s("div"),f(Ya.$$.fragment),Kf=r(),ai=s("p"),ai.textContent=$g,ep=r(),Ie=s("div"),f(Qa.$$.fragment),op=r(),ri=s("p"),ri.textContent=yg,tp=r(),f(No.$$.fragment),ap=r(),$e=s("div"),f(Oa.$$.fragment),rp=r(),ni=s("p"),ni.innerHTML=Mg,np=r(),si=s("p"),si.textContent=Tg,sp=r(),f(zo.$$.fragment),ip=r(),Ue=s("div"),f(Ka.$$.fragment),dp=r(),ii=s("p"),ii.innerHTML=Dg,lp=r(),f(Yo.$$.fragment),cp=r(),Ve=s("div"),f(er.$$.fragment),fp=r(),di=s("p"),di.textContent=Cg,pp=r(),f(Qo.$$.fragment),mp=r(),Oo=s("div"),f(or.$$.fragment),_p=r(),li=s("p"),li.textContent=Sg,pc=r(),f(tr.$$.fragment),mc=r(),P=s("div"),f(ar.$$.fragment),up=r(),ci=s("p"),ci.innerHTML=kg,hp=r(),Ko=s("div"),f(rr.$$.fragment),gp=r(),fi=s("p"),fi.innerHTML=Rg,xp=r(),et=s("div"),f(nr.$$.fragment),Lp=r(),pi=s("p"),pi.innerHTML=Ag,bp=r(),re=s("div"),f(sr.$$.fragment),wp=r(),mi=s("p"),mi.innerHTML=Ig,vp=r(),_i=s("p"),_i.innerHTML=Ug,$p=r(),ui=s("p"),ui.innerHTML=Vg,yp=r(),hi=s("p"),hi.innerHTML=Wg,Mp=r(),gi=s("p"),gi.innerHTML=Xg,Tp=r(),We=s("div"),f(ir.$$.fragment),Dp=r(),xi=s("p"),xi.textContent=Pg,Cp=r(),f(ot.$$.fragment),Sp=r(),tt=s("div"),f(dr.$$.fragment),kp=r(),Li=s("p"),Li.textContent=Fg,_c=r(),f(lr.$$.fragment),uc=r(),F=s("div"),f(cr.$$.fragment),Rp=r(),bi=s("p"),bi.innerHTML=Jg,Ap=r(),at=s("div"),f(fr.$$.fragment),Ip=r(),wi=s("p"),wi.innerHTML=Hg,Up=r(),rt=s("div"),f(pr.$$.fragment),Vp=r(),vi=s("p"),vi.innerHTML=jg,Wp=r(),ne=s("div"),f(mr.$$.fragment),Xp=r(),$i=s("p"),$i.innerHTML=Zg,Pp=r(),yi=s("p"),yi.innerHTML=Gg,Fp=r(),Mi=s("p"),Mi.innerHTML=qg,Jp=r(),Ti=s("p"),Ti.innerHTML=Bg,Hp=r(),Di=s("p"),Di.innerHTML=Eg,jp=r(),Xe=s("div"),f(_r.$$.fragment),Zp=r(),Ci=s("p"),Ci.textContent=Ng,Gp=r(),f(nt.$$.fragment),qp=r(),st=s("div"),f(ur.$$.fragment),Bp=r(),Si=s("p"),Si.textContent=zg,hc=r(),f(hr.$$.fragment),gc=r(),U=s("div"),f(gr.$$.fragment),Ep=r(),ki=s("p"),ki.innerHTML=Yg,Np=r(),Ri=s("p"),Ri.innerHTML=Qg,zp=r(),it=s("div"),f(xr.$$.fragment),Yp=r(),Ai=s("p"),Ai.innerHTML=Og,Qp=r(),dt=s("div"),f(Lr.$$.fragment),Op=r(),Ii=s("p"),Ii.innerHTML=Kg,Kp=r(),de=s("div"),f(br.$$.fragment),em=r(),Ui=s("p"),Ui.innerHTML=ex,om=r(),Vi=s("p"),Vi.innerHTML=ox,tm=r(),Wi=s("p"),Wi.innerHTML=tx,am=r(),Xi=s("p"),Xi.innerHTML=ax,rm=r(),Pe=s("div"),f(wr.$$.fragment),nm=r(),Pi=s("p"),Pi.textContent=rx,sm=r(),f(lt.$$.fragment),im=r(),ct=s("div"),f(vr.$$.fragment),dm=r(),Fi=s("p"),Fi.textContent=nx,lm=r(),Fe=s("div"),f($r.$$.fragment),cm=r(),Ji=s("p"),Ji.innerHTML=sx,fm=r(),f(ft.$$.fragment),xc=r(),f(yr.$$.fragment),Lc=r(),I=s("div"),f(Mr.$$.fragment),pm=r(),Hi=s("p"),Hi.innerHTML=ix,mm=r(),ji=s("p"),ji.innerHTML=dx,_m=r(),pt=s("div"),f(Tr.$$.fragment),um=r(),Zi=s("p"),Zi.innerHTML=lx,hm=r(),mt=s("div"),f(Dr.$$.fragment),gm=r(),Gi=s("p"),Gi.innerHTML=cx,xm=r(),le=s("div"),f(Cr.$$.fragment),Lm=r(),qi=s("p"),qi.innerHTML=fx,bm=r(),Bi=s("p"),Bi.innerHTML=px,wm=r(),Ei=s("p"),Ei.innerHTML=mx,vm=r(),Ni=s("p"),Ni.innerHTML=_x,$m=r(),Je=s("div"),f(Sr.$$.fragment),ym=r(),zi=s("p"),zi.textContent=ux,Mm=r(),f(_t.$$.fragment),Tm=r(),ut=s("div"),f(kr.$$.fragment),Dm=r(),Yi=s("p"),Yi.textContent=hx,Cm=r(),He=s("div"),f(Rr.$$.fragment),Sm=r(),Qi=s("p"),Qi.innerHTML=gx,km=r(),f(ht.$$.fragment),Rm=r(),je=s("div"),f(Ar.$$.fragment),Am=r(),Oi=s("p"),Oi.textContent=xx,Im=r(),f(gt.$$.fragment),bc=r(),f(Ir.$$.fragment),wc=r(),J=s("div"),f(Ur.$$.fragment),Um=r(),Ki=s("p"),Ki.innerHTML=Lx,Vm=r(),xt=s("div"),f(Vr.$$.fragment),Wm=r(),ed=s("p"),ed.innerHTML=bx,Xm=r(),Lt=s("div"),f(Wr.$$.fragment),Pm=r(),od=s("p"),od.innerHTML=wx,Fm=r(),Ze=s("div"),f(Xr.$$.fragment),Jm=r(),td=s("p"),td.textContent=vx,Hm=r(),f(bt.$$.fragment),jm=r(),wt=s("div"),f(Pr.$$.fragment),Zm=r(),ad=s("p"),ad.textContent=$x,Gm=r(),Ge=s("div"),f(Fr.$$.fragment),qm=r(),rd=s("p"),rd.innerHTML=yx,Bm=r(),f(vt.$$.fragment),vc=r(),f(Jr.$$.fragment),$c=r(),H=s("div"),f(Hr.$$.fragment),Em=r(),nd=s("p"),nd.innerHTML=Mx,Nm=r(),$t=s("div"),f(jr.$$.fragment),zm=r(),sd=s("p"),sd.innerHTML=Tx,Ym=r(),yt=s("div"),f(Zr.$$.fragment),Qm=r(),id=s("p"),id.innerHTML=Dx,Om=r(),qe=s("div"),f(Gr.$$.fragment),Km=r(),dd=s("p"),dd.textContent=Cx,e_=r(),f(Mt.$$.fragment),o_=r(),Tt=s("div"),f(qr.$$.fragment),t_=r(),ld=s("p"),ld.textContent=Sx,a_=r(),Be=s("div"),f(Br.$$.fragment),r_=r(),cd=s("p"),cd.innerHTML=kx,n_=r(),f(Dt.$$.fragment),yc=r(),f(Er.$$.fragment),Mc=r(),j=s("div"),f(Nr.$$.fragment),s_=r(),fd=s("p"),fd.innerHTML=Rx,i_=r(),Ct=s("div"),f(zr.$$.fragment),d_=r(),pd=s("p"),pd.innerHTML=Ax,l_=r(),St=s("div"),f(Yr.$$.fragment),c_=r(),md=s("p"),md.innerHTML=Ix,f_=r(),Ee=s("div"),f(Qr.$$.fragment),p_=r(),_d=s("p"),_d.textContent=Ux,m_=r(),f(kt.$$.fragment),__=r(),Rt=s("div"),f(Or.$$.fragment),u_=r(),ud=s("p"),ud.textContent=Vx,h_=r(),Ne=s("div"),f(Kr.$$.fragment),g_=r(),hd=s("p"),hd.innerHTML=Wx,x_=r(),f(At.$$.fragment),Tc=r(),f(en.$$.fragment),Dc=r(),Z=s("div"),f(on.$$.fragment),L_=r(),gd=s("p"),gd.innerHTML=Xx,b_=r(),It=s("div"),f(tn.$$.fragment),w_=r(),xd=s("p"),xd.innerHTML=Px,v_=r(),Ut=s("div"),f(an.$$.fragment),$_=r(),Ld=s("p"),Ld.innerHTML=Fx,y_=r(),ze=s("div"),f(rn.$$.fragment),M_=r(),bd=s("p"),bd.textContent=Jx,T_=r(),f(Vt.$$.fragment),D_=r(),Wt=s("div"),f(nn.$$.fragment),C_=r(),wd=s("p"),wd.textContent=Hx,S_=r(),Ye=s("div"),f(sn.$$.fragment),k_=r(),vd=s("p"),vd.innerHTML=jx,R_=r(),f(Xt.$$.fragment),Cc=r(),f(dn.$$.fragment),Sc=r(),G=s("div"),f(ln.$$.fragment),A_=r(),$d=s("p"),$d.innerHTML=Zx,I_=r(),Pt=s("div"),f(cn.$$.fragment),U_=r(),yd=s("p"),yd.innerHTML=Gx,V_=r(),Ft=s("div"),f(fn.$$.fragment),W_=r(),Md=s("p"),Md.innerHTML=qx,X_=r(),Qe=s("div"),f(pn.$$.fragment),P_=r(),Td=s("p"),Td.textContent=Bx,F_=r(),f(Jt.$$.fragment),J_=r(),Ht=s("div"),f(mn.$$.fragment),H_=r(),Dd=s("p"),Dd.textContent=Ex,j_=r(),Oe=s("div"),f(_n.$$.fragment),Z_=r(),Cd=s("p"),Cd.innerHTML=Nx,G_=r(),f(jt.$$.fragment),kc=r(),f(un.$$.fragment),Rc=r(),q=s("div"),f(hn.$$.fragment),q_=r(),Sd=s("p"),Sd.innerHTML=zx,B_=r(),Zt=s("div"),f(gn.$$.fragment),E_=r(),kd=s("p"),kd.innerHTML=Yx,N_=r(),Gt=s("div"),f(xn.$$.fragment),z_=r(),Rd=s("p"),Rd.innerHTML=Qx,Y_=r(),Ke=s("div"),f(Ln.$$.fragment),Q_=r(),Ad=s("p"),Ad.textContent=Ox,O_=r(),f(qt.$$.fragment),K_=r(),Bt=s("div"),f(bn.$$.fragment),eu=r(),Id=s("p"),Id.textContent=Kx,ou=r(),eo=s("div"),f(wn.$$.fragment),tu=r(),Ud=s("p"),Ud.innerHTML=eL,au=r(),f(Et.$$.fragment),Ac=r(),f(vn.$$.fragment),Ic=r(),B=s("div"),f($n.$$.fragment),ru=r(),Vd=s("p"),Vd.innerHTML=oL,nu=r(),Nt=s("div"),f(yn.$$.fragment),su=r(),Wd=s("p"),Wd.innerHTML=tL,iu=r(),zt=s("div"),f(Mn.$$.fragment),du=r(),Xd=s("p"),Xd.innerHTML=aL,lu=r(),oo=s("div"),f(Tn.$$.fragment),cu=r(),Pd=s("p"),Pd.textContent=rL,fu=r(),f(Yt.$$.fragment),pu=r(),Qt=s("div"),f(Dn.$$.fragment),mu=r(),Fd=s("p"),Fd.textContent=nL,_u=r(),to=s("div"),f(Cn.$$.fragment),uu=r(),Jd=s("p"),Jd.innerHTML=sL,hu=r(),f(Ot.$$.fragment),Uc=r(),f(Sn.$$.fragment),Vc=r(),E=s("div"),f(kn.$$.fragment),gu=r(),Hd=s("p"),Hd.innerHTML=iL,xu=r(),Kt=s("div"),f(Rn.$$.fragment),Lu=r(),jd=s("p"),jd.innerHTML=dL,bu=r(),ea=s("div"),f(An.$$.fragment),wu=r(),Zd=s("p"),Zd.innerHTML=lL,vu=r(),ao=s("div"),f(In.$$.fragment),$u=r(),Gd=s("p"),Gd.textContent=cL,yu=r(),f(oa.$$.fragment),Mu=r(),ta=s("div"),f(Un.$$.fragment),Tu=r(),qd=s("p"),qd.textContent=fL,Du=r(),ro=s("div"),f(Vn.$$.fragment),Cu=r(),Bd=s("p"),Bd.innerHTML=pL,Su=r(),f(aa.$$.fragment),Wc=r(),f(Wn.$$.fragment),Xc=r(),N=s("div"),f(Xn.$$.fragment),ku=r(),Ed=s("p"),Ed.innerHTML=mL,Ru=r(),ra=s("div"),f(Pn.$$.fragment),Au=r(),Nd=s("p"),Nd.innerHTML=_L,Iu=r(),na=s("div"),f(Fn.$$.fragment),Uu=r(),zd=s("p"),zd.innerHTML=uL,Vu=r(),no=s("div"),f(Jn.$$.fragment),Wu=r(),Yd=s("p"),Yd.textContent=hL,Xu=r(),f(sa.$$.fragment),Pu=r(),ia=s("div"),f(Hn.$$.fragment),Fu=r(),Qd=s("p"),Qd.textContent=gL,Ju=r(),so=s("div"),f(jn.$$.fragment),Hu=r(),Od=s("p"),Od.innerHTML=xL,ju=r(),f(da.$$.fragment),Pc=r(),f(Zn.$$.fragment),Fc=r(),z=s("div"),f(Gn.$$.fragment),Zu=r(),Kd=s("p"),Kd.innerHTML=LL,Gu=r(),la=s("div"),f(qn.$$.fragment),qu=r(),el=s("p"),el.innerHTML=bL,Bu=r(),ca=s("div"),f(Bn.$$.fragment),Eu=r(),ol=s("p"),ol.innerHTML=wL,Nu=r(),io=s("div"),f(En.$$.fragment),zu=r(),tl=s("p"),tl.textContent=vL,Yu=r(),f(fa.$$.fragment),Qu=r(),pa=s("div"),f(Nn.$$.fragment),Ou=r(),al=s("p"),al.textContent=$L,Ku=r(),lo=s("div"),f(zn.$$.fragment),eh=r(),rl=s("p"),rl.innerHTML=yL,oh=r(),f(ma.$$.fragment),Jc=r(),f(Yn.$$.fragment),Hc=r(),Te=s("div"),f(Qn.$$.fragment),th=r(),_a=s("div"),f(On.$$.fragment),ah=r(),nl=s("p"),nl.innerHTML=ML,rh=r(),ua=s("div"),f(Kn.$$.fragment),nh=r(),sl=s("p"),sl.textContent=TL,jc=r(),f(es.$$.fragment),Zc=r(),Y=s("div"),f(os.$$.fragment),sh=r(),il=s("p"),il.innerHTML=DL,ih=r(),ha=s("div"),f(ts.$$.fragment),dh=r(),dl=s("p"),dl.innerHTML=CL,lh=r(),ga=s("div"),f(as.$$.fragment),ch=r(),ll=s("p"),ll.innerHTML=SL,fh=r(),co=s("div"),f(rs.$$.fragment),ph=r(),cl=s("p"),cl.textContent=kL,mh=r(),f(xa.$$.fragment),_h=r(),La=s("div"),f(ns.$$.fragment),uh=r(),fl=s("p"),fl.textContent=RL,hh=r(),fo=s("div"),f(ss.$$.fragment),gh=r(),pl=s("p"),pl.innerHTML=AL,xh=r(),f(ba.$$.fragment),Gc=r(),f(is.$$.fragment),qc=r(),Q=s("div"),f(ds.$$.fragment),Lh=r(),ml=s("p"),ml.innerHTML=IL,bh=r(),wa=s("div"),f(ls.$$.fragment),wh=r(),_l=s("p"),_l.innerHTML=UL,vh=r(),va=s("div"),f(cs.$$.fragment),$h=r(),ul=s("p"),ul.innerHTML=VL,yh=r(),po=s("div"),f(fs.$$.fragment),Mh=r(),hl=s("p"),hl.textContent=WL,Th=r(),f($a.$$.fragment),Dh=r(),ya=s("div"),f(ps.$$.fragment),Ch=r(),gl=s("p"),gl.textContent=XL,Sh=r(),mo=s("div"),f(ms.$$.fragment),kh=r(),xl=s("p"),xl.innerHTML=PL,Rh=r(),f(Ma.$$.fragment),Bc=r(),f(_s.$$.fragment),Ec=r(),k=s("div"),f(us.$$.fragment),Ah=r(),Ll=s("p"),Ll.textContent=FL,Ih=r(),_o=s("div"),f(hs.$$.fragment),Uh=r(),bl=s("p"),bl.textContent=JL,Vh=r(),f(Ta.$$.fragment),Wh=r(),uo=s("div"),f(gs.$$.fragment),Xh=r(),wl=s("p"),wl.textContent=HL,Ph=r(),f(Da.$$.fragment),Fh=r(),ho=s("div"),f(xs.$$.fragment),Jh=r(),vl=s("p"),vl.textContent=jL,Hh=r(),f(Ca.$$.fragment),jh=r(),Sa=s("div"),f(Ls.$$.fragment),Zh=r(),$l=s("p"),$l.textContent=ZL,Gh=r(),ye=s("div"),f(bs.$$.fragment),qh=r(),yl=s("p"),yl.textContent=GL,Bh=r(),f(ka.$$.fragment),Eh=r(),f(Ra.$$.fragment),Nh=r(),go=s("div"),f(ws.$$.fragment),zh=r(),Ml=s("p"),Ml.textContent=qL,Yh=r(),f(Aa.$$.fragment),Qh=r(),Ia=s("div"),f(vs.$$.fragment),Oh=r(),Tl=s("p"),Tl.textContent=BL,Kh=r(),xo=s("div"),f($s.$$.fragment),eg=r(),Dl=s("p"),Dl.textContent=EL,og=r(),f(Ua.$$.fragment),tg=r(),Me=s("div"),f(ys.$$.fragment),ag=r(),Cl=s("p"),Cl.innerHTML=NL,rg=r(),Sl=s("p"),Sl.textContent=zL,ng=r(),f(Va.$$.fragment),sg=r(),Lo=s("div"),f(Ms.$$.fragment),ig=r(),kl=s("p"),kl.innerHTML=YL,dg=r(),f(Wa.$$.fragment),lg=r(),bo=s("div"),f(Ts.$$.fragment),cg=r(),Rl=s("p"),Rl.textContent=QL,fg=r(),f(Xa.$$.fragment),pg=r(),Pa=s("div"),f(Ds.$$.fragment),mg=r(),Al=s("p"),Al.textContent=OL,Nc=r(),f(Cs.$$.fragment),zc=r(),ic=s("p"),this.h()},l(e){const x=ab("svelte-u9bgzb",document.head);t=i(x,"META",{name:!0,content:!0}),x.forEach(d),b=n(e),l=i(e,"P",{}),$(l).forEach(d),c=n(e),p(v.$$.fragment,e),a=n(e),w=i(e,"P",{"data-svelte-h":!0}),g(w)!=="svelte-c39qs9"&&(w.innerHTML=_g),dc=n(e),Ha=i(e,"UL",{"data-svelte-h":!0}),g(Ha)!=="svelte-pqrzex"&&(Ha.innerHTML=ug),lc=n(e),p(Fo.$$.fragment,e),cc=n(e),p(ja.$$.fragment,e),fc=n(e),S=i(e,"DIV",{class:!0});var R=$(S);p(Za.$$.fragment,R),If=n(R),Ys=i(R,"P",{"data-svelte-h":!0}),g(Ys)!=="svelte-1q4bbx"&&(Ys.textContent=hg),Uf=n(R),Se=i(R,"DIV",{class:!0});var wo=$(Se);p(Ga.$$.fragment,wo),Vf=n(wo),Qs=i(wo,"P",{"data-svelte-h":!0}),g(Qs)!=="svelte-197ly1e"&&(Qs.textContent=gg),Wf=n(wo),p(Jo.$$.fragment,wo),wo.forEach(d),Xf=n(R),ke=i(R,"DIV",{class:!0});var vo=$(ke);p(qa.$$.fragment,vo),Pf=n(vo),Os=i(vo,"P",{"data-svelte-h":!0}),g(Os)!=="svelte-1k7sb6g"&&(Os.textContent=xg),Ff=n(vo),p(Ho.$$.fragment,vo),vo.forEach(d),Jf=n(R),Re=i(R,"DIV",{class:!0});var $o=$(Re);p(Ba.$$.fragment,$o),Hf=n($o),Ks=i($o,"P",{"data-svelte-h":!0}),g(Ks)!=="svelte-1270mz9"&&(Ks.textContent=Lg),jf=n($o),p(jo.$$.fragment,$o),$o.forEach(d),Zf=n(R),Zo=i(R,"DIV",{class:!0});var Ss=$(Zo);p(Ea.$$.fragment,Ss),Gf=n(Ss),ei=i(Ss,"P",{"data-svelte-h":!0}),g(ei)!=="svelte-aqzrjr"&&(ei.textContent=bg),Ss.forEach(d),qf=n(R),ve=i(R,"DIV",{class:!0});var De=$(ve);p(Na.$$.fragment,De),Bf=n(De),oi=i(De,"P",{"data-svelte-h":!0}),g(oi)!=="svelte-1nr2dy0"&&(oi.textContent=wg),Ef=n(De),p(Go.$$.fragment,De),Nf=n(De),p(qo.$$.fragment,De),De.forEach(d),zf=n(R),Ae=i(R,"DIV",{class:!0});var yo=$(Ae);p(za.$$.fragment,yo),Yf=n(yo),ti=i(yo,"P",{"data-svelte-h":!0}),g(ti)!=="svelte-h0os0v"&&(ti.textContent=vg),Qf=n(yo),p(Bo.$$.fragment,yo),yo.forEach(d),Of=n(R),Eo=i(R,"DIV",{class:!0});var ks=$(Eo);p(Ya.$$.fragment,ks),Kf=n(ks),ai=i(ks,"P",{"data-svelte-h":!0}),g(ai)!=="svelte-1825k9e"&&(ai.textContent=$g),ks.forEach(d),ep=n(R),Ie=i(R,"DIV",{class:!0});var Mo=$(Ie);p(Qa.$$.fragment,Mo),op=n(Mo),ri=i(Mo,"P",{"data-svelte-h":!0}),g(ri)!=="svelte-1nht1gz"&&(ri.textContent=yg),tp=n(Mo),p(No.$$.fragment,Mo),Mo.forEach(d),ap=n(R),$e=i(R,"DIV",{class:!0});var Ce=$($e);p(Oa.$$.fragment,Ce),rp=n(Ce),ni=i(Ce,"P",{"data-svelte-h":!0}),g(ni)!=="svelte-rvubqa"&&(ni.innerHTML=Mg),np=n(Ce),si=i(Ce,"P",{"data-svelte-h":!0}),g(si)!=="svelte-x8llv0"&&(si.textContent=Tg),sp=n(Ce),p(zo.$$.fragment,Ce),Ce.forEach(d),ip=n(R),Ue=i(R,"DIV",{class:!0});var To=$(Ue);p(Ka.$$.fragment,To),dp=n(To),ii=i(To,"P",{"data-svelte-h":!0}),g(ii)!=="svelte-ioswce"&&(ii.innerHTML=Dg),lp=n(To),p(Yo.$$.fragment,To),To.forEach(d),cp=n(R),Ve=i(R,"DIV",{class:!0});var Do=$(Ve);p(er.$$.fragment,Do),fp=n(Do),di=i(Do,"P",{"data-svelte-h":!0}),g(di)!=="svelte-119cgd9"&&(di.textContent=Cg),pp=n(Do),p(Qo.$$.fragment,Do),Do.forEach(d),mp=n(R),Oo=i(R,"DIV",{class:!0});var Rs=$(Oo);p(or.$$.fragment,Rs),_p=n(Rs),li=i(Rs,"P",{"data-svelte-h":!0}),g(li)!=="svelte-1rtya5j"&&(li.textContent=Sg),Rs.forEach(d),R.forEach(d),pc=n(e),p(tr.$$.fragment,e),mc=n(e),P=i(e,"DIV",{class:!0});var O=$(P);p(ar.$$.fragment,O),up=n(O),ci=i(O,"P",{"data-svelte-h":!0}),g(ci)!=="svelte-1fm4l3u"&&(ci.innerHTML=kg),hp=n(O),Ko=i(O,"DIV",{class:!0});var As=$(Ko);p(rr.$$.fragment,As),gp=n(As),fi=i(As,"P",{"data-svelte-h":!0}),g(fi)!=="svelte-1062ci4"&&(fi.innerHTML=Rg),As.forEach(d),xp=n(O),et=i(O,"DIV",{class:!0});var Is=$(et);p(nr.$$.fragment,Is),Lp=n(Is),pi=i(Is,"P",{"data-svelte-h":!0}),g(pi)!=="svelte-u3q4so"&&(pi.innerHTML=Ag),Is.forEach(d),bp=n(O),re=i(O,"DIV",{class:!0});var se=$(re);p(sr.$$.fragment,se),wp=n(se),mi=i(se,"P",{"data-svelte-h":!0}),g(mi)!=="svelte-vs7s0z"&&(mi.innerHTML=Ig),vp=n(se),_i=i(se,"P",{"data-svelte-h":!0}),g(_i)!=="svelte-15b960v"&&(_i.innerHTML=Ug),$p=n(se),ui=i(se,"P",{"data-svelte-h":!0}),g(ui)!=="svelte-nkp88r"&&(ui.innerHTML=Vg),yp=n(se),hi=i(se,"P",{"data-svelte-h":!0}),g(hi)!=="svelte-r6ah3g"&&(hi.innerHTML=Wg),Mp=n(se),gi=i(se,"P",{"data-svelte-h":!0}),g(gi)!=="svelte-k1somu"&&(gi.innerHTML=Xg),se.forEach(d),Tp=n(O),We=i(O,"DIV",{class:!0});var Co=$(We);p(ir.$$.fragment,Co),Dp=n(Co),xi=i(Co,"P",{"data-svelte-h":!0}),g(xi)!=="svelte-flusvq"&&(xi.textContent=Pg),Cp=n(Co),p(ot.$$.fragment,Co),Co.forEach(d),Sp=n(O),tt=i(O,"DIV",{class:!0});var Us=$(tt);p(dr.$$.fragment,Us),kp=n(Us),Li=i(Us,"P",{"data-svelte-h":!0}),g(Li)!=="svelte-1ufq5ot"&&(Li.textContent=Fg),Us.forEach(d),O.forEach(d),_c=n(e),p(lr.$$.fragment,e),uc=n(e),F=i(e,"DIV",{class:!0});var K=$(F);p(cr.$$.fragment,K),Rp=n(K),bi=i(K,"P",{"data-svelte-h":!0}),g(bi)!=="svelte-zi7tsv"&&(bi.innerHTML=Jg),Ap=n(K),at=i(K,"DIV",{class:!0});var Vs=$(at);p(fr.$$.fragment,Vs),Ip=n(Vs),wi=i(Vs,"P",{"data-svelte-h":!0}),g(wi)!=="svelte-1062ci4"&&(wi.innerHTML=Hg),Vs.forEach(d),Up=n(K),rt=i(K,"DIV",{class:!0});var Ws=$(rt);p(pr.$$.fragment,Ws),Vp=n(Ws),vi=i(Ws,"P",{"data-svelte-h":!0}),g(vi)!=="svelte-u3q4so"&&(vi.innerHTML=jg),Ws.forEach(d),Wp=n(K),ne=i(K,"DIV",{class:!0});var ie=$(ne);p(mr.$$.fragment,ie),Xp=n(ie),$i=i(ie,"P",{"data-svelte-h":!0}),g($i)!=="svelte-vs7s0z"&&($i.innerHTML=Zg),Pp=n(ie),yi=i(ie,"P",{"data-svelte-h":!0}),g(yi)!=="svelte-15b960v"&&(yi.innerHTML=Gg),Fp=n(ie),Mi=i(ie,"P",{"data-svelte-h":!0}),g(Mi)!=="svelte-nkp88r"&&(Mi.innerHTML=qg),Jp=n(ie),Ti=i(ie,"P",{"data-svelte-h":!0}),g(Ti)!=="svelte-r6ah3g"&&(Ti.innerHTML=Bg),Hp=n(ie),Di=i(ie,"P",{"data-svelte-h":!0}),g(Di)!=="svelte-k1somu"&&(Di.innerHTML=Eg),ie.forEach(d),jp=n(K),Xe=i(K,"DIV",{class:!0});var So=$(Xe);p(_r.$$.fragment,So),Zp=n(So),Ci=i(So,"P",{"data-svelte-h":!0}),g(Ci)!=="svelte-flusvq"&&(Ci.textContent=Ng),Gp=n(So),p(nt.$$.fragment,So),So.forEach(d),qp=n(K),st=i(K,"DIV",{class:!0});var Xs=$(st);p(ur.$$.fragment,Xs),Bp=n(Xs),Si=i(Xs,"P",{"data-svelte-h":!0}),g(Si)!=="svelte-1ufq5ot"&&(Si.textContent=zg),Xs.forEach(d),K.forEach(d),hc=n(e),p(hr.$$.fragment,e),gc=n(e),U=i(e,"DIV",{class:!0});var W=$(U);p(gr.$$.fragment,W),Ep=n(W),ki=i(W,"P",{"data-svelte-h":!0}),g(ki)!=="svelte-1qegdq"&&(ki.innerHTML=Yg),Np=n(W),Ri=i(W,"P",{"data-svelte-h":!0}),g(Ri)!=="svelte-m22mzw"&&(Ri.innerHTML=Qg),zp=n(W),it=i(W,"DIV",{class:!0});var Ps=$(it);p(xr.$$.fragment,Ps),Yp=n(Ps),Ai=i(Ps,"P",{"data-svelte-h":!0}),g(Ai)!=="svelte-1062ci4"&&(Ai.innerHTML=Og),Ps.forEach(d),Qp=n(W),dt=i(W,"DIV",{class:!0});var Fs=$(dt);p(Lr.$$.fragment,Fs),Op=n(Fs),Ii=i(Fs,"P",{"data-svelte-h":!0}),g(Ii)!=="svelte-1lgbsz7"&&(Ii.innerHTML=Kg),Fs.forEach(d),Kp=n(W),de=i(W,"DIV",{class:!0});var be=$(de);p(br.$$.fragment,be),em=n(be),Ui=i(be,"P",{"data-svelte-h":!0}),g(Ui)!=="svelte-vs7s0z"&&(Ui.innerHTML=ex),om=n(be),Vi=i(be,"P",{"data-svelte-h":!0}),g(Vi)!=="svelte-15b960v"&&(Vi.innerHTML=ox),tm=n(be),Wi=i(be,"P",{"data-svelte-h":!0}),g(Wi)!=="svelte-nkp88r"&&(Wi.innerHTML=tx),am=n(be),Xi=i(be,"P",{"data-svelte-h":!0}),g(Xi)!=="svelte-1ukghd4"&&(Xi.innerHTML=ax),be.forEach(d),rm=n(W),Pe=i(W,"DIV",{class:!0});var ko=$(Pe);p(wr.$$.fragment,ko),nm=n(ko),Pi=i(ko,"P",{"data-svelte-h":!0}),g(Pi)!=="svelte-flusvq"&&(Pi.textContent=rx),sm=n(ko),p(lt.$$.fragment,ko),ko.forEach(d),im=n(W),ct=i(W,"DIV",{class:!0});var Js=$(ct);p(vr.$$.fragment,Js),dm=n(Js),Fi=i(Js,"P",{"data-svelte-h":!0}),g(Fi)!=="svelte-1ufq5ot"&&(Fi.textContent=nx),Js.forEach(d),lm=n(W),Fe=i(W,"DIV",{class:!0});var Ro=$(Fe);p($r.$$.fragment,Ro),cm=n(Ro),Ji=i(Ro,"P",{"data-svelte-h":!0}),g(Ji)!=="svelte-ioswce"&&(Ji.innerHTML=sx),fm=n(Ro),p(ft.$$.fragment,Ro),Ro.forEach(d),W.forEach(d),xc=n(e),p(yr.$$.fragment,e),Lc=n(e),I=i(e,"DIV",{class:!0});var V=$(I);p(Mr.$$.fragment,V),pm=n(V),Hi=i(V,"P",{"data-svelte-h":!0}),g(Hi)!=="svelte-8779wv"&&(Hi.innerHTML=ix),mm=n(V),ji=i(V,"P",{"data-svelte-h":!0}),g(ji)!=="svelte-m22mzw"&&(ji.innerHTML=dx),_m=n(V),pt=i(V,"DIV",{class:!0});var Hs=$(pt);p(Tr.$$.fragment,Hs),um=n(Hs),Zi=i(Hs,"P",{"data-svelte-h":!0}),g(Zi)!=="svelte-1062ci4"&&(Zi.innerHTML=lx),Hs.forEach(d),hm=n(V),mt=i(V,"DIV",{class:!0});var js=$(mt);p(Dr.$$.fragment,js),gm=n(js),Gi=i(js,"P",{"data-svelte-h":!0}),g(Gi)!=="svelte-1lgbsz7"&&(Gi.innerHTML=cx),js.forEach(d),xm=n(V),le=i(V,"DIV",{class:!0});var we=$(le);p(Cr.$$.fragment,we),Lm=n(we),qi=i(we,"P",{"data-svelte-h":!0}),g(qi)!=="svelte-178gcly"&&(qi.innerHTML=fx),bm=n(we),Bi=i(we,"P",{"data-svelte-h":!0}),g(Bi)!=="svelte-15b960v"&&(Bi.innerHTML=px),wm=n(we),Ei=i(we,"P",{"data-svelte-h":!0}),g(Ei)!=="svelte-nkp88r"&&(Ei.innerHTML=mx),vm=n(we),Ni=i(we,"P",{"data-svelte-h":!0}),g(Ni)!=="svelte-1ukghd4"&&(Ni.innerHTML=_x),we.forEach(d),$m=n(V),Je=i(V,"DIV",{class:!0});var Ao=$(Je);p(Sr.$$.fragment,Ao),ym=n(Ao),zi=i(Ao,"P",{"data-svelte-h":!0}),g(zi)!=="svelte-flusvq"&&(zi.textContent=ux),Mm=n(Ao),p(_t.$$.fragment,Ao),Ao.forEach(d),Tm=n(V),ut=i(V,"DIV",{class:!0});var Zs=$(ut);p(kr.$$.fragment,Zs),Dm=n(Zs),Yi=i(Zs,"P",{"data-svelte-h":!0}),g(Yi)!=="svelte-1ufq5ot"&&(Yi.textContent=hx),Zs.forEach(d),Cm=n(V),He=i(V,"DIV",{class:!0});var Io=$(He);p(Rr.$$.fragment,Io),Sm=n(Io),Qi=i(Io,"P",{"data-svelte-h":!0}),g(Qi)!=="svelte-ioswce"&&(Qi.innerHTML=gx),km=n(Io),p(ht.$$.fragment,Io),Io.forEach(d),Rm=n(V),je=i(V,"DIV",{class:!0});var Uo=$(je);p(Ar.$$.fragment,Uo),Am=n(Uo),Oi=i(Uo,"P",{"data-svelte-h":!0}),g(Oi)!=="svelte-119cgd9"&&(Oi.textContent=xx),Im=n(Uo),p(gt.$$.fragment,Uo),Uo.forEach(d),V.forEach(d),bc=n(e),p(Ir.$$.fragment,e),wc=n(e),J=i(e,"DIV",{class:!0});var ee=$(J);p(Ur.$$.fragment,ee),Um=n(ee),Ki=i(ee,"P",{"data-svelte-h":!0}),g(Ki)!=="svelte-140eopd"&&(Ki.innerHTML=Lx),Vm=n(ee),xt=i(ee,"DIV",{class:!0});var Gs=$(xt);p(Vr.$$.fragment,Gs),Wm=n(Gs),ed=i(Gs,"P",{"data-svelte-h":!0}),g(ed)!=="svelte-1lgbsz7"&&(ed.innerHTML=bx),Gs.forEach(d),Xm=n(ee),Lt=i(ee,"DIV",{class:!0});var qs=$(Lt);p(Wr.$$.fragment,qs),Pm=n(qs),od=i(qs,"P",{"data-svelte-h":!0}),g(od)!=="svelte-1podb0u"&&(od.innerHTML=wx),qs.forEach(d),Fm=n(ee),Ze=i(ee,"DIV",{class:!0});var Vo=$(Ze);p(Xr.$$.fragment,Vo),Jm=n(Vo),td=i(Vo,"P",{"data-svelte-h":!0}),g(td)!=="svelte-flusvq"&&(td.textContent=vx),Hm=n(Vo),p(bt.$$.fragment,Vo),Vo.forEach(d),jm=n(ee),wt=i(ee,"DIV",{class:!0});var Bs=$(wt);p(Pr.$$.fragment,Bs),Zm=n(Bs),ad=i(Bs,"P",{"data-svelte-h":!0}),g(ad)!=="svelte-1gl6t2c"&&(ad.textContent=$x),Bs.forEach(d),Gm=n(ee),Ge=i(ee,"DIV",{class:!0});var Wo=$(Ge);p(Fr.$$.fragment,Wo),qm=n(Wo),rd=i(Wo,"P",{"data-svelte-h":!0}),g(rd)!=="svelte-ioswce"&&(rd.innerHTML=yx),Bm=n(Wo),p(vt.$$.fragment,Wo),Wo.forEach(d),ee.forEach(d),vc=n(e),p(Jr.$$.fragment,e),$c=n(e),H=i(e,"DIV",{class:!0});var oe=$(H);p(Hr.$$.fragment,oe),Em=n(oe),nd=i(oe,"P",{"data-svelte-h":!0}),g(nd)!=="svelte-4tm3fl"&&(nd.innerHTML=Mx),Nm=n(oe),$t=i(oe,"DIV",{class:!0});var Es=$($t);p(jr.$$.fragment,Es),zm=n(Es),sd=i(Es,"P",{"data-svelte-h":!0}),g(sd)!=="svelte-1lgbsz7"&&(sd.innerHTML=Tx),Es.forEach(d),Ym=n(oe),yt=i(oe,"DIV",{class:!0});var Ns=$(yt);p(Zr.$$.fragment,Ns),Qm=n(Ns),id=i(Ns,"P",{"data-svelte-h":!0}),g(id)!=="svelte-1podb0u"&&(id.innerHTML=Dx),Ns.forEach(d),Om=n(oe),qe=i(oe,"DIV",{class:!0});var Xo=$(qe);p(Gr.$$.fragment,Xo),Km=n(Xo),dd=i(Xo,"P",{"data-svelte-h":!0}),g(dd)!=="svelte-flusvq"&&(dd.textContent=Cx),e_=n(Xo),p(Mt.$$.fragment,Xo),Xo.forEach(d),o_=n(oe),Tt=i(oe,"DIV",{class:!0});var zs=$(Tt);p(qr.$$.fragment,zs),t_=n(zs),ld=i(zs,"P",{"data-svelte-h":!0}),g(ld)!=="svelte-1gl6t2c"&&(ld.textContent=Sx),zs.forEach(d),a_=n(oe),Be=i(oe,"DIV",{class:!0});var Po=$(Be);p(Br.$$.fragment,Po),r_=n(Po),cd=i(Po,"P",{"data-svelte-h":!0}),g(cd)!=="svelte-ioswce"&&(cd.innerHTML=kx),n_=n(Po),p(Dt.$$.fragment,Po),Po.forEach(d),oe.forEach(d),yc=n(e),p(Er.$$.fragment,e),Mc=n(e),j=i(e,"DIV",{class:!0});var ce=$(j);p(Nr.$$.fragment,ce),s_=n(ce),fd=i(ce,"P",{"data-svelte-h":!0}),g(fd)!=="svelte-ewe6bw"&&(fd.innerHTML=Rx),i_=n(ce),Ct=i(ce,"DIV",{class:!0});var Qc=$(Ct);p(zr.$$.fragment,Qc),d_=n(Qc),pd=i(Qc,"P",{"data-svelte-h":!0}),g(pd)!=="svelte-1lgbsz7"&&(pd.innerHTML=Ax),Qc.forEach(d),l_=n(ce),St=i(ce,"DIV",{class:!0});var Oc=$(St);p(Yr.$$.fragment,Oc),c_=n(Oc),md=i(Oc,"P",{"data-svelte-h":!0}),g(md)!=="svelte-1podb0u"&&(md.innerHTML=Ix),Oc.forEach(d),f_=n(ce),Ee=i(ce,"DIV",{class:!0});var Il=$(Ee);p(Qr.$$.fragment,Il),p_=n(Il),_d=i(Il,"P",{"data-svelte-h":!0}),g(_d)!=="svelte-flusvq"&&(_d.textContent=Ux),m_=n(Il),p(kt.$$.fragment,Il),Il.forEach(d),__=n(ce),Rt=i(ce,"DIV",{class:!0});var Kc=$(Rt);p(Or.$$.fragment,Kc),u_=n(Kc),ud=i(Kc,"P",{"data-svelte-h":!0}),g(ud)!=="svelte-1gl6t2c"&&(ud.textContent=Vx),Kc.forEach(d),h_=n(ce),Ne=i(ce,"DIV",{class:!0});var Ul=$(Ne);p(Kr.$$.fragment,Ul),g_=n(Ul),hd=i(Ul,"P",{"data-svelte-h":!0}),g(hd)!=="svelte-ioswce"&&(hd.innerHTML=Wx),x_=n(Ul),p(At.$$.fragment,Ul),Ul.forEach(d),ce.forEach(d),Tc=n(e),p(en.$$.fragment,e),Dc=n(e),Z=i(e,"DIV",{class:!0});var fe=$(Z);p(on.$$.fragment,fe),L_=n(fe),gd=i(fe,"P",{"data-svelte-h":!0}),g(gd)!=="svelte-149rafp"&&(gd.innerHTML=Xx),b_=n(fe),It=i(fe,"DIV",{class:!0});var ef=$(It);p(tn.$$.fragment,ef),w_=n(ef),xd=i(ef,"P",{"data-svelte-h":!0}),g(xd)!=="svelte-1lgbsz7"&&(xd.innerHTML=Px),ef.forEach(d),v_=n(fe),Ut=i(fe,"DIV",{class:!0});var of=$(Ut);p(an.$$.fragment,of),$_=n(of),Ld=i(of,"P",{"data-svelte-h":!0}),g(Ld)!=="svelte-1podb0u"&&(Ld.innerHTML=Fx),of.forEach(d),y_=n(fe),ze=i(fe,"DIV",{class:!0});var Vl=$(ze);p(rn.$$.fragment,Vl),M_=n(Vl),bd=i(Vl,"P",{"data-svelte-h":!0}),g(bd)!=="svelte-flusvq"&&(bd.textContent=Jx),T_=n(Vl),p(Vt.$$.fragment,Vl),Vl.forEach(d),D_=n(fe),Wt=i(fe,"DIV",{class:!0});var tf=$(Wt);p(nn.$$.fragment,tf),C_=n(tf),wd=i(tf,"P",{"data-svelte-h":!0}),g(wd)!=="svelte-1gl6t2c"&&(wd.textContent=Hx),tf.forEach(d),S_=n(fe),Ye=i(fe,"DIV",{class:!0});var Wl=$(Ye);p(sn.$$.fragment,Wl),k_=n(Wl),vd=i(Wl,"P",{"data-svelte-h":!0}),g(vd)!=="svelte-ioswce"&&(vd.innerHTML=jx),R_=n(Wl),p(Xt.$$.fragment,Wl),Wl.forEach(d),fe.forEach(d),Cc=n(e),p(dn.$$.fragment,e),Sc=n(e),G=i(e,"DIV",{class:!0});var pe=$(G);p(ln.$$.fragment,pe),A_=n(pe),$d=i(pe,"P",{"data-svelte-h":!0}),g($d)!=="svelte-1783gxs"&&($d.innerHTML=Zx),I_=n(pe),Pt=i(pe,"DIV",{class:!0});var af=$(Pt);p(cn.$$.fragment,af),U_=n(af),yd=i(af,"P",{"data-svelte-h":!0}),g(yd)!=="svelte-1lgbsz7"&&(yd.innerHTML=Gx),af.forEach(d),V_=n(pe),Ft=i(pe,"DIV",{class:!0});var rf=$(Ft);p(fn.$$.fragment,rf),W_=n(rf),Md=i(rf,"P",{"data-svelte-h":!0}),g(Md)!=="svelte-1podb0u"&&(Md.innerHTML=qx),rf.forEach(d),X_=n(pe),Qe=i(pe,"DIV",{class:!0});var Xl=$(Qe);p(pn.$$.fragment,Xl),P_=n(Xl),Td=i(Xl,"P",{"data-svelte-h":!0}),g(Td)!=="svelte-flusvq"&&(Td.textContent=Bx),F_=n(Xl),p(Jt.$$.fragment,Xl),Xl.forEach(d),J_=n(pe),Ht=i(pe,"DIV",{class:!0});var nf=$(Ht);p(mn.$$.fragment,nf),H_=n(nf),Dd=i(nf,"P",{"data-svelte-h":!0}),g(Dd)!=="svelte-1gl6t2c"&&(Dd.textContent=Ex),nf.forEach(d),j_=n(pe),Oe=i(pe,"DIV",{class:!0});var Pl=$(Oe);p(_n.$$.fragment,Pl),Z_=n(Pl),Cd=i(Pl,"P",{"data-svelte-h":!0}),g(Cd)!=="svelte-ioswce"&&(Cd.innerHTML=Nx),G_=n(Pl),p(jt.$$.fragment,Pl),Pl.forEach(d),pe.forEach(d),kc=n(e),p(un.$$.fragment,e),Rc=n(e),q=i(e,"DIV",{class:!0});var me=$(q);p(hn.$$.fragment,me),q_=n(me),Sd=i(me,"P",{"data-svelte-h":!0}),g(Sd)!=="svelte-jermnw"&&(Sd.innerHTML=zx),B_=n(me),Zt=i(me,"DIV",{class:!0});var sf=$(Zt);p(gn.$$.fragment,sf),E_=n(sf),kd=i(sf,"P",{"data-svelte-h":!0}),g(kd)!=="svelte-1lgbsz7"&&(kd.innerHTML=Yx),sf.forEach(d),N_=n(me),Gt=i(me,"DIV",{class:!0});var df=$(Gt);p(xn.$$.fragment,df),z_=n(df),Rd=i(df,"P",{"data-svelte-h":!0}),g(Rd)!=="svelte-1podb0u"&&(Rd.innerHTML=Qx),df.forEach(d),Y_=n(me),Ke=i(me,"DIV",{class:!0});var Fl=$(Ke);p(Ln.$$.fragment,Fl),Q_=n(Fl),Ad=i(Fl,"P",{"data-svelte-h":!0}),g(Ad)!=="svelte-flusvq"&&(Ad.textContent=Ox),O_=n(Fl),p(qt.$$.fragment,Fl),Fl.forEach(d),K_=n(me),Bt=i(me,"DIV",{class:!0});var lf=$(Bt);p(bn.$$.fragment,lf),eu=n(lf),Id=i(lf,"P",{"data-svelte-h":!0}),g(Id)!=="svelte-1gl6t2c"&&(Id.textContent=Kx),lf.forEach(d),ou=n(me),eo=i(me,"DIV",{class:!0});var Jl=$(eo);p(wn.$$.fragment,Jl),tu=n(Jl),Ud=i(Jl,"P",{"data-svelte-h":!0}),g(Ud)!=="svelte-ioswce"&&(Ud.innerHTML=eL),au=n(Jl),p(Et.$$.fragment,Jl),Jl.forEach(d),me.forEach(d),Ac=n(e),p(vn.$$.fragment,e),Ic=n(e),B=i(e,"DIV",{class:!0});var _e=$(B);p($n.$$.fragment,_e),ru=n(_e),Vd=i(_e,"P",{"data-svelte-h":!0}),g(Vd)!=="svelte-1gpc1wh"&&(Vd.innerHTML=oL),nu=n(_e),Nt=i(_e,"DIV",{class:!0});var cf=$(Nt);p(yn.$$.fragment,cf),su=n(cf),Wd=i(cf,"P",{"data-svelte-h":!0}),g(Wd)!=="svelte-1lgbsz7"&&(Wd.innerHTML=tL),cf.forEach(d),iu=n(_e),zt=i(_e,"DIV",{class:!0});var ff=$(zt);p(Mn.$$.fragment,ff),du=n(ff),Xd=i(ff,"P",{"data-svelte-h":!0}),g(Xd)!=="svelte-1podb0u"&&(Xd.innerHTML=aL),ff.forEach(d),lu=n(_e),oo=i(_e,"DIV",{class:!0});var Hl=$(oo);p(Tn.$$.fragment,Hl),cu=n(Hl),Pd=i(Hl,"P",{"data-svelte-h":!0}),g(Pd)!=="svelte-flusvq"&&(Pd.textContent=rL),fu=n(Hl),p(Yt.$$.fragment,Hl),Hl.forEach(d),pu=n(_e),Qt=i(_e,"DIV",{class:!0});var pf=$(Qt);p(Dn.$$.fragment,pf),mu=n(pf),Fd=i(pf,"P",{"data-svelte-h":!0}),g(Fd)!=="svelte-1gl6t2c"&&(Fd.textContent=nL),pf.forEach(d),_u=n(_e),to=i(_e,"DIV",{class:!0});var jl=$(to);p(Cn.$$.fragment,jl),uu=n(jl),Jd=i(jl,"P",{"data-svelte-h":!0}),g(Jd)!=="svelte-ioswce"&&(Jd.innerHTML=sL),hu=n(jl),p(Ot.$$.fragment,jl),jl.forEach(d),_e.forEach(d),Uc=n(e),p(Sn.$$.fragment,e),Vc=n(e),E=i(e,"DIV",{class:!0});var ue=$(E);p(kn.$$.fragment,ue),gu=n(ue),Hd=i(ue,"P",{"data-svelte-h":!0}),g(Hd)!=="svelte-18qe22e"&&(Hd.innerHTML=iL),xu=n(ue),Kt=i(ue,"DIV",{class:!0});var mf=$(Kt);p(Rn.$$.fragment,mf),Lu=n(mf),jd=i(mf,"P",{"data-svelte-h":!0}),g(jd)!=="svelte-1lgbsz7"&&(jd.innerHTML=dL),mf.forEach(d),bu=n(ue),ea=i(ue,"DIV",{class:!0});var _f=$(ea);p(An.$$.fragment,_f),wu=n(_f),Zd=i(_f,"P",{"data-svelte-h":!0}),g(Zd)!=="svelte-1podb0u"&&(Zd.innerHTML=lL),_f.forEach(d),vu=n(ue),ao=i(ue,"DIV",{class:!0});var Zl=$(ao);p(In.$$.fragment,Zl),$u=n(Zl),Gd=i(Zl,"P",{"data-svelte-h":!0}),g(Gd)!=="svelte-flusvq"&&(Gd.textContent=cL),yu=n(Zl),p(oa.$$.fragment,Zl),Zl.forEach(d),Mu=n(ue),ta=i(ue,"DIV",{class:!0});var uf=$(ta);p(Un.$$.fragment,uf),Tu=n(uf),qd=i(uf,"P",{"data-svelte-h":!0}),g(qd)!=="svelte-1gl6t2c"&&(qd.textContent=fL),uf.forEach(d),Du=n(ue),ro=i(ue,"DIV",{class:!0});var Gl=$(ro);p(Vn.$$.fragment,Gl),Cu=n(Gl),Bd=i(Gl,"P",{"data-svelte-h":!0}),g(Bd)!=="svelte-ioswce"&&(Bd.innerHTML=pL),Su=n(Gl),p(aa.$$.fragment,Gl),Gl.forEach(d),ue.forEach(d),Wc=n(e),p(Wn.$$.fragment,e),Xc=n(e),N=i(e,"DIV",{class:!0});var he=$(N);p(Xn.$$.fragment,he),ku=n(he),Ed=i(he,"P",{"data-svelte-h":!0}),g(Ed)!=="svelte-1m7e2sd"&&(Ed.innerHTML=mL),Ru=n(he),ra=i(he,"DIV",{class:!0});var hf=$(ra);p(Pn.$$.fragment,hf),Au=n(hf),Nd=i(hf,"P",{"data-svelte-h":!0}),g(Nd)!=="svelte-1lgbsz7"&&(Nd.innerHTML=_L),hf.forEach(d),Iu=n(he),na=i(he,"DIV",{class:!0});var gf=$(na);p(Fn.$$.fragment,gf),Uu=n(gf),zd=i(gf,"P",{"data-svelte-h":!0}),g(zd)!=="svelte-1podb0u"&&(zd.innerHTML=uL),gf.forEach(d),Vu=n(he),no=i(he,"DIV",{class:!0});var ql=$(no);p(Jn.$$.fragment,ql),Wu=n(ql),Yd=i(ql,"P",{"data-svelte-h":!0}),g(Yd)!=="svelte-flusvq"&&(Yd.textContent=hL),Xu=n(ql),p(sa.$$.fragment,ql),ql.forEach(d),Pu=n(he),ia=i(he,"DIV",{class:!0});var xf=$(ia);p(Hn.$$.fragment,xf),Fu=n(xf),Qd=i(xf,"P",{"data-svelte-h":!0}),g(Qd)!=="svelte-1gl6t2c"&&(Qd.textContent=gL),xf.forEach(d),Ju=n(he),so=i(he,"DIV",{class:!0});var Bl=$(so);p(jn.$$.fragment,Bl),Hu=n(Bl),Od=i(Bl,"P",{"data-svelte-h":!0}),g(Od)!=="svelte-ioswce"&&(Od.innerHTML=xL),ju=n(Bl),p(da.$$.fragment,Bl),Bl.forEach(d),he.forEach(d),Pc=n(e),p(Zn.$$.fragment,e),Fc=n(e),z=i(e,"DIV",{class:!0});var ge=$(z);p(Gn.$$.fragment,ge),Zu=n(ge),Kd=i(ge,"P",{"data-svelte-h":!0}),g(Kd)!=="svelte-q86rvu"&&(Kd.innerHTML=LL),Gu=n(ge),la=i(ge,"DIV",{class:!0});var Lf=$(la);p(qn.$$.fragment,Lf),qu=n(Lf),el=i(Lf,"P",{"data-svelte-h":!0}),g(el)!=="svelte-1lgbsz7"&&(el.innerHTML=bL),Lf.forEach(d),Bu=n(ge),ca=i(ge,"DIV",{class:!0});var bf=$(ca);p(Bn.$$.fragment,bf),Eu=n(bf),ol=i(bf,"P",{"data-svelte-h":!0}),g(ol)!=="svelte-1podb0u"&&(ol.innerHTML=wL),bf.forEach(d),Nu=n(ge),io=i(ge,"DIV",{class:!0});var El=$(io);p(En.$$.fragment,El),zu=n(El),tl=i(El,"P",{"data-svelte-h":!0}),g(tl)!=="svelte-flusvq"&&(tl.textContent=vL),Yu=n(El),p(fa.$$.fragment,El),El.forEach(d),Qu=n(ge),pa=i(ge,"DIV",{class:!0});var wf=$(pa);p(Nn.$$.fragment,wf),Ou=n(wf),al=i(wf,"P",{"data-svelte-h":!0}),g(al)!=="svelte-1gl6t2c"&&(al.textContent=$L),wf.forEach(d),Ku=n(ge),lo=i(ge,"DIV",{class:!0});var Nl=$(lo);p(zn.$$.fragment,Nl),eh=n(Nl),rl=i(Nl,"P",{"data-svelte-h":!0}),g(rl)!=="svelte-ioswce"&&(rl.innerHTML=yL),oh=n(Nl),p(ma.$$.fragment,Nl),Nl.forEach(d),ge.forEach(d),Jc=n(e),p(Yn.$$.fragment,e),Hc=n(e),Te=i(e,"DIV",{class:!0});var zl=$(Te);p(Qn.$$.fragment,zl),th=n(zl),_a=i(zl,"DIV",{class:!0});var vf=$(_a);p(On.$$.fragment,vf),ah=n(vf),nl=i(vf,"P",{"data-svelte-h":!0}),g(nl)!=="svelte-1lgbsz7"&&(nl.innerHTML=ML),vf.forEach(d),rh=n(zl),ua=i(zl,"DIV",{class:!0});var $f=$(ua);p(Kn.$$.fragment,$f),nh=n($f),sl=i($f,"P",{"data-svelte-h":!0}),g(sl)!=="svelte-1ufq5ot"&&(sl.textContent=TL),$f.forEach(d),zl.forEach(d),jc=n(e),p(es.$$.fragment,e),Zc=n(e),Y=i(e,"DIV",{class:!0});var xe=$(Y);p(os.$$.fragment,xe),sh=n(xe),il=i(xe,"P",{"data-svelte-h":!0}),g(il)!=="svelte-z57aok"&&(il.innerHTML=DL),ih=n(xe),ha=i(xe,"DIV",{class:!0});var yf=$(ha);p(ts.$$.fragment,yf),dh=n(yf),dl=i(yf,"P",{"data-svelte-h":!0}),g(dl)!=="svelte-1lgbsz7"&&(dl.innerHTML=CL),yf.forEach(d),lh=n(xe),ga=i(xe,"DIV",{class:!0});var Mf=$(ga);p(as.$$.fragment,Mf),ch=n(Mf),ll=i(Mf,"P",{"data-svelte-h":!0}),g(ll)!=="svelte-1podb0u"&&(ll.innerHTML=SL),Mf.forEach(d),fh=n(xe),co=i(xe,"DIV",{class:!0});var Yl=$(co);p(rs.$$.fragment,Yl),ph=n(Yl),cl=i(Yl,"P",{"data-svelte-h":!0}),g(cl)!=="svelte-flusvq"&&(cl.textContent=kL),mh=n(Yl),p(xa.$$.fragment,Yl),Yl.forEach(d),_h=n(xe),La=i(xe,"DIV",{class:!0});var Tf=$(La);p(ns.$$.fragment,Tf),uh=n(Tf),fl=i(Tf,"P",{"data-svelte-h":!0}),g(fl)!=="svelte-1gl6t2c"&&(fl.textContent=RL),Tf.forEach(d),hh=n(xe),fo=i(xe,"DIV",{class:!0});var Ql=$(fo);p(ss.$$.fragment,Ql),gh=n(Ql),pl=i(Ql,"P",{"data-svelte-h":!0}),g(pl)!=="svelte-ioswce"&&(pl.innerHTML=AL),xh=n(Ql),p(ba.$$.fragment,Ql),Ql.forEach(d),xe.forEach(d),Gc=n(e),p(is.$$.fragment,e),qc=n(e),Q=i(e,"DIV",{class:!0});var Le=$(Q);p(ds.$$.fragment,Le),Lh=n(Le),ml=i(Le,"P",{"data-svelte-h":!0}),g(ml)!=="svelte-13694p0"&&(ml.innerHTML=IL),bh=n(Le),wa=i(Le,"DIV",{class:!0});var Df=$(wa);p(ls.$$.fragment,Df),wh=n(Df),_l=i(Df,"P",{"data-svelte-h":!0}),g(_l)!=="svelte-1lgbsz7"&&(_l.innerHTML=UL),Df.forEach(d),vh=n(Le),va=i(Le,"DIV",{class:!0});var Cf=$(va);p(cs.$$.fragment,Cf),$h=n(Cf),ul=i(Cf,"P",{"data-svelte-h":!0}),g(ul)!=="svelte-1podb0u"&&(ul.innerHTML=VL),Cf.forEach(d),yh=n(Le),po=i(Le,"DIV",{class:!0});var Ol=$(po);p(fs.$$.fragment,Ol),Mh=n(Ol),hl=i(Ol,"P",{"data-svelte-h":!0}),g(hl)!=="svelte-flusvq"&&(hl.textContent=WL),Th=n(Ol),p($a.$$.fragment,Ol),Ol.forEach(d),Dh=n(Le),ya=i(Le,"DIV",{class:!0});var Sf=$(ya);p(ps.$$.fragment,Sf),Ch=n(Sf),gl=i(Sf,"P",{"data-svelte-h":!0}),g(gl)!=="svelte-1gl6t2c"&&(gl.textContent=XL),Sf.forEach(d),Sh=n(Le),mo=i(Le,"DIV",{class:!0});var Kl=$(mo);p(ms.$$.fragment,Kl),kh=n(Kl),xl=i(Kl,"P",{"data-svelte-h":!0}),g(xl)!=="svelte-ioswce"&&(xl.innerHTML=PL),Rh=n(Kl),p(Ma.$$.fragment,Kl),Kl.forEach(d),Le.forEach(d),Bc=n(e),p(_s.$$.fragment,e),Ec=n(e),k=i(e,"DIV",{class:!0});var A=$(k);p(us.$$.fragment,A),Ah=n(A),Ll=i(A,"P",{"data-svelte-h":!0}),g(Ll)!=="svelte-1q4bbx"&&(Ll.textContent=FL),Ih=n(A),_o=i(A,"DIV",{class:!0});var ec=$(_o);p(hs.$$.fragment,ec),Uh=n(ec),bl=i(ec,"P",{"data-svelte-h":!0}),g(bl)!=="svelte-197ly1e"&&(bl.textContent=JL),Vh=n(ec),p(Ta.$$.fragment,ec),ec.forEach(d),Wh=n(A),uo=i(A,"DIV",{class:!0});var oc=$(uo);p(gs.$$.fragment,oc),Xh=n(oc),wl=i(oc,"P",{"data-svelte-h":!0}),g(wl)!=="svelte-1k7sb6g"&&(wl.textContent=HL),Ph=n(oc),p(Da.$$.fragment,oc),oc.forEach(d),Fh=n(A),ho=i(A,"DIV",{class:!0});var tc=$(ho);p(xs.$$.fragment,tc),Jh=n(tc),vl=i(tc,"P",{"data-svelte-h":!0}),g(vl)!=="svelte-1270mz9"&&(vl.textContent=jL),Hh=n(tc),p(Ca.$$.fragment,tc),tc.forEach(d),jh=n(A),Sa=i(A,"DIV",{class:!0});var kf=$(Sa);p(Ls.$$.fragment,kf),Zh=n(kf),$l=i(kf,"P",{"data-svelte-h":!0}),g($l)!=="svelte-aqzrjr"&&($l.textContent=ZL),kf.forEach(d),Gh=n(A),ye=i(A,"DIV",{class:!0});var Fa=$(ye);p(bs.$$.fragment,Fa),qh=n(Fa),yl=i(Fa,"P",{"data-svelte-h":!0}),g(yl)!=="svelte-1nr2dy0"&&(yl.textContent=GL),Bh=n(Fa),p(ka.$$.fragment,Fa),Eh=n(Fa),p(Ra.$$.fragment,Fa),Fa.forEach(d),Nh=n(A),go=i(A,"DIV",{class:!0});var ac=$(go);p(ws.$$.fragment,ac),zh=n(ac),Ml=i(ac,"P",{"data-svelte-h":!0}),g(Ml)!=="svelte-h0os0v"&&(Ml.textContent=qL),Yh=n(ac),p(Aa.$$.fragment,ac),ac.forEach(d),Qh=n(A),Ia=i(A,"DIV",{class:!0});var Rf=$(Ia);p(vs.$$.fragment,Rf),Oh=n(Rf),Tl=i(Rf,"P",{"data-svelte-h":!0}),g(Tl)!=="svelte-1825k9e"&&(Tl.textContent=BL),Rf.forEach(d),Kh=n(A),xo=i(A,"DIV",{class:!0});var rc=$(xo);p($s.$$.fragment,rc),eg=n(rc),Dl=i(rc,"P",{"data-svelte-h":!0}),g(Dl)!=="svelte-1nht1gz"&&(Dl.textContent=EL),og=n(rc),p(Ua.$$.fragment,rc),rc.forEach(d),tg=n(A),Me=i(A,"DIV",{class:!0});var Ja=$(Me);p(ys.$$.fragment,Ja),ag=n(Ja),Cl=i(Ja,"P",{"data-svelte-h":!0}),g(Cl)!=="svelte-rvubqa"&&(Cl.innerHTML=NL),rg=n(Ja),Sl=i(Ja,"P",{"data-svelte-h":!0}),g(Sl)!=="svelte-x8llv0"&&(Sl.textContent=zL),ng=n(Ja),p(Va.$$.fragment,Ja),Ja.forEach(d),sg=n(A),Lo=i(A,"DIV",{class:!0});var nc=$(Lo);p(Ms.$$.fragment,nc),ig=n(nc),kl=i(nc,"P",{"data-svelte-h":!0}),g(kl)!=="svelte-ioswce"&&(kl.innerHTML=YL),dg=n(nc),p(Wa.$$.fragment,nc),nc.forEach(d),lg=n(A),bo=i(A,"DIV",{class:!0});var sc=$(bo);p(Ts.$$.fragment,sc),cg=n(sc),Rl=i(sc,"P",{"data-svelte-h":!0}),g(Rl)!=="svelte-119cgd9"&&(Rl.textContent=QL),fg=n(sc),p(Xa.$$.fragment,sc),sc.forEach(d),pg=n(A),Pa=i(A,"DIV",{class:!0});var Af=$(Pa);p(Ds.$$.fragment,Af),mg=n(Af),Al=i(Af,"P",{"data-svelte-h":!0}),g(Al)!=="svelte-1rtya5j"&&(Al.textContent=OL),Af.forEach(d),A.forEach(d),Nc=n(e),p(Cs.$$.fragment,e),zc=n(e),ic=i(e,"P",{}),$(ic).forEach(d),this.h()},h(){y(t,"name","hf:doc:metadata"),y(t,"content",r2),y(Se,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ke,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Re,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Zo,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ve,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Ae,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Eo,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Ie,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y($e,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Ue,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Ve,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Oo,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(S,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Ko,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(et,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(re,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(We,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(tt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(P,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(at,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(rt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ne,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Xe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(st,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(F,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(it,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(dt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(de,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Pe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ct,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Fe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(U,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(pt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(mt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(le,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Je,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ut,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(He,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(je,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(I,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(xt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Lt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Ze,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(wt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Ge,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(J,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y($t,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(yt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(qe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Tt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Be,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(H,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Ct,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(St,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Ee,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Rt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Ne,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(j,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(It,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Ut,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ze,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Wt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Ye,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Z,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Pt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Ft,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Qe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Ht,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Oe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(G,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Zt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Gt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Ke,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Bt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(eo,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(q,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Nt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(zt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(oo,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Qt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(to,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(B,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Kt,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ea,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ao,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ta,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ro,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(E,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ra,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(na,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(no,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ia,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(so,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(N,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(la,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ca,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(io,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(pa,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(lo,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(z,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(_a,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ua,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Te,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ha,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ga,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(co,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(La,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(fo,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Y,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(wa,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(va,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(po,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ya,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(mo,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Q,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(_o,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(uo,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ho,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Sa,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(ye,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(go,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Ia,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(xo,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Me,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Lo,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(bo,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(Pa,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(k,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8")},m(e,x){o(document.head,t),L(e,b,x),L(e,l,x),L(e,c,x),m(v,e,x),L(e,a,x),L(e,w,x),L(e,dc,x),L(e,Ha,x),L(e,lc,x),m(Fo,e,x),L(e,cc,x),m(ja,e,x),L(e,fc,x),L(e,S,x),m(Za,S,null),o(S,If),o(S,Ys),o(S,Uf),o(S,Se),m(Ga,Se,null),o(Se,Vf),o(Se,Qs),o(Se,Wf),m(Jo,Se,null),o(S,Xf),o(S,ke),m(qa,ke,null),o(ke,Pf),o(ke,Os),o(ke,Ff),m(Ho,ke,null),o(S,Jf),o(S,Re),m(Ba,Re,null),o(Re,Hf),o(Re,Ks),o(Re,jf),m(jo,Re,null),o(S,Zf),o(S,Zo),m(Ea,Zo,null),o(Zo,Gf),o(Zo,ei),o(S,qf),o(S,ve),m(Na,ve,null),o(ve,Bf),o(ve,oi),o(ve,Ef),m(Go,ve,null),o(ve,Nf),m(qo,ve,null),o(S,zf),o(S,Ae),m(za,Ae,null),o(Ae,Yf),o(Ae,ti),o(Ae,Qf),m(Bo,Ae,null),o(S,Of),o(S,Eo),m(Ya,Eo,null),o(Eo,Kf),o(Eo,ai),o(S,ep),o(S,Ie),m(Qa,Ie,null),o(Ie,op),o(Ie,ri),o(Ie,tp),m(No,Ie,null),o(S,ap),o(S,$e),m(Oa,$e,null),o($e,rp),o($e,ni),o($e,np),o($e,si),o($e,sp),m(zo,$e,null),o(S,ip),o(S,Ue),m(Ka,Ue,null),o(Ue,dp),o(Ue,ii),o(Ue,lp),m(Yo,Ue,null),o(S,cp),o(S,Ve),m(er,Ve,null),o(Ve,fp),o(Ve,di),o(Ve,pp),m(Qo,Ve,null),o(S,mp),o(S,Oo),m(or,Oo,null),o(Oo,_p),o(Oo,li),L(e,pc,x),m(tr,e,x),L(e,mc,x),L(e,P,x),m(ar,P,null),o(P,up),o(P,ci),o(P,hp),o(P,Ko),m(rr,Ko,null),o(Ko,gp),o(Ko,fi),o(P,xp),o(P,et),m(nr,et,null),o(et,Lp),o(et,pi),o(P,bp),o(P,re),m(sr,re,null),o(re,wp),o(re,mi),o(re,vp),o(re,_i),o(re,$p),o(re,ui),o(re,yp),o(re,hi),o(re,Mp),o(re,gi),o(P,Tp),o(P,We),m(ir,We,null),o(We,Dp),o(We,xi),o(We,Cp),m(ot,We,null),o(P,Sp),o(P,tt),m(dr,tt,null),o(tt,kp),o(tt,Li),L(e,_c,x),m(lr,e,x),L(e,uc,x),L(e,F,x),m(cr,F,null),o(F,Rp),o(F,bi),o(F,Ap),o(F,at),m(fr,at,null),o(at,Ip),o(at,wi),o(F,Up),o(F,rt),m(pr,rt,null),o(rt,Vp),o(rt,vi),o(F,Wp),o(F,ne),m(mr,ne,null),o(ne,Xp),o(ne,$i),o(ne,Pp),o(ne,yi),o(ne,Fp),o(ne,Mi),o(ne,Jp),o(ne,Ti),o(ne,Hp),o(ne,Di),o(F,jp),o(F,Xe),m(_r,Xe,null),o(Xe,Zp),o(Xe,Ci),o(Xe,Gp),m(nt,Xe,null),o(F,qp),o(F,st),m(ur,st,null),o(st,Bp),o(st,Si),L(e,hc,x),m(hr,e,x),L(e,gc,x),L(e,U,x),m(gr,U,null),o(U,Ep),o(U,ki),o(U,Np),o(U,Ri),o(U,zp),o(U,it),m(xr,it,null),o(it,Yp),o(it,Ai),o(U,Qp),o(U,dt),m(Lr,dt,null),o(dt,Op),o(dt,Ii),o(U,Kp),o(U,de),m(br,de,null),o(de,em),o(de,Ui),o(de,om),o(de,Vi),o(de,tm),o(de,Wi),o(de,am),o(de,Xi),o(U,rm),o(U,Pe),m(wr,Pe,null),o(Pe,nm),o(Pe,Pi),o(Pe,sm),m(lt,Pe,null),o(U,im),o(U,ct),m(vr,ct,null),o(ct,dm),o(ct,Fi),o(U,lm),o(U,Fe),m($r,Fe,null),o(Fe,cm),o(Fe,Ji),o(Fe,fm),m(ft,Fe,null),L(e,xc,x),m(yr,e,x),L(e,Lc,x),L(e,I,x),m(Mr,I,null),o(I,pm),o(I,Hi),o(I,mm),o(I,ji),o(I,_m),o(I,pt),m(Tr,pt,null),o(pt,um),o(pt,Zi),o(I,hm),o(I,mt),m(Dr,mt,null),o(mt,gm),o(mt,Gi),o(I,xm),o(I,le),m(Cr,le,null),o(le,Lm),o(le,qi),o(le,bm),o(le,Bi),o(le,wm),o(le,Ei),o(le,vm),o(le,Ni),o(I,$m),o(I,Je),m(Sr,Je,null),o(Je,ym),o(Je,zi),o(Je,Mm),m(_t,Je,null),o(I,Tm),o(I,ut),m(kr,ut,null),o(ut,Dm),o(ut,Yi),o(I,Cm),o(I,He),m(Rr,He,null),o(He,Sm),o(He,Qi),o(He,km),m(ht,He,null),o(I,Rm),o(I,je),m(Ar,je,null),o(je,Am),o(je,Oi),o(je,Im),m(gt,je,null),L(e,bc,x),m(Ir,e,x),L(e,wc,x),L(e,J,x),m(Ur,J,null),o(J,Um),o(J,Ki),o(J,Vm),o(J,xt),m(Vr,xt,null),o(xt,Wm),o(xt,ed),o(J,Xm),o(J,Lt),m(Wr,Lt,null),o(Lt,Pm),o(Lt,od),o(J,Fm),o(J,Ze),m(Xr,Ze,null),o(Ze,Jm),o(Ze,td),o(Ze,Hm),m(bt,Ze,null),o(J,jm),o(J,wt),m(Pr,wt,null),o(wt,Zm),o(wt,ad),o(J,Gm),o(J,Ge),m(Fr,Ge,null),o(Ge,qm),o(Ge,rd),o(Ge,Bm),m(vt,Ge,null),L(e,vc,x),m(Jr,e,x),L(e,$c,x),L(e,H,x),m(Hr,H,null),o(H,Em),o(H,nd),o(H,Nm),o(H,$t),m(jr,$t,null),o($t,zm),o($t,sd),o(H,Ym),o(H,yt),m(Zr,yt,null),o(yt,Qm),o(yt,id),o(H,Om),o(H,qe),m(Gr,qe,null),o(qe,Km),o(qe,dd),o(qe,e_),m(Mt,qe,null),o(H,o_),o(H,Tt),m(qr,Tt,null),o(Tt,t_),o(Tt,ld),o(H,a_),o(H,Be),m(Br,Be,null),o(Be,r_),o(Be,cd),o(Be,n_),m(Dt,Be,null),L(e,yc,x),m(Er,e,x),L(e,Mc,x),L(e,j,x),m(Nr,j,null),o(j,s_),o(j,fd),o(j,i_),o(j,Ct),m(zr,Ct,null),o(Ct,d_),o(Ct,pd),o(j,l_),o(j,St),m(Yr,St,null),o(St,c_),o(St,md),o(j,f_),o(j,Ee),m(Qr,Ee,null),o(Ee,p_),o(Ee,_d),o(Ee,m_),m(kt,Ee,null),o(j,__),o(j,Rt),m(Or,Rt,null),o(Rt,u_),o(Rt,ud),o(j,h_),o(j,Ne),m(Kr,Ne,null),o(Ne,g_),o(Ne,hd),o(Ne,x_),m(At,Ne,null),L(e,Tc,x),m(en,e,x),L(e,Dc,x),L(e,Z,x),m(on,Z,null),o(Z,L_),o(Z,gd),o(Z,b_),o(Z,It),m(tn,It,null),o(It,w_),o(It,xd),o(Z,v_),o(Z,Ut),m(an,Ut,null),o(Ut,$_),o(Ut,Ld),o(Z,y_),o(Z,ze),m(rn,ze,null),o(ze,M_),o(ze,bd),o(ze,T_),m(Vt,ze,null),o(Z,D_),o(Z,Wt),m(nn,Wt,null),o(Wt,C_),o(Wt,wd),o(Z,S_),o(Z,Ye),m(sn,Ye,null),o(Ye,k_),o(Ye,vd),o(Ye,R_),m(Xt,Ye,null),L(e,Cc,x),m(dn,e,x),L(e,Sc,x),L(e,G,x),m(ln,G,null),o(G,A_),o(G,$d),o(G,I_),o(G,Pt),m(cn,Pt,null),o(Pt,U_),o(Pt,yd),o(G,V_),o(G,Ft),m(fn,Ft,null),o(Ft,W_),o(Ft,Md),o(G,X_),o(G,Qe),m(pn,Qe,null),o(Qe,P_),o(Qe,Td),o(Qe,F_),m(Jt,Qe,null),o(G,J_),o(G,Ht),m(mn,Ht,null),o(Ht,H_),o(Ht,Dd),o(G,j_),o(G,Oe),m(_n,Oe,null),o(Oe,Z_),o(Oe,Cd),o(Oe,G_),m(jt,Oe,null),L(e,kc,x),m(un,e,x),L(e,Rc,x),L(e,q,x),m(hn,q,null),o(q,q_),o(q,Sd),o(q,B_),o(q,Zt),m(gn,Zt,null),o(Zt,E_),o(Zt,kd),o(q,N_),o(q,Gt),m(xn,Gt,null),o(Gt,z_),o(Gt,Rd),o(q,Y_),o(q,Ke),m(Ln,Ke,null),o(Ke,Q_),o(Ke,Ad),o(Ke,O_),m(qt,Ke,null),o(q,K_),o(q,Bt),m(bn,Bt,null),o(Bt,eu),o(Bt,Id),o(q,ou),o(q,eo),m(wn,eo,null),o(eo,tu),o(eo,Ud),o(eo,au),m(Et,eo,null),L(e,Ac,x),m(vn,e,x),L(e,Ic,x),L(e,B,x),m($n,B,null),o(B,ru),o(B,Vd),o(B,nu),o(B,Nt),m(yn,Nt,null),o(Nt,su),o(Nt,Wd),o(B,iu),o(B,zt),m(Mn,zt,null),o(zt,du),o(zt,Xd),o(B,lu),o(B,oo),m(Tn,oo,null),o(oo,cu),o(oo,Pd),o(oo,fu),m(Yt,oo,null),o(B,pu),o(B,Qt),m(Dn,Qt,null),o(Qt,mu),o(Qt,Fd),o(B,_u),o(B,to),m(Cn,to,null),o(to,uu),o(to,Jd),o(to,hu),m(Ot,to,null),L(e,Uc,x),m(Sn,e,x),L(e,Vc,x),L(e,E,x),m(kn,E,null),o(E,gu),o(E,Hd),o(E,xu),o(E,Kt),m(Rn,Kt,null),o(Kt,Lu),o(Kt,jd),o(E,bu),o(E,ea),m(An,ea,null),o(ea,wu),o(ea,Zd),o(E,vu),o(E,ao),m(In,ao,null),o(ao,$u),o(ao,Gd),o(ao,yu),m(oa,ao,null),o(E,Mu),o(E,ta),m(Un,ta,null),o(ta,Tu),o(ta,qd),o(E,Du),o(E,ro),m(Vn,ro,null),o(ro,Cu),o(ro,Bd),o(ro,Su),m(aa,ro,null),L(e,Wc,x),m(Wn,e,x),L(e,Xc,x),L(e,N,x),m(Xn,N,null),o(N,ku),o(N,Ed),o(N,Ru),o(N,ra),m(Pn,ra,null),o(ra,Au),o(ra,Nd),o(N,Iu),o(N,na),m(Fn,na,null),o(na,Uu),o(na,zd),o(N,Vu),o(N,no),m(Jn,no,null),o(no,Wu),o(no,Yd),o(no,Xu),m(sa,no,null),o(N,Pu),o(N,ia),m(Hn,ia,null),o(ia,Fu),o(ia,Qd),o(N,Ju),o(N,so),m(jn,so,null),o(so,Hu),o(so,Od),o(so,ju),m(da,so,null),L(e,Pc,x),m(Zn,e,x),L(e,Fc,x),L(e,z,x),m(Gn,z,null),o(z,Zu),o(z,Kd),o(z,Gu),o(z,la),m(qn,la,null),o(la,qu),o(la,el),o(z,Bu),o(z,ca),m(Bn,ca,null),o(ca,Eu),o(ca,ol),o(z,Nu),o(z,io),m(En,io,null),o(io,zu),o(io,tl),o(io,Yu),m(fa,io,null),o(z,Qu),o(z,pa),m(Nn,pa,null),o(pa,Ou),o(pa,al),o(z,Ku),o(z,lo),m(zn,lo,null),o(lo,eh),o(lo,rl),o(lo,oh),m(ma,lo,null),L(e,Jc,x),m(Yn,e,x),L(e,Hc,x),L(e,Te,x),m(Qn,Te,null),o(Te,th),o(Te,_a),m(On,_a,null),o(_a,ah),o(_a,nl),o(Te,rh),o(Te,ua),m(Kn,ua,null),o(ua,nh),o(ua,sl),L(e,jc,x),m(es,e,x),L(e,Zc,x),L(e,Y,x),m(os,Y,null),o(Y,sh),o(Y,il),o(Y,ih),o(Y,ha),m(ts,ha,null),o(ha,dh),o(ha,dl),o(Y,lh),o(Y,ga),m(as,ga,null),o(ga,ch),o(ga,ll),o(Y,fh),o(Y,co),m(rs,co,null),o(co,ph),o(co,cl),o(co,mh),m(xa,co,null),o(Y,_h),o(Y,La),m(ns,La,null),o(La,uh),o(La,fl),o(Y,hh),o(Y,fo),m(ss,fo,null),o(fo,gh),o(fo,pl),o(fo,xh),m(ba,fo,null),L(e,Gc,x),m(is,e,x),L(e,qc,x),L(e,Q,x),m(ds,Q,null),o(Q,Lh),o(Q,ml),o(Q,bh),o(Q,wa),m(ls,wa,null),o(wa,wh),o(wa,_l),o(Q,vh),o(Q,va),m(cs,va,null),o(va,$h),o(va,ul),o(Q,yh),o(Q,po),m(fs,po,null),o(po,Mh),o(po,hl),o(po,Th),m($a,po,null),o(Q,Dh),o(Q,ya),m(ps,ya,null),o(ya,Ch),o(ya,gl),o(Q,Sh),o(Q,mo),m(ms,mo,null),o(mo,kh),o(mo,xl),o(mo,Rh),m(Ma,mo,null),L(e,Bc,x),m(_s,e,x),L(e,Ec,x),L(e,k,x),m(us,k,null),o(k,Ah),o(k,Ll),o(k,Ih),o(k,_o),m(hs,_o,null),o(_o,Uh),o(_o,bl),o(_o,Vh),m(Ta,_o,null),o(k,Wh),o(k,uo),m(gs,uo,null),o(uo,Xh),o(uo,wl),o(uo,Ph),m(Da,uo,null),o(k,Fh),o(k,ho),m(xs,ho,null),o(ho,Jh),o(ho,vl),o(ho,Hh),m(Ca,ho,null),o(k,jh),o(k,Sa),m(Ls,Sa,null),o(Sa,Zh),o(Sa,$l),o(k,Gh),o(k,ye),m(bs,ye,null),o(ye,qh),o(ye,yl),o(ye,Bh),m(ka,ye,null),o(ye,Eh),m(Ra,ye,null),o(k,Nh),o(k,go),m(ws,go,null),o(go,zh),o(go,Ml),o(go,Yh),m(Aa,go,null),o(k,Qh),o(k,Ia),m(vs,Ia,null),o(Ia,Oh),o(Ia,Tl),o(k,Kh),o(k,xo),m($s,xo,null),o(xo,eg),o(xo,Dl),o(xo,og),m(Ua,xo,null),o(k,tg),o(k,Me),m(ys,Me,null),o(Me,ag),o(Me,Cl),o(Me,rg),o(Me,Sl),o(Me,ng),m(Va,Me,null),o(k,sg),o(k,Lo),m(Ms,Lo,null),o(Lo,ig),o(Lo,kl),o(Lo,dg),m(Wa,Lo,null),o(k,lg),o(k,bo),m(Ts,bo,null),o(bo,cg),o(bo,Rl),o(bo,fg),m(Xa,bo,null),o(k,pg),o(k,Pa),m(Ds,Pa,null),o(Pa,mg),o(Pa,Al),L(e,Nc,x),m(Cs,e,x),L(e,zc,x),L(e,ic,x),Yc=!0},p(e,[x]){const R={};x&2&&(R.$$scope={dirty:x,ctx:e}),Fo.$set(R);const wo={};x&2&&(wo.$$scope={dirty:x,ctx:e}),Jo.$set(wo);const vo={};x&2&&(vo.$$scope={dirty:x,ctx:e}),Ho.$set(vo);const $o={};x&2&&($o.$$scope={dirty:x,ctx:e}),jo.$set($o);const Ss={};x&2&&(Ss.$$scope={dirty:x,ctx:e}),Go.$set(Ss);const De={};x&2&&(De.$$scope={dirty:x,ctx:e}),qo.$set(De);const yo={};x&2&&(yo.$$scope={dirty:x,ctx:e}),Bo.$set(yo);const ks={};x&2&&(ks.$$scope={dirty:x,ctx:e}),No.$set(ks);const Mo={};x&2&&(Mo.$$scope={dirty:x,ctx:e}),zo.$set(Mo);const Ce={};x&2&&(Ce.$$scope={dirty:x,ctx:e}),Yo.$set(Ce);const To={};x&2&&(To.$$scope={dirty:x,ctx:e}),Qo.$set(To);const Do={};x&2&&(Do.$$scope={dirty:x,ctx:e}),ot.$set(Do);const Rs={};x&2&&(Rs.$$scope={dirty:x,ctx:e}),nt.$set(Rs);const O={};x&2&&(O.$$scope={dirty:x,ctx:e}),lt.$set(O);const As={};x&2&&(As.$$scope={dirty:x,ctx:e}),ft.$set(As);const Is={};x&2&&(Is.$$scope={dirty:x,ctx:e}),_t.$set(Is);const se={};x&2&&(se.$$scope={dirty:x,ctx:e}),ht.$set(se);const Co={};x&2&&(Co.$$scope={dirty:x,ctx:e}),gt.$set(Co);const Us={};x&2&&(Us.$$scope={dirty:x,ctx:e}),bt.$set(Us);const K={};x&2&&(K.$$scope={dirty:x,ctx:e}),vt.$set(K);const Vs={};x&2&&(Vs.$$scope={dirty:x,ctx:e}),Mt.$set(Vs);const Ws={};x&2&&(Ws.$$scope={dirty:x,ctx:e}),Dt.$set(Ws);const ie={};x&2&&(ie.$$scope={dirty:x,ctx:e}),kt.$set(ie);const So={};x&2&&(So.$$scope={dirty:x,ctx:e}),At.$set(So);const Xs={};x&2&&(Xs.$$scope={dirty:x,ctx:e}),Vt.$set(Xs);const W={};x&2&&(W.$$scope={dirty:x,ctx:e}),Xt.$set(W);const Ps={};x&2&&(Ps.$$scope={dirty:x,ctx:e}),Jt.$set(Ps);const Fs={};x&2&&(Fs.$$scope={dirty:x,ctx:e}),jt.$set(Fs);const be={};x&2&&(be.$$scope={dirty:x,ctx:e}),qt.$set(be);const ko={};x&2&&(ko.$$scope={dirty:x,ctx:e}),Et.$set(ko);const Js={};x&2&&(Js.$$scope={dirty:x,ctx:e}),Yt.$set(Js);const Ro={};x&2&&(Ro.$$scope={dirty:x,ctx:e}),Ot.$set(Ro);const V={};x&2&&(V.$$scope={dirty:x,ctx:e}),oa.$set(V);const Hs={};x&2&&(Hs.$$scope={dirty:x,ctx:e}),aa.$set(Hs);const js={};x&2&&(js.$$scope={dirty:x,ctx:e}),sa.$set(js);const we={};x&2&&(we.$$scope={dirty:x,ctx:e}),da.$set(we);const Ao={};x&2&&(Ao.$$scope={dirty:x,ctx:e}),fa.$set(Ao);const Zs={};x&2&&(Zs.$$scope={dirty:x,ctx:e}),ma.$set(Zs);const Io={};x&2&&(Io.$$scope={dirty:x,ctx:e}),xa.$set(Io);const Uo={};x&2&&(Uo.$$scope={dirty:x,ctx:e}),ba.$set(Uo);const ee={};x&2&&(ee.$$scope={dirty:x,ctx:e}),$a.$set(ee);const Gs={};x&2&&(Gs.$$scope={dirty:x,ctx:e}),Ma.$set(Gs);const qs={};x&2&&(qs.$$scope={dirty:x,ctx:e}),Ta.$set(qs);const Vo={};x&2&&(Vo.$$scope={dirty:x,ctx:e}),Da.$set(Vo);const Bs={};x&2&&(Bs.$$scope={dirty:x,ctx:e}),Ca.$set(Bs);const Wo={};x&2&&(Wo.$$scope={dirty:x,ctx:e}),ka.$set(Wo);const oe={};x&2&&(oe.$$scope={dirty:x,ctx:e}),Ra.$set(oe);const Es={};x&2&&(Es.$$scope={dirty:x,ctx:e}),Aa.$set(Es);const Ns={};x&2&&(Ns.$$scope={dirty:x,ctx:e}),Ua.$set(Ns);const Xo={};x&2&&(Xo.$$scope={dirty:x,ctx:e}),Va.$set(Xo);const zs={};x&2&&(zs.$$scope={dirty:x,ctx:e}),Wa.$set(zs);const Po={};x&2&&(Po.$$scope={dirty:x,ctx:e}),Xa.$set(Po)},i(e){Yc||(_(v.$$.fragment,e),_(Fo.$$.fragment,e),_(ja.$$.fragment,e),_(Za.$$.fragment,e),_(Ga.$$.fragment,e),_(Jo.$$.fragment,e),_(qa.$$.fragment,e),_(Ho.$$.fragment,e),_(Ba.$$.fragment,e),_(jo.$$.fragment,e),_(Ea.$$.fragment,e),_(Na.$$.fragment,e),_(Go.$$.fragment,e),_(qo.$$.fragment,e),_(za.$$.fragment,e),_(Bo.$$.fragment,e),_(Ya.$$.fragment,e),_(Qa.$$.fragment,e),_(No.$$.fragment,e),_(Oa.$$.fragment,e),_(zo.$$.fragment,e),_(Ka.$$.fragment,e),_(Yo.$$.fragment,e),_(er.$$.fragment,e),_(Qo.$$.fragment,e),_(or.$$.fragment,e),_(tr.$$.fragment,e),_(ar.$$.fragment,e),_(rr.$$.fragment,e),_(nr.$$.fragment,e),_(sr.$$.fragment,e),_(ir.$$.fragment,e),_(ot.$$.fragment,e),_(dr.$$.fragment,e),_(lr.$$.fragment,e),_(cr.$$.fragment,e),_(fr.$$.fragment,e),_(pr.$$.fragment,e),_(mr.$$.fragment,e),_(_r.$$.fragment,e),_(nt.$$.fragment,e),_(ur.$$.fragment,e),_(hr.$$.fragment,e),_(gr.$$.fragment,e),_(xr.$$.fragment,e),_(Lr.$$.fragment,e),_(br.$$.fragment,e),_(wr.$$.fragment,e),_(lt.$$.fragment,e),_(vr.$$.fragment,e),_($r.$$.fragment,e),_(ft.$$.fragment,e),_(yr.$$.fragment,e),_(Mr.$$.fragment,e),_(Tr.$$.fragment,e),_(Dr.$$.fragment,e),_(Cr.$$.fragment,e),_(Sr.$$.fragment,e),_(_t.$$.fragment,e),_(kr.$$.fragment,e),_(Rr.$$.fragment,e),_(ht.$$.fragment,e),_(Ar.$$.fragment,e),_(gt.$$.fragment,e),_(Ir.$$.fragment,e),_(Ur.$$.fragment,e),_(Vr.$$.fragment,e),_(Wr.$$.fragment,e),_(Xr.$$.fragment,e),_(bt.$$.fragment,e),_(Pr.$$.fragment,e),_(Fr.$$.fragment,e),_(vt.$$.fragment,e),_(Jr.$$.fragment,e),_(Hr.$$.fragment,e),_(jr.$$.fragment,e),_(Zr.$$.fragment,e),_(Gr.$$.fragment,e),_(Mt.$$.fragment,e),_(qr.$$.fragment,e),_(Br.$$.fragment,e),_(Dt.$$.fragment,e),_(Er.$$.fragment,e),_(Nr.$$.fragment,e),_(zr.$$.fragment,e),_(Yr.$$.fragment,e),_(Qr.$$.fragment,e),_(kt.$$.fragment,e),_(Or.$$.fragment,e),_(Kr.$$.fragment,e),_(At.$$.fragment,e),_(en.$$.fragment,e),_(on.$$.fragment,e),_(tn.$$.fragment,e),_(an.$$.fragment,e),_(rn.$$.fragment,e),_(Vt.$$.fragment,e),_(nn.$$.fragment,e),_(sn.$$.fragment,e),_(Xt.$$.fragment,e),_(dn.$$.fragment,e),_(ln.$$.fragment,e),_(cn.$$.fragment,e),_(fn.$$.fragment,e),_(pn.$$.fragment,e),_(Jt.$$.fragment,e),_(mn.$$.fragment,e),_(_n.$$.fragment,e),_(jt.$$.fragment,e),_(un.$$.fragment,e),_(hn.$$.fragment,e),_(gn.$$.fragment,e),_(xn.$$.fragment,e),_(Ln.$$.fragment,e),_(qt.$$.fragment,e),_(bn.$$.fragment,e),_(wn.$$.fragment,e),_(Et.$$.fragment,e),_(vn.$$.fragment,e),_($n.$$.fragment,e),_(yn.$$.fragment,e),_(Mn.$$.fragment,e),_(Tn.$$.fragment,e),_(Yt.$$.fragment,e),_(Dn.$$.fragment,e),_(Cn.$$.fragment,e),_(Ot.$$.fragment,e),_(Sn.$$.fragment,e),_(kn.$$.fragment,e),_(Rn.$$.fragment,e),_(An.$$.fragment,e),_(In.$$.fragment,e),_(oa.$$.fragment,e),_(Un.$$.fragment,e),_(Vn.$$.fragment,e),_(aa.$$.fragment,e),_(Wn.$$.fragment,e),_(Xn.$$.fragment,e),_(Pn.$$.fragment,e),_(Fn.$$.fragment,e),_(Jn.$$.fragment,e),_(sa.$$.fragment,e),_(Hn.$$.fragment,e),_(jn.$$.fragment,e),_(da.$$.fragment,e),_(Zn.$$.fragment,e),_(Gn.$$.fragment,e),_(qn.$$.fragment,e),_(Bn.$$.fragment,e),_(En.$$.fragment,e),_(fa.$$.fragment,e),_(Nn.$$.fragment,e),_(zn.$$.fragment,e),_(ma.$$.fragment,e),_(Yn.$$.fragment,e),_(Qn.$$.fragment,e),_(On.$$.fragment,e),_(Kn.$$.fragment,e),_(es.$$.fragment,e),_(os.$$.fragment,e),_(ts.$$.fragment,e),_(as.$$.fragment,e),_(rs.$$.fragment,e),_(xa.$$.fragment,e),_(ns.$$.fragment,e),_(ss.$$.fragment,e),_(ba.$$.fragment,e),_(is.$$.fragment,e),_(ds.$$.fragment,e),_(ls.$$.fragment,e),_(cs.$$.fragment,e),_(fs.$$.fragment,e),_($a.$$.fragment,e),_(ps.$$.fragment,e),_(ms.$$.fragment,e),_(Ma.$$.fragment,e),_(_s.$$.fragment,e),_(us.$$.fragment,e),_(hs.$$.fragment,e),_(Ta.$$.fragment,e),_(gs.$$.fragment,e),_(Da.$$.fragment,e),_(xs.$$.fragment,e),_(Ca.$$.fragment,e),_(Ls.$$.fragment,e),_(bs.$$.fragment,e),_(ka.$$.fragment,e),_(Ra.$$.fragment,e),_(ws.$$.fragment,e),_(Aa.$$.fragment,e),_(vs.$$.fragment,e),_($s.$$.fragment,e),_(Ua.$$.fragment,e),_(ys.$$.fragment,e),_(Va.$$.fragment,e),_(Ms.$$.fragment,e),_(Wa.$$.fragment,e),_(Ts.$$.fragment,e),_(Xa.$$.fragment,e),_(Ds.$$.fragment,e),_(Cs.$$.fragment,e),Yc=!0)},o(e){u(v.$$.fragment,e),u(Fo.$$.fragment,e),u(ja.$$.fragment,e),u(Za.$$.fragment,e),u(Ga.$$.fragment,e),u(Jo.$$.fragment,e),u(qa.$$.fragment,e),u(Ho.$$.fragment,e),u(Ba.$$.fragment,e),u(jo.$$.fragment,e),u(Ea.$$.fragment,e),u(Na.$$.fragment,e),u(Go.$$.fragment,e),u(qo.$$.fragment,e),u(za.$$.fragment,e),u(Bo.$$.fragment,e),u(Ya.$$.fragment,e),u(Qa.$$.fragment,e),u(No.$$.fragment,e),u(Oa.$$.fragment,e),u(zo.$$.fragment,e),u(Ka.$$.fragment,e),u(Yo.$$.fragment,e),u(er.$$.fragment,e),u(Qo.$$.fragment,e),u(or.$$.fragment,e),u(tr.$$.fragment,e),u(ar.$$.fragment,e),u(rr.$$.fragment,e),u(nr.$$.fragment,e),u(sr.$$.fragment,e),u(ir.$$.fragment,e),u(ot.$$.fragment,e),u(dr.$$.fragment,e),u(lr.$$.fragment,e),u(cr.$$.fragment,e),u(fr.$$.fragment,e),u(pr.$$.fragment,e),u(mr.$$.fragment,e),u(_r.$$.fragment,e),u(nt.$$.fragment,e),u(ur.$$.fragment,e),u(hr.$$.fragment,e),u(gr.$$.fragment,e),u(xr.$$.fragment,e),u(Lr.$$.fragment,e),u(br.$$.fragment,e),u(wr.$$.fragment,e),u(lt.$$.fragment,e),u(vr.$$.fragment,e),u($r.$$.fragment,e),u(ft.$$.fragment,e),u(yr.$$.fragment,e),u(Mr.$$.fragment,e),u(Tr.$$.fragment,e),u(Dr.$$.fragment,e),u(Cr.$$.fragment,e),u(Sr.$$.fragment,e),u(_t.$$.fragment,e),u(kr.$$.fragment,e),u(Rr.$$.fragment,e),u(ht.$$.fragment,e),u(Ar.$$.fragment,e),u(gt.$$.fragment,e),u(Ir.$$.fragment,e),u(Ur.$$.fragment,e),u(Vr.$$.fragment,e),u(Wr.$$.fragment,e),u(Xr.$$.fragment,e),u(bt.$$.fragment,e),u(Pr.$$.fragment,e),u(Fr.$$.fragment,e),u(vt.$$.fragment,e),u(Jr.$$.fragment,e),u(Hr.$$.fragment,e),u(jr.$$.fragment,e),u(Zr.$$.fragment,e),u(Gr.$$.fragment,e),u(Mt.$$.fragment,e),u(qr.$$.fragment,e),u(Br.$$.fragment,e),u(Dt.$$.fragment,e),u(Er.$$.fragment,e),u(Nr.$$.fragment,e),u(zr.$$.fragment,e),u(Yr.$$.fragment,e),u(Qr.$$.fragment,e),u(kt.$$.fragment,e),u(Or.$$.fragment,e),u(Kr.$$.fragment,e),u(At.$$.fragment,e),u(en.$$.fragment,e),u(on.$$.fragment,e),u(tn.$$.fragment,e),u(an.$$.fragment,e),u(rn.$$.fragment,e),u(Vt.$$.fragment,e),u(nn.$$.fragment,e),u(sn.$$.fragment,e),u(Xt.$$.fragment,e),u(dn.$$.fragment,e),u(ln.$$.fragment,e),u(cn.$$.fragment,e),u(fn.$$.fragment,e),u(pn.$$.fragment,e),u(Jt.$$.fragment,e),u(mn.$$.fragment,e),u(_n.$$.fragment,e),u(jt.$$.fragment,e),u(un.$$.fragment,e),u(hn.$$.fragment,e),u(gn.$$.fragment,e),u(xn.$$.fragment,e),u(Ln.$$.fragment,e),u(qt.$$.fragment,e),u(bn.$$.fragment,e),u(wn.$$.fragment,e),u(Et.$$.fragment,e),u(vn.$$.fragment,e),u($n.$$.fragment,e),u(yn.$$.fragment,e),u(Mn.$$.fragment,e),u(Tn.$$.fragment,e),u(Yt.$$.fragment,e),u(Dn.$$.fragment,e),u(Cn.$$.fragment,e),u(Ot.$$.fragment,e),u(Sn.$$.fragment,e),u(kn.$$.fragment,e),u(Rn.$$.fragment,e),u(An.$$.fragment,e),u(In.$$.fragment,e),u(oa.$$.fragment,e),u(Un.$$.fragment,e),u(Vn.$$.fragment,e),u(aa.$$.fragment,e),u(Wn.$$.fragment,e),u(Xn.$$.fragment,e),u(Pn.$$.fragment,e),u(Fn.$$.fragment,e),u(Jn.$$.fragment,e),u(sa.$$.fragment,e),u(Hn.$$.fragment,e),u(jn.$$.fragment,e),u(da.$$.fragment,e),u(Zn.$$.fragment,e),u(Gn.$$.fragment,e),u(qn.$$.fragment,e),u(Bn.$$.fragment,e),u(En.$$.fragment,e),u(fa.$$.fragment,e),u(Nn.$$.fragment,e),u(zn.$$.fragment,e),u(ma.$$.fragment,e),u(Yn.$$.fragment,e),u(Qn.$$.fragment,e),u(On.$$.fragment,e),u(Kn.$$.fragment,e),u(es.$$.fragment,e),u(os.$$.fragment,e),u(ts.$$.fragment,e),u(as.$$.fragment,e),u(rs.$$.fragment,e),u(xa.$$.fragment,e),u(ns.$$.fragment,e),u(ss.$$.fragment,e),u(ba.$$.fragment,e),u(is.$$.fragment,e),u(ds.$$.fragment,e),u(ls.$$.fragment,e),u(cs.$$.fragment,e),u(fs.$$.fragment,e),u($a.$$.fragment,e),u(ps.$$.fragment,e),u(ms.$$.fragment,e),u(Ma.$$.fragment,e),u(_s.$$.fragment,e),u(us.$$.fragment,e),u(hs.$$.fragment,e),u(Ta.$$.fragment,e),u(gs.$$.fragment,e),u(Da.$$.fragment,e),u(xs.$$.fragment,e),u(Ca.$$.fragment,e),u(Ls.$$.fragment,e),u(bs.$$.fragment,e),u(ka.$$.fragment,e),u(Ra.$$.fragment,e),u(ws.$$.fragment,e),u(Aa.$$.fragment,e),u(vs.$$.fragment,e),u($s.$$.fragment,e),u(Ua.$$.fragment,e),u(ys.$$.fragment,e),u(Va.$$.fragment,e),u(Ms.$$.fragment,e),u(Wa.$$.fragment,e),u(Ts.$$.fragment,e),u(Xa.$$.fragment,e),u(Ds.$$.fragment,e),u(Cs.$$.fragment,e),Yc=!1},d(e){e&&(d(b),d(l),d(c),d(a),d(w),d(dc),d(Ha),d(lc),d(cc),d(fc),d(S),d(pc),d(mc),d(P),d(_c),d(uc),d(F),d(hc),d(gc),d(U),d(xc),d(Lc),d(I),d(bc),d(wc),d(J),d(vc),d($c),d(H),d(yc),d(Mc),d(j),d(Tc),d(Dc),d(Z),d(Cc),d(Sc),d(G),d(kc),d(Rc),d(q),d(Ac),d(Ic),d(B),d(Uc),d(Vc),d(E),d(Wc),d(Xc),d(N),d(Pc),d(Fc),d(z),d(Jc),d(Hc),d(Te),d(jc),d(Zc),d(Y),d(Gc),d(qc),d(Q),d(Bc),d(Ec),d(k),d(Nc),d(zc),d(ic)),d(t),h(v,e),h(Fo,e),h(ja,e),h(Za),h(Ga),h(Jo),h(qa),h(Ho),h(Ba),h(jo),h(Ea),h(Na),h(Go),h(qo),h(za),h(Bo),h(Ya),h(Qa),h(No),h(Oa),h(zo),h(Ka),h(Yo),h(er),h(Qo),h(or),h(tr,e),h(ar),h(rr),h(nr),h(sr),h(ir),h(ot),h(dr),h(lr,e),h(cr),h(fr),h(pr),h(mr),h(_r),h(nt),h(ur),h(hr,e),h(gr),h(xr),h(Lr),h(br),h(wr),h(lt),h(vr),h($r),h(ft),h(yr,e),h(Mr),h(Tr),h(Dr),h(Cr),h(Sr),h(_t),h(kr),h(Rr),h(ht),h(Ar),h(gt),h(Ir,e),h(Ur),h(Vr),h(Wr),h(Xr),h(bt),h(Pr),h(Fr),h(vt),h(Jr,e),h(Hr),h(jr),h(Zr),h(Gr),h(Mt),h(qr),h(Br),h(Dt),h(Er,e),h(Nr),h(zr),h(Yr),h(Qr),h(kt),h(Or),h(Kr),h(At),h(en,e),h(on),h(tn),h(an),h(rn),h(Vt),h(nn),h(sn),h(Xt),h(dn,e),h(ln),h(cn),h(fn),h(pn),h(Jt),h(mn),h(_n),h(jt),h(un,e),h(hn),h(gn),h(xn),h(Ln),h(qt),h(bn),h(wn),h(Et),h(vn,e),h($n),h(yn),h(Mn),h(Tn),h(Yt),h(Dn),h(Cn),h(Ot),h(Sn,e),h(kn),h(Rn),h(An),h(In),h(oa),h(Un),h(Vn),h(aa),h(Wn,e),h(Xn),h(Pn),h(Fn),h(Jn),h(sa),h(Hn),h(jn),h(da),h(Zn,e),h(Gn),h(qn),h(Bn),h(En),h(fa),h(Nn),h(zn),h(ma),h(Yn,e),h(Qn),h(On),h(Kn),h(es,e),h(os),h(ts),h(as),h(rs),h(xa),h(ns),h(ss),h(ba),h(is,e),h(ds),h(ls),h(cs),h(fs),h($a),h(ps),h(ms),h(Ma),h(_s,e),h(us),h(hs),h(Ta),h(gs),h(Da),h(xs),h(Ca),h(Ls),h(bs),h(ka),h(Ra),h(ws),h(Aa),h(vs),h($s),h(Ua),h(ys),h(Va),h(Ms),h(Wa),h(Ts),h(Xa),h(Ds),h(Cs,e)}}}const r2='{"title":"LoRA","local":"lora","sections":[{"title":"LoraBaseMixin","local":"diffusers.loaders.lora_base.LoraBaseMixin","sections":[],"depth":2},{"title":"StableDiffusionLoraLoaderMixin","local":"diffusers.loaders.StableDiffusionLoraLoaderMixin","sections":[],"depth":2},{"title":"StableDiffusionXLLoraLoaderMixin","local":"diffusers.loaders.StableDiffusionXLLoraLoaderMixin","sections":[],"depth":2},{"title":"SD3LoraLoaderMixin","local":"diffusers.loaders.SD3LoraLoaderMixin","sections":[],"depth":2},{"title":"FluxLoraLoaderMixin","local":"diffusers.loaders.FluxLoraLoaderMixin","sections":[],"depth":2},{"title":"CogVideoXLoraLoaderMixin","local":"diffusers.loaders.CogVideoXLoraLoaderMixin","sections":[],"depth":2},{"title":"Mochi1LoraLoaderMixin","local":"diffusers.loaders.Mochi1LoraLoaderMixin","sections":[],"depth":2},{"title":"AuraFlowLoraLoaderMixin","local":"diffusers.loaders.AuraFlowLoraLoaderMixin","sections":[],"depth":2},{"title":"LTXVideoLoraLoaderMixin","local":"diffusers.loaders.LTXVideoLoraLoaderMixin","sections":[],"depth":2},{"title":"SanaLoraLoaderMixin","local":"diffusers.loaders.SanaLoraLoaderMixin","sections":[],"depth":2},{"title":"HunyuanVideoLoraLoaderMixin","local":"diffusers.loaders.HunyuanVideoLoraLoaderMixin","sections":[],"depth":2},{"title":"Lumina2LoraLoaderMixin","local":"diffusers.loaders.Lumina2LoraLoaderMixin","sections":[],"depth":2},{"title":"CogView4LoraLoaderMixin","local":"diffusers.loaders.CogView4LoraLoaderMixin","sections":[],"depth":2},{"title":"WanLoraLoaderMixin","local":"diffusers.loaders.WanLoraLoaderMixin","sections":[],"depth":2},{"title":"SkyReelsV2LoraLoaderMixin","local":"diffusers.loaders.SkyReelsV2LoraLoaderMixin","sections":[],"depth":2},{"title":"AmusedLoraLoaderMixin","local":"diffusers.loaders.AmusedLoraLoaderMixin","sections":[],"depth":2},{"title":"HiDreamImageLoraLoaderMixin","local":"diffusers.loaders.HiDreamImageLoraLoaderMixin","sections":[],"depth":2},{"title":"QwenImageLoraLoaderMixin","local":"diffusers.loaders.QwenImageLoraLoaderMixin","sections":[],"depth":2},{"title":"LoraBaseMixin","local":"diffusers.loaders.lora_base.LoraBaseMixin","sections":[],"depth":2}],"depth":1}';function n2(T){return eb(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class m2 extends ob{constructor(t){super(),tb(this,t,n2,a2,KL,{})}}export{m2 as component};