diffusers/pr_11986/en/_app/immutable/nodes/10.7f0cfa4f.js

import{s as nL,o as sL,n as D}from"../chunks/scheduler.8c3d61f6.js";import{S as iL,i as dL,g as s,s as r,r as f,A as lL,h as i,f as l,c as n,j as $,u as p,x as g,k as y,y as o,a as b,v as m,d as _,t as u,w as h}from"../chunks/index.da70eac4.js";import{T as k}from"../chunks/Tip.1d9b8c37.js";import{D as M}from"../chunks/Docstring.eabe339b.js";import{C as te}from"../chunks/CodeBlock.a9c4becf.js";import{E as oe}from"../chunks/ExampleCodeBlock.4ca28371.js";import{H as Y,E as cL}from"../chunks/getInferenceSnippets.366c2c95.js";function fL(T){let t,L='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=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-1fw6lx1"&&(t.innerHTML=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function pL(T){let t,L="Example:",c,d,w;return d=new te({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=L,c=r(),f(d.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=L),c=n(a),p(d.$$.fragment,a)},m(a,v){b(a,t,v),b(a,c,v),m(d,a,v),w=!0},p:D,i(a){w||(_(d.$$.fragment,a),w=!0)},o(a){u(d.$$.fragment,a),w=!1},d(a){a&&(l(t),l(c)),h(d,a)}}}function mL(T){let t,L="Example:",c,d,w;return d=new te({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=L,c=r(),f(d.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=L),c=n(a),p(d.$$.fragment,a)},m(a,v){b(a,t,v),b(a,c,v),m(d,a,v),w=!0},p:D,i(a){w||(_(d.$$.fragment,a),w=!0)},o(a){u(d.$$.fragment,a),w=!1},d(a){a&&(l(t),l(c)),h(d,a)}}}function _L(T){let t,L="Example:",c,d,w;return d=new te({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=L,c=r(),f(d.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=L),c=n(a),p(d.$$.fragment,a)},m(a,v){b(a,t,v),b(a,c,v),m(d,a,v),w=!0},p:D,i(a){w||(_(d.$$.fragment,a),w=!0)},o(a){u(d.$$.fragment,a),w=!1},d(a){a&&(l(t),l(c)),h(d,a)}}}function uL(T){let t,L="This is an experimental API.";return{c(){t=s("p"),t.textContent=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function hL(T){let t,L="Example:",c,d,w;return d=new te({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=L,c=r(),f(d.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=L),c=n(a),p(d.$$.fragment,a)},m(a,v){b(a,t,v),b(a,c,v),m(d,a,v),w=!0},p:D,i(a){w||(_(d.$$.fragment,a),w=!0)},o(a){u(d.$$.fragment,a),w=!1},d(a){a&&(l(t),l(c)),h(d,a)}}}function gL(T){let t,L="Example:",c,d,w;return d=new te({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=L,c=r(),f(d.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=L),c=n(a),p(d.$$.fragment,a)},m(a,v){b(a,t,v),b(a,c,v),m(d,a,v),w=!0},p:D,i(a){w||(_(d.$$.fragment,a),w=!0)},o(a){u(d.$$.fragment,a),w=!1},d(a){a&&(l(t),l(c)),h(d,a)}}}function xL(T){let t,L="Example:",c,d,w;return d=new te({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=L,c=r(),f(d.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=L),c=n(a),p(d.$$.fragment,a)},m(a,v){b(a,t,v),b(a,c,v),m(d,a,v),w=!0},p:D,i(a){w||(_(d.$$.fragment,a),w=!0)},o(a){u(d.$$.fragment,a),w=!1},d(a){a&&(l(t),l(c)),h(d,a)}}}function LL(T){let t,L;return t=new te({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.$$.fragment)},l(c){p(t.$$.fragment,c)},m(c,d){m(t,c,d),L=!0},p:D,i(c){L||(_(t.$$.fragment,c),L=!0)},o(c){u(t.$$.fragment,c),L=!1},d(c){h(t,c)}}}function bL(T){let t,L="This is an experimental API.";return{c(){t=s("p"),t.textContent=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function wL(T){let t,L="Examples:",c,d,w;return d=new te({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=L,c=r(),f(d.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-kvfsh7"&&(t.textContent=L),c=n(a),p(d.$$.fragment,a)},m(a,v){b(a,t,v),b(a,c,v),m(d,a,v),w=!0},p:D,i(a){w||(_(d.$$.fragment,a),w=!0)},o(a){u(d.$$.fragment,a),w=!1},d(a){a&&(l(t),l(c)),h(d,a)}}}function vL(T){let t,L="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",c,d,w="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=L,c=r(),d=s("p"),d.textContent=w},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=L),c=n(a),d=i(a,"P",{"data-svelte-h":!0}),g(d)!=="svelte-3fufvn"&&(d.textContent=w)},m(a,v){b(a,t,v),b(a,c,v),b(a,d,v)},p:D,d(a){a&&(l(t),l(c),l(d))}}}function $L(T){let t,L="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",c,d,w="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=L,c=r(),d=s("p"),d.textContent=w},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=L),c=n(a),d=i(a,"P",{"data-svelte-h":!0}),g(d)!=="svelte-3fufvn"&&(d.textContent=w)},m(a,v){b(a,t,v),b(a,c,v),b(a,d,v)},p:D,d(a){a&&(l(t),l(c),l(d))}}}function yL(T){let t,L="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",c,d,w="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=L,c=r(),d=s("p"),d.textContent=w},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=L),c=n(a),d=i(a,"P",{"data-svelte-h":!0}),g(d)!=="svelte-3fufvn"&&(d.textContent=w)},m(a,v){b(a,t,v),b(a,c,v),b(a,d,v)},p:D,d(a){a&&(l(t),l(c),l(d))}}}function ML(T){let t,L="This is an experimental API.";return{c(){t=s("p"),t.textContent=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function TL(T){let t,L="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",c,d,w="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=L,c=r(),d=s("p"),d.textContent=w},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=L),c=n(a),d=i(a,"P",{"data-svelte-h":!0}),g(d)!=="svelte-3fufvn"&&(d.textContent=w)},m(a,v){b(a,t,v),b(a,c,v),b(a,d,v)},p:D,d(a){a&&(l(t),l(c),l(d))}}}function DL(T){let t,L="This is an experimental API.";return{c(){t=s("p"),t.textContent=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function CL(T){let t,L="Examples:",c,d,w;return d=new te({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=L,c=r(),f(d.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-kvfsh7"&&(t.textContent=L),c=n(a),p(d.$$.fragment,a)},m(a,v){b(a,t,v),b(a,c,v),m(d,a,v),w=!0},p:D,i(a){w||(_(d.$$.fragment,a),w=!0)},o(a){u(d.$$.fragment,a),w=!1},d(a){a&&(l(t),l(c)),h(d,a)}}}function SL(T){let t,L="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",c,d,w="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=L,c=r(),d=s("p"),d.textContent=w},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=L),c=n(a),d=i(a,"P",{"data-svelte-h":!0}),g(d)!=="svelte-3fufvn"&&(d.textContent=w)},m(a,v){b(a,t,v),b(a,c,v),b(a,d,v)},p:D,d(a){a&&(l(t),l(c),l(d))}}}function kL(T){let t,L="This is an experimental API.";return{c(){t=s("p"),t.textContent=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function RL(T){let t,L="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",c,d,w="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=L,c=r(),d=s("p"),d.textContent=w},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=L),c=n(a),d=i(a,"P",{"data-svelte-h":!0}),g(d)!=="svelte-3fufvn"&&(d.textContent=w)},m(a,v){b(a,t,v),b(a,c,v),b(a,d,v)},p:D,d(a){a&&(l(t),l(c),l(d))}}}function AL(T){let t,L="This is an experimental API.";return{c(){t=s("p"),t.textContent=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function UL(T){let t,L="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",c,d,w="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=L,c=r(),d=s("p"),d.textContent=w},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=L),c=n(a),d=i(a,"P",{"data-svelte-h":!0}),g(d)!=="svelte-3fufvn"&&(d.textContent=w)},m(a,v){b(a,t,v),b(a,c,v),b(a,d,v)},p:D,d(a){a&&(l(t),l(c),l(d))}}}function VL(T){let t,L="This is an experimental API.";return{c(){t=s("p"),t.textContent=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function IL(T){let t,L="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",c,d,w="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=L,c=r(),d=s("p"),d.textContent=w},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=L),c=n(a),d=i(a,"P",{"data-svelte-h":!0}),g(d)!=="svelte-3fufvn"&&(d.textContent=w)},m(a,v){b(a,t,v),b(a,c,v),b(a,d,v)},p:D,d(a){a&&(l(t),l(c),l(d))}}}function WL(T){let t,L="This is an experimental API.";return{c(){t=s("p"),t.textContent=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function XL(T){let t,L="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",c,d,w="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=L,c=r(),d=s("p"),d.textContent=w},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=L),c=n(a),d=i(a,"P",{"data-svelte-h":!0}),g(d)!=="svelte-3fufvn"&&(d.textContent=w)},m(a,v){b(a,t,v),b(a,c,v),b(a,d,v)},p:D,d(a){a&&(l(t),l(c),l(d))}}}function FL(T){let t,L="This is an experimental API.";return{c(){t=s("p"),t.textContent=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function JL(T){let t,L="We support loading original format HunyuanVideo LoRA checkpoints.",c,d,w="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=L,c=r(),d=s("p"),d.textContent=w},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-gyrs6h"&&(t.textContent=L),c=n(a),d=i(a,"P",{"data-svelte-h":!0}),g(d)!=="svelte-3fufvn"&&(d.textContent=w)},m(a,v){b(a,t,v),b(a,c,v),b(a,d,v)},p:D,d(a){a&&(l(t),l(c),l(d))}}}function PL(T){let t,L="This is an experimental API.";return{c(){t=s("p"),t.textContent=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function HL(T){let t,L="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",c,d,w="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=L,c=r(),d=s("p"),d.textContent=w},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=L),c=n(a),d=i(a,"P",{"data-svelte-h":!0}),g(d)!=="svelte-3fufvn"&&(d.textContent=w)},m(a,v){b(a,t,v),b(a,c,v),b(a,d,v)},p:D,d(a){a&&(l(t),l(c),l(d))}}}function jL(T){let t,L="This is an experimental API.";return{c(){t=s("p"),t.textContent=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function ZL(T){let t,L="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",c,d,w="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=L,c=r(),d=s("p"),d.textContent=w},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=L),c=n(a),d=i(a,"P",{"data-svelte-h":!0}),g(d)!=="svelte-3fufvn"&&(d.textContent=w)},m(a,v){b(a,t,v),b(a,c,v),b(a,d,v)},p:D,d(a){a&&(l(t),l(c),l(d))}}}function GL(T){let t,L="This is an experimental API.";return{c(){t=s("p"),t.textContent=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function BL(T){let t,L="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",c,d,w="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=L,c=r(),d=s("p"),d.textContent=w},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=L),c=n(a),d=i(a,"P",{"data-svelte-h":!0}),g(d)!=="svelte-3fufvn"&&(d.textContent=w)},m(a,v){b(a,t,v),b(a,c,v),b(a,d,v)},p:D,d(a){a&&(l(t),l(c),l(d))}}}function EL(T){let t,L="This is an experimental API.";return{c(){t=s("p"),t.textContent=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function qL(T){let t,L="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",c,d,w="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=L,c=r(),d=s("p"),d.textContent=w},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=L),c=n(a),d=i(a,"P",{"data-svelte-h":!0}),g(d)!=="svelte-3fufvn"&&(d.textContent=w)},m(a,v){b(a,t,v),b(a,c,v),b(a,d,v)},p:D,d(a){a&&(l(t),l(c),l(d))}}}function NL(T){let t,L="This is an experimental API.";return{c(){t=s("p"),t.textContent=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function zL(T){let t,L="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",c,d,w="This function is experimental and might change in the future.";return{c(){t=s("p"),t.textContent=L,c=r(),d=s("p"),d.textContent=w},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-15l1sdn"&&(t.textContent=L),c=n(a),d=i(a,"P",{"data-svelte-h":!0}),g(d)!=="svelte-3fufvn"&&(d.textContent=w)},m(a,v){b(a,t,v),b(a,c,v),b(a,d,v)},p:D,d(a){a&&(l(t),l(c),l(d))}}}function YL(T){let t,L="This is an experimental API.";return{c(){t=s("p"),t.textContent=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function QL(T){let t,L="Example:",c,d,w;return d=new te({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=L,c=r(),f(d.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=L),c=n(a),p(d.$$.fragment,a)},m(a,v){b(a,t,v),b(a,c,v),m(d,a,v),w=!0},p:D,i(a){w||(_(d.$$.fragment,a),w=!0)},o(a){u(d.$$.fragment,a),w=!1},d(a){a&&(l(t),l(c)),h(d,a)}}}function OL(T){let t,L="Example:",c,d,w;return d=new te({props:{code:"ZnJvbSUyMGRpZmZ1c2VycyUyMGltcG9ydCUyMEF1dG9QaXBlbGluZUZvclRleHQySW1hZ2UlMEFpbXBvcnQlMjB0b3JjaCUwQSUwQXBpcGVsaW5lJTIwJTNEJTIwQXV0b1BpcGVsaW5lRm9yVGV4dDJJbWFnZS5mcm9tX3ByZXRyYWluZWQoJTBBJTIwJTIwJTIwJTIwJTIyc3RhYmlsaXR5YWklMkZzdGFibGUtZGlmZnVzaW9uLXhsLWJhc2UtMS4wJTIyJTJDJTIwdG9yY2hfZHR5cGUlM0R0b3JjaC5mbG9hdDE2JTBBKS50byglMjJjdWRhJTIyKSUwQXBpcGVsaW5lLmxvYWRfbG9yYV93ZWlnaHRzKCUwQSUyMCUyMCUyMCUyMCUyMmpiaWxja2UtaGYlMkZzZHhsLWNpbmVtYXRpYy0xJTIyJTJDJTIwd2VpZ2h0X25hbWUlM0QlMjJweXRvcmNoX2xvcmFfd2VpZ2h0cy5zYWZldGVuc29ycyUyMiUyQyUyMGFkYXB0ZXJfbmFtZSUzRCUyMmNpbmVtYXRpYyUyMiUwQSklMEFwaXBlbGluZS5kaXNhYmxlX2xvcmEoKQ==",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=L,c=r(),f(d.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=L),c=n(a),p(d.$$.fragment,a)},m(a,v){b(a,t,v),b(a,c,v),m(d,a,v),w=!0},p:D,i(a){w||(_(d.$$.fragment,a),w=!0)},o(a){u(d.$$.fragment,a),w=!1},d(a){a&&(l(t),l(c)),h(d,a)}}}function KL(T){let t,L="Example:",c,d,w;return d=new te({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=L,c=r(),f(d.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=L),c=n(a),p(d.$$.fragment,a)},m(a,v){b(a,t,v),b(a,c,v),m(d,a,v),w=!0},p:D,i(a){w||(_(d.$$.fragment,a),w=!0)},o(a){u(d.$$.fragment,a),w=!1},d(a){a&&(l(t),l(c)),h(d,a)}}}function eb(T){let t,L="This is an experimental API.";return{c(){t=s("p"),t.textContent=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function ob(T){let t,L="Example:",c,d,w;return d=new te({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=L,c=r(),f(d.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=L),c=n(a),p(d.$$.fragment,a)},m(a,v){b(a,t,v),b(a,c,v),m(d,a,v),w=!0},p:D,i(a){w||(_(d.$$.fragment,a),w=!0)},o(a){u(d.$$.fragment,a),w=!1},d(a){a&&(l(t),l(c)),h(d,a)}}}function tb(T){let t,L="Example:",c,d,w;return d=new te({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=L,c=r(),f(d.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=L),c=n(a),p(d.$$.fragment,a)},m(a,v){b(a,t,v),b(a,c,v),m(d,a,v),w=!0},p:D,i(a){w||(_(d.$$.fragment,a),w=!0)},o(a){u(d.$$.fragment,a),w=!1},d(a){a&&(l(t),l(c)),h(d,a)}}}function ab(T){let t,L="Example:",c,d,w;return d=new te({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=L,c=r(),f(d.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-11lpom8"&&(t.textContent=L),c=n(a),p(d.$$.fragment,a)},m(a,v){b(a,t,v),b(a,c,v),m(d,a,v),w=!0},p:D,i(a){w||(_(d.$$.fragment,a),w=!0)},o(a){u(d.$$.fragment,a),w=!1},d(a){a&&(l(t),l(c)),h(d,a)}}}function rb(T){let t,L;return t=new te({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.$$.fragment)},l(c){p(t.$$.fragment,c)},m(c,d){m(t,c,d),L=!0},p:D,i(c){L||(_(t.$$.fragment,c),L=!0)},o(c){u(t.$$.fragment,c),L=!1},d(c){h(t,c)}}}function nb(T){let t,L="This is an experimental API.";return{c(){t=s("p"),t.textContent=L},l(c){t=i(c,"P",{"data-svelte-h":!0}),g(t)!=="svelte-8w79b9"&&(t.textContent=L)},m(c,d){b(c,t,d)},p:D,d(c){c&&l(t)}}}function sb(T){let t,L="Examples:",c,d,w;return d=new te({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=L,c=r(),f(d.$$.fragment)},l(a){t=i(a,"P",{"data-svelte-h":!0}),g(t)!=="svelte-kvfsh7"&&(t.textContent=L),c=n(a),p(d.$$.fragment,a)},m(a,v){b(a,t,v),b(a,c,v),m(d,a,v),w=!0},p:D,i(a){w||(_(d.$$.fragment,a),w=!0)},o(a){u(d.$$.fragment,a),w=!1},d(a){a&&(l(t),l(c)),h(d,a)}}}function ib(T){let t,L,c,d,w,a,v,Th='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_11986/en/api/models/unet2d-cond#diffusers.UNet2DConditionModel">UNet2DConditionModel</a>, for example) or a Transformer (<a href="/docs/diffusers/pr_11986/en/api/models/sd3_transformer2d#diffusers.SD3Transformer2DModel">SD3Transformer2DModel</a>, for example). There are several classes for loading LoRA weights:',Xl,Ra,Dh='<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_11986/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>LoraBaseMixin</code> provides a base class with several utility methods to fuse, unfuse, unload, LoRAs and more.</li>',Fl,Vo,Jl,Aa,Pl,C,Ua,af,As,Ch="Utility class for handling LoRAs.",rf,De,Va,nf,Us,Sh="Delete an adapter’s LoRA layers from the pipeline.",sf,Io,df,Ce,Ia,lf,Vs,kh="Disables the active LoRA layers of the pipeline.",cf,Wo,ff,Se,Wa,pf,Is,Rh="Enables the active LoRA layers of the pipeline.",mf,Xo,_f,Fo,Xa,uf,Ws,Ah=`Hotswap adapters without triggering recompilation of a model or if the ranks of the loaded adapters are
different.`,hf,be,Fa,gf,Xs,Uh="Fuses the LoRA parameters into the original parameters of the corresponding blocks.",xf,Jo,Lf,Po,bf,ke,Ja,wf,Fs,Vh="Gets the list of the current active adapters.",vf,Ho,$f,jo,Pa,yf,Js,Ih="Gets the current list of all available adapters in the pipeline.",Mf,Re,Ha,Tf,Ps,Wh="Set the currently active adapters for use in the pipeline.",Df,Zo,Cf,we,ja,Sf,Hs,Xh=`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.`,kf,js,Fh=`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.`,Rf,Go,Af,Ae,Za,Uf,Zs,Jh=`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>.`,Vf,Bo,If,Ue,Ga,Wf,Gs,Ph="Unloads the LoRA parameters.",Xf,Eo,Ff,qo,Ba,Jf,Bs,Hh="Writes the state dict of the LoRA layers (optionally with metadata) to disk.",Hl,Ea,jl,X,qa,Pf,Es,jh=`Load LoRA layers into Stable Diffusion <a href="/docs/diffusers/pr_11986/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>.`,Hf,No,Na,jf,qs,Zh="This will load the LoRA layers specified in <code>state_dict</code> into <code>text_encoder</code>",Zf,zo,za,Gf,Ns,Gh="This will load the LoRA layers specified in <code>state_dict</code> into <code>unet</code>.",Bf,ae,Ya,Ef,zs,Bh=`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>.`,qf,Ys,Eh="All kwargs are forwarded to <code>self.lora_state_dict</code>.",Nf,Qs,qh=`See <a href="/docs/diffusers/pr_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is
loaded.`,zf,Os,Nh=`See <a href="/docs/diffusers/pr_11986/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>.`,Yf,Ks,zh=`See <a href="/docs/diffusers/pr_11986/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>.`,Qf,Ve,Qa,Of,ei,Yh="Return state dict for lora weights and the network alphas.",Kf,Yo,ep,Qo,Oa,op,oi,Qh="Save the LoRA parameters corresponding to the UNet and text encoder.",Zl,Ka,Gl,F,er,tp,ti,Oh=`Load LoRA layers into Stable Diffusion XL <a href="/docs/diffusers/pr_11986/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,Oo,or,rp,ai,Kh="This will load the LoRA layers specified in <code>state_dict</code> into <code>text_encoder</code>",np,Ko,tr,sp,ri,eg="This will load the LoRA layers specified in <code>state_dict</code> into <code>unet</code>.",ip,re,ar,dp,ni,og=`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>.`,lp,si,tg="All kwargs are forwarded to <code>self.lora_state_dict</code>.",cp,ii,ag=`See <a href="/docs/diffusers/pr_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is
loaded.`,fp,di,rg=`See <a href="/docs/diffusers/pr_11986/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>.`,pp,li,ng=`See <a href="/docs/diffusers/pr_11986/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>.`,mp,Ie,rr,_p,ci,sg="Return state dict for lora weights and the network alphas.",up,et,hp,ot,nr,gp,fi,ig="Save the LoRA parameters corresponding to the UNet and text encoder.",Bl,sr,El,V,ir,xp,pi,dg=`Load LoRA layers into <a href="/docs/diffusers/pr_11986/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>.`,Lp,mi,lg='Specific to <a href="/docs/diffusers/pr_11986/en/api/pipelines/stable_diffusion/stable_diffusion_3#diffusers.StableDiffusion3Pipeline">StableDiffusion3Pipeline</a>.',bp,tt,dr,wp,_i,cg="This will load the LoRA layers specified in <code>state_dict</code> into <code>text_encoder</code>",vp,at,lr,$p,ui,fg="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",yp,ie,cr,Mp,hi,pg=`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>.`,Tp,gi,mg="All kwargs are forwarded to <code>self.lora_state_dict</code>.",Dp,xi,_g=`See <a href="/docs/diffusers/pr_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is
loaded.`,Cp,Li,ug=`See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,Sp,We,fr,kp,bi,hg="Return state dict for lora weights and the network alphas.",Rp,rt,Ap,nt,pr,Up,wi,gg="Save the LoRA parameters corresponding to the UNet and text encoder.",Vp,Xe,mr,Ip,vi,xg=`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>.`,Wp,st,ql,_r,Nl,U,ur,Xp,$i,Lg=`Load LoRA layers into <a href="/docs/diffusers/pr_11986/en/api/models/flux_transformer#diffusers.FluxTransformer2DModel">FluxTransformer2DModel</a>,
<a href="https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel" rel="nofollow"><code>CLIPTextModel</code></a>.`,Fp,yi,bg='Specific to <a href="/docs/diffusers/pr_11986/en/api/pipelines/stable_diffusion/stable_diffusion_3#diffusers.StableDiffusion3Pipeline">StableDiffusion3Pipeline</a>.',Jp,it,hr,Pp,Mi,wg="This will load the LoRA layers specified in <code>state_dict</code> into <code>text_encoder</code>",Hp,dt,gr,jp,Ti,vg="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",Zp,de,xr,Gp,Di,$g=`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>.`,Bp,Ci,yg="All kwargs are forwarded to <code>self.lora_state_dict</code>.",Ep,Si,Mg=`See <a href="/docs/diffusers/pr_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is
loaded.`,qp,ki,Tg=`See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,Np,Fe,Lr,zp,Ri,Dg="Return state dict for lora weights and the network alphas.",Yp,lt,Qp,ct,br,Op,Ai,Cg="Save the LoRA parameters corresponding to the UNet and text encoder.",Kp,Je,wr,em,Ui,Sg=`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>.`,om,ft,tm,Pe,vr,am,Vi,kg="Unloads the LoRA parameters.",rm,pt,zl,$r,Yl,J,yr,nm,Ii,Rg='Load LoRA layers into <a href="/docs/diffusers/pr_11986/en/api/models/cogvideox_transformer3d#diffusers.CogVideoXTransformer3DModel">CogVideoXTransformer3DModel</a>. Specific to <a href="/docs/diffusers/pr_11986/en/api/pipelines/cogvideox#diffusers.CogVideoXPipeline">CogVideoXPipeline</a>.',sm,mt,Mr,im,Wi,Ag="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",dm,_t,Tr,lm,Xi,Ug=`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_11986/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>.`,cm,He,Dr,fm,Fi,Vg="Return state dict for lora weights and the network alphas.",pm,ut,mm,ht,Cr,_m,Ji,Ig="Save the LoRA parameters corresponding to the transformer.",um,je,Sr,hm,Pi,Wg=`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>.`,gm,gt,Ql,kr,Ol,P,Rr,xm,Hi,Xg='Load LoRA layers into <a href="/docs/diffusers/pr_11986/en/api/models/mochi_transformer3d#diffusers.MochiTransformer3DModel">MochiTransformer3DModel</a>. Specific to <a href="/docs/diffusers/pr_11986/en/api/pipelines/mochi#diffusers.MochiPipeline">MochiPipeline</a>.',Lm,xt,Ar,bm,ji,Fg="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",wm,Lt,Ur,vm,Zi,Jg=`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_11986/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>.`,$m,Ze,Vr,ym,Gi,Pg="Return state dict for lora weights and the network alphas.",Mm,bt,Tm,wt,Ir,Dm,Bi,Hg="Save the LoRA parameters corresponding to the transformer.",Cm,Ge,Wr,Sm,Ei,jg=`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,vt,Kl,Xr,ec,H,Fr,Rm,qi,Zg='Load LoRA layers into <a href="/docs/diffusers/pr_11986/en/api/models/aura_flow_transformer2d#diffusers.AuraFlowTransformer2DModel">AuraFlowTransformer2DModel</a> Specific to <a href="/docs/diffusers/pr_11986/en/api/pipelines/aura_flow#diffusers.AuraFlowPipeline">AuraFlowPipeline</a>.',Am,$t,Jr,Um,Ni,Gg="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",Vm,yt,Pr,Im,zi,Bg=`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_11986/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>.`,Wm,Be,Hr,Xm,Yi,Eg="Return state dict for lora weights and the network alphas.",Fm,Mt,Jm,Tt,jr,Pm,Qi,qg="Save the LoRA parameters corresponding to the transformer.",Hm,Ee,Zr,jm,Oi,Ng=`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>.`,Zm,Dt,oc,Gr,tc,j,Br,Gm,Ki,zg='Load LoRA layers into <a href="/docs/diffusers/pr_11986/en/api/models/ltx_video_transformer3d#diffusers.LTXVideoTransformer3DModel">LTXVideoTransformer3DModel</a>. Specific to <a href="/docs/diffusers/pr_11986/en/api/pipelines/ltx_video#diffusers.LTXPipeline">LTXPipeline</a>.',Bm,Ct,Er,Em,ed,Yg="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",qm,St,qr,Nm,od,Qg=`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_11986/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>.`,zm,qe,Nr,Ym,td,Og="Return state dict for lora weights and the network alphas.",Qm,kt,Om,Rt,zr,Km,ad,Kg="Save the LoRA parameters corresponding to the transformer.",e_,Ne,Yr,o_,rd,ex=`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>.`,t_,At,ac,Qr,rc,Z,Or,a_,nd,ox='Load LoRA layers into <a href="/docs/diffusers/pr_11986/en/api/models/sana_transformer2d#diffusers.SanaTransformer2DModel">SanaTransformer2DModel</a>. Specific to <a href="/docs/diffusers/pr_11986/en/api/pipelines/sana#diffusers.SanaPipeline">SanaPipeline</a>.',r_,Ut,Kr,n_,sd,tx="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",s_,Vt,en,i_,id,ax=`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_11986/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>.`,d_,ze,on,l_,dd,rx="Return state dict for lora weights and the network alphas.",c_,It,f_,Wt,tn,p_,ld,nx="Save the LoRA parameters corresponding to the transformer.",m_,Ye,an,__,cd,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>.`,u_,Xt,nc,rn,sc,G,nn,h_,fd,ix='Load LoRA layers into <a href="/docs/diffusers/pr_11986/en/api/models/hunyuan_video_transformer_3d#diffusers.HunyuanVideoTransformer3DModel">HunyuanVideoTransformer3DModel</a>. Specific to <a href="/docs/diffusers/pr_11986/en/api/pipelines/hunyuan_video#diffusers.HunyuanVideoPipeline">HunyuanVideoPipeline</a>.',g_,Ft,sn,x_,pd,dx="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",L_,Jt,dn,b_,md,lx=`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_11986/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>.`,w_,Qe,ln,v_,_d,cx="Return state dict for lora weights and the network alphas.",$_,Pt,y_,Ht,cn,M_,ud,fx="Save the LoRA parameters corresponding to the transformer.",T_,Oe,fn,D_,hd,px=`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>.`,C_,jt,ic,pn,dc,B,mn,S_,gd,mx='Load LoRA layers into <a href="/docs/diffusers/pr_11986/en/api/models/lumina2_transformer2d#diffusers.Lumina2Transformer2DModel">Lumina2Transformer2DModel</a>. Specific to <code>Lumina2Text2ImgPipeline</code>.',k_,Zt,_n,R_,xd,_x="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",A_,Gt,un,U_,Ld,ux=`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_11986/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>.`,V_,Ke,hn,I_,bd,hx="Return state dict for lora weights and the network alphas.",W_,Bt,X_,Et,gn,F_,wd,gx="Save the LoRA parameters corresponding to the transformer.",J_,eo,xn,P_,vd,xx=`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>.`,H_,qt,lc,Ln,cc,E,bn,j_,$d,Lx='Load LoRA layers into <a href="/docs/diffusers/pr_11986/en/api/models/wan_transformer_3d#diffusers.WanTransformer3DModel">WanTransformer3DModel</a>. Specific to <a href="/docs/diffusers/pr_11986/en/api/pipelines/cogview4#diffusers.CogView4Pipeline">CogView4Pipeline</a>.',Z_,Nt,wn,G_,yd,bx="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",B_,zt,vn,E_,Md,wx=`Load LoRA weights specified in <code>pretrained_model_name_or_path_or_dict</code> into <code>self.transformer</code> and
<code>self.text_encoder</code>. All kwargs are forwarded to <code>self.lora_state_dict</code>. See
<a href="/docs/diffusers/pr_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is loaded.
See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,q_,oo,$n,N_,Td,vx="Return state dict for lora weights and the network alphas.",z_,Yt,Y_,Qt,yn,Q_,Dd,$x="Save the LoRA parameters corresponding to the transformer.",O_,to,Mn,K_,Cd,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>.`,eu,Ot,fc,Tn,pc,q,Dn,ou,Sd,Mx='Load LoRA layers into <a href="/docs/diffusers/pr_11986/en/api/models/wan_transformer_3d#diffusers.WanTransformer3DModel">WanTransformer3DModel</a>. Specific to <a href="/docs/diffusers/pr_11986/en/api/pipelines/wan#diffusers.WanPipeline">WanPipeline</a> and <code>[WanImageToVideoPipeline</code>].',tu,Kt,Cn,au,kd,Tx="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",ru,ea,Sn,nu,Rd,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_11986/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>.`,su,ao,kn,iu,Ad,Cx="Return state dict for lora weights and the network alphas.",du,oa,lu,ta,Rn,cu,Ud,Sx="Save the LoRA parameters corresponding to the transformer.",fu,ro,An,pu,Vd,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>.`,mu,aa,mc,Un,_c,N,Vn,_u,Id,Rx='Load LoRA layers into <a href="/docs/diffusers/pr_11986/en/api/models/skyreels_v2_transformer_3d#diffusers.SkyReelsV2Transformer3DModel">SkyReelsV2Transformer3DModel</a>.',uu,ra,In,hu,Wd,Ax="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",gu,na,Wn,xu,Xd,Ux=`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_11986/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,no,Xn,bu,Fd,Vx="Return state dict for lora weights and the network alphas.",wu,sa,vu,ia,Fn,$u,Jd,Ix="Save the LoRA parameters corresponding to the transformer.",yu,so,Jn,Mu,Pd,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>.`,Tu,da,uc,Pn,hc,ye,Hn,Du,la,jn,Cu,Hd,Xx="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",Su,ca,Zn,ku,jd,Fx="Save the LoRA parameters corresponding to the UNet and text encoder.",gc,Gn,xc,z,Bn,Ru,Zd,Jx='Load LoRA layers into <a href="/docs/diffusers/pr_11986/en/api/models/hidream_image_transformer#diffusers.HiDreamImageTransformer2DModel">HiDreamImageTransformer2DModel</a>. Specific to <a href="/docs/diffusers/pr_11986/en/api/pipelines/hidream#diffusers.HiDreamImagePipeline">HiDreamImagePipeline</a>.',Au,fa,En,Uu,Gd,Px="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",Vu,pa,qn,Iu,Bd,Hx=`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_11986/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>.`,Wu,io,Nn,Xu,Ed,jx="Return state dict for lora weights and the network alphas.",Fu,ma,Ju,_a,zn,Pu,qd,Zx="Save the LoRA parameters corresponding to the transformer.",Hu,lo,Yn,ju,Nd,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>.`,Zu,ua,Lc,Qn,bc,S,On,Gu,zd,Bx="Utility class for handling LoRAs.",Bu,co,Kn,Eu,Yd,Ex="Delete an adapter’s LoRA layers from the pipeline.",qu,ha,Nu,fo,es,zu,Qd,qx="Disables the active LoRA layers of the pipeline.",Yu,ga,Qu,po,os,Ou,Od,Nx="Enables the active LoRA layers of the pipeline.",Ku,xa,eh,La,ts,oh,Kd,zx=`Hotswap adapters without triggering recompilation of a model or if the ranks of the loaded adapters are
different.`,th,ve,as,ah,el,Yx="Fuses the LoRA parameters into the original parameters of the corresponding blocks.",rh,ba,nh,wa,sh,mo,rs,ih,ol,Qx="Gets the list of the current active adapters.",dh,va,lh,$a,ns,ch,tl,Ox="Gets the current list of all available adapters in the pipeline.",fh,_o,ss,ph,al,Kx="Set the currently active adapters for use in the pipeline.",mh,ya,_h,$e,is,uh,rl,eL=`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.`,hh,nl,oL=`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.`,gh,Ma,xh,uo,ds,Lh,sl,tL=`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>.`,bh,Ta,wh,ho,ls,vh,il,aL="Unloads the LoRA parameters.",$h,Da,yh,Ca,cs,Mh,dl,rL="Writes the state dict of the LoRA layers (optionally with metadata) to disk.",wc,fs,vc,Wl,$c;return w=new Y({props:{title:"LoRA",local:"lora",headingTag:"h1"}}),Vo=new k({props:{$$slots:{default:[fL]},$$scope:{ctx:T}}}),Aa=new Y({props:{title:"LoraBaseMixin",local:"diffusers.loaders.lora_base.LoraBaseMixin",headingTag:"h2"}}),Ua=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_11986/src/diffusers/loaders/lora_base.py#L478"}}),Va=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_11986/src/diffusers/loaders/lora_base.py#L842"}}),Io=new oe({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.delete_adapters.example",$$slots:{default:[pL]},$$scope:{ctx:T}}}),Ia=new M({props:{name:"disable_lora",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.disable_lora",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_base.py#L782"}}),Wo=new oe({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.disable_lora.example",$$slots:{default:[mL]},$$scope:{ctx:T}}}),Wa=new M({props:{name:"enable_lora",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.enable_lora",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_base.py#L812"}}),Xo=new oe({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.enable_lora.example",$$slots:{default:[_L]},$$scope:{ctx:T}}}),Xa=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_11986/src/diffusers/loaders/lora_base.py#L989"}}),Fa=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_11986/src/diffusers/loaders/lora_base.py#L536"}}),Jo=new k({props:{warning:!0,$$slots:{default:[uL]},$$scope:{ctx:T}}}),Po=new oe({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.fuse_lora.example",$$slots:{default:[hL]},$$scope:{ctx:T}}}),Ja=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_11986/src/diffusers/loaders/lora_base.py#L880"}}),Ho=new oe({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.get_active_adapters.example",$$slots:{default:[gL]},$$scope:{ctx:T}}}),Pa=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_11986/src/diffusers/loaders/lora_base.py#L913"}}),Ha=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_11986/src/diffusers/loaders/lora_base.py#L683"}}),Zo=new oe({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_adapters.example",$$slots:{default:[xL]},$$scope:{ctx:T}}}),ja=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_11986/src/diffusers/loaders/lora_base.py#L935"}}),Go=new oe({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_lora_device.example",$$slots:{default:[LL]},$$scope:{ctx:T}}}),Za=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_11986/src/diffusers/loaders/lora_base.py#L626"}}),Bo=new k({props:{warning:!0,$$slots:{default:[bL]},$$scope:{ctx:T}}}),Ga=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_11986/src/diffusers/loaders/lora_base.py#L513"}}),Eo=new oe({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.unload_lora_weights.example",$$slots:{default:[wL]},$$scope:{ctx:T}}}),Ba=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_11986/src/diffusers/loaders/lora_base.py#L1012"}}),Ea=new Y({props:{title:"StableDiffusionLoraLoaderMixin",local:"diffusers.loaders.StableDiffusionLoraLoaderMixin",headingTag:"h2"}}),qa=new M({props:{name:"class diffusers.loaders.StableDiffusionLoraLoaderMixin",anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L127"}}),Na=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L415"}}),za=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L354"}}),Ya=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L137"}}),Qa=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L238"}}),Yo=new k({props:{warning:!0,$$slots:{default:[vL]},$$scope:{ctx:T}}}),Oa=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_11986/src/diffusers/loaders/lora_pipeline.py#L473"}}),Ka=new Y({props:{title:"StableDiffusionXLLoraLoaderMixin",local:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin",headingTag:"h2"}}),er=new M({props:{name:"class diffusers.loaders.StableDiffusionXLLoraLoaderMixin",anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L611"}}),or=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L901"}}),tr=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L839"}}),ar=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_11986/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_11986/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_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L622"}}),rr=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L722"}}),et=new k({props:{warning:!0,$$slots:{default:[$L]},$$scope:{ctx:T}}}),nr=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_11986/src/diffusers/loaders/lora_pipeline.py#L960"}}),sr=new Y({props:{title:"SD3LoraLoaderMixin",local:"diffusers.loaders.SD3LoraLoaderMixin",headingTag:"h2"}}),ir=new M({props:{name:"class diffusers.loaders.SD3LoraLoaderMixin",anchor:"diffusers.loaders.SD3LoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L1114"}}),dr=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L1363"}}),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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L1313"}}),cr=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_11986/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_11986/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_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L1225"}}),fr=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L1127"}}),rt=new k({props:{warning:!0,$$slots:{default:[yL]},$$scope:{ctx:T}}}),pr=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_11986/src/diffusers/loaders/lora_pipeline.py#L1422"}}),mr=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_11986/src/diffusers/loaders/lora_pipeline.py#L1560"}}),st=new k({props:{warning:!0,$$slots:{default:[ML]},$$scope:{ctx:T}}}),_r=new Y({props:{title:"FluxLoraLoaderMixin",local:"diffusers.loaders.FluxLoraLoaderMixin",headingTag:"h2"}}),ur=new M({props:{name:"class diffusers.loaders.FluxLoraLoaderMixin",anchor:"diffusers.loaders.FluxLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L1923"}}),hr=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L2338"}}),gr=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L2229"}}),xr=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_11986/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_11986/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_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L2104"}}),Lr=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L1936"}}),lt=new k({props:{warning:!0,$$slots:{default:[TL]},$$scope:{ctx:T}}}),br=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_11986/src/diffusers/loaders/lora_pipeline.py#L2397"}}),wr=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_11986/src/diffusers/loaders/lora_pipeline.py#L2530"}}),ft=new k({props:{warning:!0,$$slots:{default:[DL]},$$scope:{ctx:T}}}),vr=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_11986/src/diffusers/loaders/lora_pipeline.py#L2551"}}),pt=new oe({props:{anchor:"diffusers.loaders.FluxLoraLoaderMixin.unload_lora_weights.example",$$slots:{default:[CL]},$$scope:{ctx:T}}}),$r=new Y({props:{title:"CogVideoXLoraLoaderMixin",local:"diffusers.loaders.CogVideoXLoraLoaderMixin",headingTag:"h2"}}),yr=new M({props:{name:"class diffusers.loaders.CogVideoXLoraLoaderMixin",anchor:"diffusers.loaders.CogVideoXLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L3006"}}),Mr=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L3172"}}),Tr=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_11986/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_11986/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_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L3113"}}),Dr=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L3014"}}),ut=new k({props:{warning:!0,$$slots:{default:[SL]},$$scope:{ctx:T}}}),Cr=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_11986/src/diffusers/loaders/lora_pipeline.py#L3223"}}),Sr=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_11986/src/diffusers/loaders/lora_pipeline.py#L3327"}}),gt=new k({props:{warning:!0,$$slots:{default:[kL]},$$scope:{ctx:T}}}),kr=new Y({props:{title:"Mochi1LoraLoaderMixin",local:"diffusers.loaders.Mochi1LoraLoaderMixin",headingTag:"h2"}}),Rr=new M({props:{name:"class diffusers.loaders.Mochi1LoraLoaderMixin",anchor:"diffusers.loaders.Mochi1LoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L3345"}}),Ar=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L3512"}}),Ur=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_11986/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_11986/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_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L3453"}}),Vr=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L3353"}}),bt=new k({props:{warning:!0,$$slots:{default:[RL]},$$scope:{ctx:T}}}),Ir=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_11986/src/diffusers/loaders/lora_pipeline.py#L3563"}}),Wr=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_11986/src/diffusers/loaders/lora_pipeline.py#L3669"}}),vt=new k({props:{warning:!0,$$slots:{default:[AL]},$$scope:{ctx:T}}}),Xr=new Y({props:{title:"AuraFlowLoraLoaderMixin",local:"diffusers.loaders.AuraFlowLoraLoaderMixin",headingTag:"h2"}}),Fr=new M({props:{name:"class diffusers.loaders.AuraFlowLoraLoaderMixin",anchor:"diffusers.loaders.AuraFlowLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L1581"}}),Jr=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L1748"}}),Pr=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_11986/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_11986/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_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L1689"}}),Hr=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L1589"}}),Mt=new k({props:{warning:!0,$$slots:{default:[UL]},$$scope:{ctx:T}}}),jr=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_11986/src/diffusers/loaders/lora_pipeline.py#L1799"}}),Zr=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_11986/src/diffusers/loaders/lora_pipeline.py#L1905"}}),Dt=new k({props:{warning:!0,$$slots:{default:[VL]},$$scope:{ctx:T}}}),Gr=new Y({props:{title:"LTXVideoLoraLoaderMixin",local:"diffusers.loaders.LTXVideoLoraLoaderMixin",headingTag:"h2"}}),Br=new M({props:{name:"class diffusers.loaders.LTXVideoLoraLoaderMixin",anchor:"diffusers.loaders.LTXVideoLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L3687"}}),Er=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L3856"}}),qr=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_11986/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_11986/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_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L3797"}}),Nr=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L3695"}}),kt=new k({props:{warning:!0,$$slots:{default:[IL]},$$scope:{ctx:T}}}),zr=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_11986/src/diffusers/loaders/lora_pipeline.py#L3907"}}),Yr=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_11986/src/diffusers/loaders/lora_pipeline.py#L4013"}}),At=new k({props:{warning:!0,$$slots:{default:[WL]},$$scope:{ctx:T}}}),Qr=new Y({props:{title:"SanaLoraLoaderMixin",local:"diffusers.loaders.SanaLoraLoaderMixin",headingTag:"h2"}}),Or=new M({props:{name:"class diffusers.loaders.SanaLoraLoaderMixin",anchor:"diffusers.loaders.SanaLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L4031"}}),Kr=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L4198"}}),en=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_11986/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_11986/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_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L4139"}}),on=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L4039"}}),It=new k({props:{warning:!0,$$slots:{default:[XL]},$$scope:{ctx:T}}}),tn=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_11986/src/diffusers/loaders/lora_pipeline.py#L4249"}}),an=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_11986/src/diffusers/loaders/lora_pipeline.py#L4355"}}),Xt=new k({props:{warning:!0,$$slots:{default:[FL]},$$scope:{ctx:T}}}),rn=new Y({props:{title:"HunyuanVideoLoraLoaderMixin",local:"diffusers.loaders.HunyuanVideoLoraLoaderMixin",headingTag:"h2"}}),nn=new M({props:{name:"class diffusers.loaders.HunyuanVideoLoraLoaderMixin",anchor:"diffusers.loaders.HunyuanVideoLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L4373"}}),sn=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L4542"}}),dn=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_11986/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_11986/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_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L4483"}}),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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L4381"}}),Pt=new k({props:{warning:!0,$$slots:{default:[JL]},$$scope:{ctx:T}}}),cn=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_11986/src/diffusers/loaders/lora_pipeline.py#L4593"}}),fn=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_11986/src/diffusers/loaders/lora_pipeline.py#L4699"}}),jt=new k({props:{warning:!0,$$slots:{default:[PL]},$$scope:{ctx:T}}}),pn=new Y({props:{title:"Lumina2LoraLoaderMixin",local:"diffusers.loaders.Lumina2LoraLoaderMixin",headingTag:"h2"}}),mn=new M({props:{name:"class diffusers.loaders.Lumina2LoraLoaderMixin",anchor:"diffusers.loaders.Lumina2LoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L4717"}}),_n=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L4887"}}),un=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_11986/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_11986/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_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L4828"}}),hn=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L4725"}}),Bt=new k({props:{warning:!0,$$slots:{default:[HL]},$$scope:{ctx:T}}}),gn=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_11986/src/diffusers/loaders/lora_pipeline.py#L4938"}}),xn=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_11986/src/diffusers/loaders/lora_pipeline.py#L5044"}}),qt=new k({props:{warning:!0,$$slots:{default:[jL]},$$scope:{ctx:T}}}),Ln=new Y({props:{title:"CogView4LoraLoaderMixin",local:"diffusers.loaders.CogView4LoraLoaderMixin",headingTag:"h2"}}),bn=new M({props:{name:"class diffusers.loaders.CogView4LoraLoaderMixin",anchor:"diffusers.loaders.CogView4LoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L5855"}}),wn=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L6022"}}),vn=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_11986/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_11986/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_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L5963"}}),$n=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L5863"}}),Yt=new k({props:{warning:!0,$$slots:{default:[ZL]},$$scope:{ctx:T}}}),yn=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_11986/src/diffusers/loaders/lora_pipeline.py#L6073"}}),Mn=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_11986/src/diffusers/loaders/lora_pipeline.py#L6179"}}),Ot=new k({props:{warning:!0,$$slots:{default:[GL]},$$scope:{ctx:T}}}),Tn=new Y({props:{title:"WanLoraLoaderMixin",local:"diffusers.loaders.WanLoraLoaderMixin",headingTag:"h2"}}),Dn=new M({props:{name:"class diffusers.loaders.WanLoraLoaderMixin",anchor:"diffusers.loaders.WanLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L5062"}}),Cn=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L5282"}}),Sn=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_11986/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_11986/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_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L5219"}}),kn=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L5070"}}),oa=new k({props:{warning:!0,$$slots:{default:[BL]},$$scope:{ctx:T}}}),Rn=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_11986/src/diffusers/loaders/lora_pipeline.py#L5333"}}),An=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_11986/src/diffusers/loaders/lora_pipeline.py#L5439"}}),aa=new k({props:{warning:!0,$$slots:{default:[EL]},$$scope:{ctx:T}}}),Un=new Y({props:{title:"SkyReelsV2LoraLoaderMixin",local:"diffusers.loaders.SkyReelsV2LoraLoaderMixin",headingTag:"h2"}}),Vn=new M({props:{name:"class diffusers.loaders.SkyReelsV2LoraLoaderMixin",anchor:"diffusers.loaders.SkyReelsV2LoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L5457"}}),In=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L5680"}}),Wn=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_11986/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_11986/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_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L5617"}}),Xn=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L5465"}}),sa=new k({props:{warning:!0,$$slots:{default:[qL]},$$scope:{ctx:T}}}),Fn=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_11986/src/diffusers/loaders/lora_pipeline.py#L5731"}}),Jn=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_11986/src/diffusers/loaders/lora_pipeline.py#L5837"}}),da=new k({props:{warning:!0,$$slots:{default:[NL]},$$scope:{ctx:T}}}),Pn=new Y({props:{title:"AmusedLoraLoaderMixin",local:"diffusers.loaders.AmusedLoraLoaderMixin",headingTag:"h2"}}),Hn=new M({props:{name:"class diffusers.loaders.AmusedLoraLoaderMixin",anchor:"diffusers.loaders.AmusedLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L2831"}}),jn=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L2836"}}),Zn=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_11986/src/diffusers/loaders/lora_pipeline.py#L2951"}}),Gn=new Y({props:{title:"HiDreamImageLoraLoaderMixin",local:"diffusers.loaders.HiDreamImageLoraLoaderMixin",headingTag:"h2"}}),Bn=new M({props:{name:"class diffusers.loaders.HiDreamImageLoraLoaderMixin",anchor:"diffusers.loaders.HiDreamImageLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L6197"}}),En=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L6366"}}),qn=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_11986/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_11986/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_11986/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_pipeline.py#L6307"}}),Nn=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_11986/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_11986/src/diffusers/loaders/lora_pipeline.py#L6205"}}),ma=new k({props:{warning:!0,$$slots:{default:[zL]},$$scope:{ctx:T}}}),zn=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_11986/src/diffusers/loaders/lora_pipeline.py#L6417"}}),Yn=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_11986/src/diffusers/loaders/lora_pipeline.py#L6523"}}),ua=new k({props:{warning:!0,$$slots:{default:[YL]},$$scope:{ctx:T}}}),Qn=new Y({props:{title:"LoraBaseMixin",local:"diffusers.loaders.lora_base.LoraBaseMixin",headingTag:"h2"}}),On=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_11986/src/diffusers/loaders/lora_base.py#L478"}}),Kn=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_11986/src/diffusers/loaders/lora_base.py#L842"}}),ha=new oe({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.delete_adapters.example",$$slots:{default:[QL]},$$scope:{ctx:T}}}),es=new M({props:{name:"disable_lora",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.disable_lora",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_base.py#L782"}}),ga=new oe({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.disable_lora.example",$$slots:{default:[OL]},$$scope:{ctx:T}}}),os=new M({props:{name:"enable_lora",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.enable_lora",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_11986/src/diffusers/loaders/lora_base.py#L812"}}),xa=new oe({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.enable_lora.example",$$slots:{default:[KL]},$$scope:{ctx:T}}}),ts=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_11986/src/diffusers/loaders/lora_base.py#L989"}}),as=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_11986/src/diffusers/loaders/lora_base.py#L536"}}),ba=new k({props:{warning:!0,$$slots:{default:[eb]},$$scope:{ctx:T}}}),wa=new oe({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.fuse_lora.example",$$slots:{default:[ob]},$$scope:{ctx:T}}}),rs=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_11986/src/diffusers/loaders/lora_base.py#L880"}}),va=new oe({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.get_active_adapters.example",$$slots:{default:[tb]},$$scope:{ctx:T}}}),ns=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_11986/src/diffusers/loaders/lora_base.py#L913"}}),ss=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_11986/src/diffusers/loaders/lora_base.py#L683"}}),ya=new oe({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_adapters.example",$$slots:{default:[ab]},$$scope:{ctx:T}}}),is=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_11986/src/diffusers/loaders/lora_base.py#L935"}}),Ma=new oe({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.set_lora_device.example",$$slots:{default:[rb]},$$scope:{ctx:T}}}),ds=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_11986/src/diffusers/loaders/lora_base.py#L626"}}),Ta=new k({props:{warning:!0,$$slots:{default:[nb]},$$scope:{ctx:T}}}),ls=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_11986/src/diffusers/loaders/lora_base.py#L513"}}),Da=new oe({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.unload_lora_weights.example",$$slots:{default:[sb]},$$scope:{ctx:T}}}),cs=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_11986/src/diffusers/loaders/lora_base.py#L1012"}}),fs=new cL({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/loaders/lora.md"}}),{c(){t=s("meta"),L=r(),c=s("p"),d=r(),f(w.$$.fragment),a=r(),v=s("p"),v.innerHTML=Th,Xl=r(),Ra=s("ul"),Ra.innerHTML=Dh,Fl=r(),f(Vo.$$.fragment),Jl=r(),f(Aa.$$.fragment),Pl=r(),C=s("div"),f(Ua.$$.fragment),af=r(),As=s("p"),As.textContent=Ch,rf=r(),De=s("div"),f(Va.$$.fragment),nf=r(),Us=s("p"),Us.textContent=Sh,sf=r(),f(Io.$$.fragment),df=r(),Ce=s("div"),f(Ia.$$.fragment),lf=r(),Vs=s("p"),Vs.textContent=kh,cf=r(),f(Wo.$$.fragment),ff=r(),Se=s("div"),f(Wa.$$.fragment),pf=r(),Is=s("p"),Is.textContent=Rh,mf=r(),f(Xo.$$.fragment),_f=r(),Fo=s("div"),f(Xa.$$.fragment),uf=r(),Ws=s("p"),Ws.textContent=Ah,hf=r(),be=s("div"),f(Fa.$$.fragment),gf=r(),Xs=s("p"),Xs.textContent=Uh,xf=r(),f(Jo.$$.fragment),Lf=r(),f(Po.$$.fragment),bf=r(),ke=s("div"),f(Ja.$$.fragment),wf=r(),Fs=s("p"),Fs.textContent=Vh,vf=r(),f(Ho.$$.fragment),$f=r(),jo=s("div"),f(Pa.$$.fragment),yf=r(),Js=s("p"),Js.textContent=Ih,Mf=r(),Re=s("div"),f(Ha.$$.fragment),Tf=r(),Ps=s("p"),Ps.textContent=Wh,Df=r(),f(Zo.$$.fragment),Cf=r(),we=s("div"),f(ja.$$.fragment),Sf=r(),Hs=s("p"),Hs.innerHTML=Xh,kf=r(),js=s("p"),js.textContent=Fh,Rf=r(),f(Go.$$.fragment),Af=r(),Ae=s("div"),f(Za.$$.fragment),Uf=r(),Zs=s("p"),Zs.innerHTML=Jh,Vf=r(),f(Bo.$$.fragment),If=r(),Ue=s("div"),f(Ga.$$.fragment),Wf=r(),Gs=s("p"),Gs.textContent=Ph,Xf=r(),f(Eo.$$.fragment),Ff=r(),qo=s("div"),f(Ba.$$.fragment),Jf=r(),Bs=s("p"),Bs.textContent=Hh,Hl=r(),f(Ea.$$.fragment),jl=r(),X=s("div"),f(qa.$$.fragment),Pf=r(),Es=s("p"),Es.innerHTML=jh,Hf=r(),No=s("div"),f(Na.$$.fragment),jf=r(),qs=s("p"),qs.innerHTML=Zh,Zf=r(),zo=s("div"),f(za.$$.fragment),Gf=r(),Ns=s("p"),Ns.innerHTML=Gh,Bf=r(),ae=s("div"),f(Ya.$$.fragment),Ef=r(),zs=s("p"),zs.innerHTML=Bh,qf=r(),Ys=s("p"),Ys.innerHTML=Eh,Nf=r(),Qs=s("p"),Qs.innerHTML=qh,zf=r(),Os=s("p"),Os.innerHTML=Nh,Yf=r(),Ks=s("p"),Ks.innerHTML=zh,Qf=r(),Ve=s("div"),f(Qa.$$.fragment),Of=r(),ei=s("p"),ei.textContent=Yh,Kf=r(),f(Yo.$$.fragment),ep=r(),Qo=s("div"),f(Oa.$$.fragment),op=r(),oi=s("p"),oi.textContent=Qh,Zl=r(),f(Ka.$$.fragment),Gl=r(),F=s("div"),f(er.$$.fragment),tp=r(),ti=s("p"),ti.innerHTML=Oh,ap=r(),Oo=s("div"),f(or.$$.fragment),rp=r(),ai=s("p"),ai.innerHTML=Kh,np=r(),Ko=s("div"),f(tr.$$.fragment),sp=r(),ri=s("p"),ri.innerHTML=eg,ip=r(),re=s("div"),f(ar.$$.fragment),dp=r(),ni=s("p"),ni.innerHTML=og,lp=r(),si=s("p"),si.innerHTML=tg,cp=r(),ii=s("p"),ii.innerHTML=ag,fp=r(),di=s("p"),di.innerHTML=rg,pp=r(),li=s("p"),li.innerHTML=ng,mp=r(),Ie=s("div"),f(rr.$$.fragment),_p=r(),ci=s("p"),ci.textContent=sg,up=r(),f(et.$$.fragment),hp=r(),ot=s("div"),f(nr.$$.fragment),gp=r(),fi=s("p"),fi.textContent=ig,Bl=r(),f(sr.$$.fragment),El=r(),V=s("div"),f(ir.$$.fragment),xp=r(),pi=s("p"),pi.innerHTML=dg,Lp=r(),mi=s("p"),mi.innerHTML=lg,bp=r(),tt=s("div"),f(dr.$$.fragment),wp=r(),_i=s("p"),_i.innerHTML=cg,vp=r(),at=s("div"),f(lr.$$.fragment),$p=r(),ui=s("p"),ui.innerHTML=fg,yp=r(),ie=s("div"),f(cr.$$.fragment),Mp=r(),hi=s("p"),hi.innerHTML=pg,Tp=r(),gi=s("p"),gi.innerHTML=mg,Dp=r(),xi=s("p"),xi.innerHTML=_g,Cp=r(),Li=s("p"),Li.innerHTML=ug,Sp=r(),We=s("div"),f(fr.$$.fragment),kp=r(),bi=s("p"),bi.textContent=hg,Rp=r(),f(rt.$$.fragment),Ap=r(),nt=s("div"),f(pr.$$.fragment),Up=r(),wi=s("p"),wi.textContent=gg,Vp=r(),Xe=s("div"),f(mr.$$.fragment),Ip=r(),vi=s("p"),vi.innerHTML=xg,Wp=r(),f(st.$$.fragment),ql=r(),f(_r.$$.fragment),Nl=r(),U=s("div"),f(ur.$$.fragment),Xp=r(),$i=s("p"),$i.innerHTML=Lg,Fp=r(),yi=s("p"),yi.innerHTML=bg,Jp=r(),it=s("div"),f(hr.$$.fragment),Pp=r(),Mi=s("p"),Mi.innerHTML=wg,Hp=r(),dt=s("div"),f(gr.$$.fragment),jp=r(),Ti=s("p"),Ti.innerHTML=vg,Zp=r(),de=s("div"),f(xr.$$.fragment),Gp=r(),Di=s("p"),Di.innerHTML=$g,Bp=r(),Ci=s("p"),Ci.innerHTML=yg,Ep=r(),Si=s("p"),Si.innerHTML=Mg,qp=r(),ki=s("p"),ki.innerHTML=Tg,Np=r(),Fe=s("div"),f(Lr.$$.fragment),zp=r(),Ri=s("p"),Ri.textContent=Dg,Yp=r(),f(lt.$$.fragment),Qp=r(),ct=s("div"),f(br.$$.fragment),Op=r(),Ai=s("p"),Ai.textContent=Cg,Kp=r(),Je=s("div"),f(wr.$$.fragment),em=r(),Ui=s("p"),Ui.innerHTML=Sg,om=r(),f(ft.$$.fragment),tm=r(),Pe=s("div"),f(vr.$$.fragment),am=r(),Vi=s("p"),Vi.textContent=kg,rm=r(),f(pt.$$.fragment),zl=r(),f($r.$$.fragment),Yl=r(),J=s("div"),f(yr.$$.fragment),nm=r(),Ii=s("p"),Ii.innerHTML=Rg,sm=r(),mt=s("div"),f(Mr.$$.fragment),im=r(),Wi=s("p"),Wi.innerHTML=Ag,dm=r(),_t=s("div"),f(Tr.$$.fragment),lm=r(),Xi=s("p"),Xi.innerHTML=Ug,cm=r(),He=s("div"),f(Dr.$$.fragment),fm=r(),Fi=s("p"),Fi.textContent=Vg,pm=r(),f(ut.$$.fragment),mm=r(),ht=s("div"),f(Cr.$$.fragment),_m=r(),Ji=s("p"),Ji.textContent=Ig,um=r(),je=s("div"),f(Sr.$$.fragment),hm=r(),Pi=s("p"),Pi.innerHTML=Wg,gm=r(),f(gt.$$.fragment),Ql=r(),f(kr.$$.fragment),Ol=r(),P=s("div"),f(Rr.$$.fragment),xm=r(),Hi=s("p"),Hi.innerHTML=Xg,Lm=r(),xt=s("div"),f(Ar.$$.fragment),bm=r(),ji=s("p"),ji.innerHTML=Fg,wm=r(),Lt=s("div"),f(Ur.$$.fragment),vm=r(),Zi=s("p"),Zi.innerHTML=Jg,$m=r(),Ze=s("div"),f(Vr.$$.fragment),ym=r(),Gi=s("p"),Gi.textContent=Pg,Mm=r(),f(bt.$$.fragment),Tm=r(),wt=s("div"),f(Ir.$$.fragment),Dm=r(),Bi=s("p"),Bi.textContent=Hg,Cm=r(),Ge=s("div"),f(Wr.$$.fragment),Sm=r(),Ei=s("p"),Ei.innerHTML=jg,km=r(),f(vt.$$.fragment),Kl=r(),f(Xr.$$.fragment),ec=r(),H=s("div"),f(Fr.$$.fragment),Rm=r(),qi=s("p"),qi.innerHTML=Zg,Am=r(),$t=s("div"),f(Jr.$$.fragment),Um=r(),Ni=s("p"),Ni.innerHTML=Gg,Vm=r(),yt=s("div"),f(Pr.$$.fragment),Im=r(),zi=s("p"),zi.innerHTML=Bg,Wm=r(),Be=s("div"),f(Hr.$$.fragment),Xm=r(),Yi=s("p"),Yi.textContent=Eg,Fm=r(),f(Mt.$$.fragment),Jm=r(),Tt=s("div"),f(jr.$$.fragment),Pm=r(),Qi=s("p"),Qi.textContent=qg,Hm=r(),Ee=s("div"),f(Zr.$$.fragment),jm=r(),Oi=s("p"),Oi.innerHTML=Ng,Zm=r(),f(Dt.$$.fragment),oc=r(),f(Gr.$$.fragment),tc=r(),j=s("div"),f(Br.$$.fragment),Gm=r(),Ki=s("p"),Ki.innerHTML=zg,Bm=r(),Ct=s("div"),f(Er.$$.fragment),Em=r(),ed=s("p"),ed.innerHTML=Yg,qm=r(),St=s("div"),f(qr.$$.fragment),Nm=r(),od=s("p"),od.innerHTML=Qg,zm=r(),qe=s("div"),f(Nr.$$.fragment),Ym=r(),td=s("p"),td.textContent=Og,Qm=r(),f(kt.$$.fragment),Om=r(),Rt=s("div"),f(zr.$$.fragment),Km=r(),ad=s("p"),ad.textContent=Kg,e_=r(),Ne=s("div"),f(Yr.$$.fragment),o_=r(),rd=s("p"),rd.innerHTML=ex,t_=r(),f(At.$$.fragment),ac=r(),f(Qr.$$.fragment),rc=r(),Z=s("div"),f(Or.$$.fragment),a_=r(),nd=s("p"),nd.innerHTML=ox,r_=r(),Ut=s("div"),f(Kr.$$.fragment),n_=r(),sd=s("p"),sd.innerHTML=tx,s_=r(),Vt=s("div"),f(en.$$.fragment),i_=r(),id=s("p"),id.innerHTML=ax,d_=r(),ze=s("div"),f(on.$$.fragment),l_=r(),dd=s("p"),dd.textContent=rx,c_=r(),f(It.$$.fragment),f_=r(),Wt=s("div"),f(tn.$$.fragment),p_=r(),ld=s("p"),ld.textContent=nx,m_=r(),Ye=s("div"),f(an.$$.fragment),__=r(),cd=s("p"),cd.innerHTML=sx,u_=r(),f(Xt.$$.fragment),nc=r(),f(rn.$$.fragment),sc=r(),G=s("div"),f(nn.$$.fragment),h_=r(),fd=s("p"),fd.innerHTML=ix,g_=r(),Ft=s("div"),f(sn.$$.fragment),x_=r(),pd=s("p"),pd.innerHTML=dx,L_=r(),Jt=s("div"),f(dn.$$.fragment),b_=r(),md=s("p"),md.innerHTML=lx,w_=r(),Qe=s("div"),f(ln.$$.fragment),v_=r(),_d=s("p"),_d.textContent=cx,$_=r(),f(Pt.$$.fragment),y_=r(),Ht=s("div"),f(cn.$$.fragment),M_=r(),ud=s("p"),ud.textContent=fx,T_=r(),Oe=s("div"),f(fn.$$.fragment),D_=r(),hd=s("p"),hd.innerHTML=px,C_=r(),f(jt.$$.fragment),ic=r(),f(pn.$$.fragment),dc=r(),B=s("div"),f(mn.$$.fragment),S_=r(),gd=s("p"),gd.innerHTML=mx,k_=r(),Zt=s("div"),f(_n.$$.fragment),R_=r(),xd=s("p"),xd.innerHTML=_x,A_=r(),Gt=s("div"),f(un.$$.fragment),U_=r(),Ld=s("p"),Ld.innerHTML=ux,V_=r(),Ke=s("div"),f(hn.$$.fragment),I_=r(),bd=s("p"),bd.textContent=hx,W_=r(),f(Bt.$$.fragment),X_=r(),Et=s("div"),f(gn.$$.fragment),F_=r(),wd=s("p"),wd.textContent=gx,J_=r(),eo=s("div"),f(xn.$$.fragment),P_=r(),vd=s("p"),vd.innerHTML=xx,H_=r(),f(qt.$$.fragment),lc=r(),f(Ln.$$.fragment),cc=r(),E=s("div"),f(bn.$$.fragment),j_=r(),$d=s("p"),$d.innerHTML=Lx,Z_=r(),Nt=s("div"),f(wn.$$.fragment),G_=r(),yd=s("p"),yd.innerHTML=bx,B_=r(),zt=s("div"),f(vn.$$.fragment),E_=r(),Md=s("p"),Md.innerHTML=wx,q_=r(),oo=s("div"),f($n.$$.fragment),N_=r(),Td=s("p"),Td.textContent=vx,z_=r(),f(Yt.$$.fragment),Y_=r(),Qt=s("div"),f(yn.$$.fragment),Q_=r(),Dd=s("p"),Dd.textContent=$x,O_=r(),to=s("div"),f(Mn.$$.fragment),K_=r(),Cd=s("p"),Cd.innerHTML=yx,eu=r(),f(Ot.$$.fragment),fc=r(),f(Tn.$$.fragment),pc=r(),q=s("div"),f(Dn.$$.fragment),ou=r(),Sd=s("p"),Sd.innerHTML=Mx,tu=r(),Kt=s("div"),f(Cn.$$.fragment),au=r(),kd=s("p"),kd.innerHTML=Tx,ru=r(),ea=s("div"),f(Sn.$$.fragment),nu=r(),Rd=s("p"),Rd.innerHTML=Dx,su=r(),ao=s("div"),f(kn.$$.fragment),iu=r(),Ad=s("p"),Ad.textContent=Cx,du=r(),f(oa.$$.fragment),lu=r(),ta=s("div"),f(Rn.$$.fragment),cu=r(),Ud=s("p"),Ud.textContent=Sx,fu=r(),ro=s("div"),f(An.$$.fragment),pu=r(),Vd=s("p"),Vd.innerHTML=kx,mu=r(),f(aa.$$.fragment),mc=r(),f(Un.$$.fragment),_c=r(),N=s("div"),f(Vn.$$.fragment),_u=r(),Id=s("p"),Id.innerHTML=Rx,uu=r(),ra=s("div"),f(In.$$.fragment),hu=r(),Wd=s("p"),Wd.innerHTML=Ax,gu=r(),na=s("div"),f(Wn.$$.fragment),xu=r(),Xd=s("p"),Xd.innerHTML=Ux,Lu=r(),no=s("div"),f(Xn.$$.fragment),bu=r(),Fd=s("p"),Fd.textContent=Vx,wu=r(),f(sa.$$.fragment),vu=r(),ia=s("div"),f(Fn.$$.fragment),$u=r(),Jd=s("p"),Jd.textContent=Ix,yu=r(),so=s("div"),f(Jn.$$.fragment),Mu=r(),Pd=s("p"),Pd.innerHTML=Wx,Tu=r(),f(da.$$.fragment),uc=r(),f(Pn.$$.fragment),hc=r(),ye=s("div"),f(Hn.$$.fragment),Du=r(),la=s("div"),f(jn.$$.fragment),Cu=r(),Hd=s("p"),Hd.innerHTML=Xx,Su=r(),ca=s("div"),f(Zn.$$.fragment),ku=r(),jd=s("p"),jd.textContent=Fx,gc=r(),f(Gn.$$.fragment),xc=r(),z=s("div"),f(Bn.$$.fragment),Ru=r(),Zd=s("p"),Zd.innerHTML=Jx,Au=r(),fa=s("div"),f(En.$$.fragment),Uu=r(),Gd=s("p"),Gd.innerHTML=Px,Vu=r(),pa=s("div"),f(qn.$$.fragment),Iu=r(),Bd=s("p"),Bd.innerHTML=Hx,Wu=r(),io=s("div"),f(Nn.$$.fragment),Xu=r(),Ed=s("p"),Ed.textContent=jx,Fu=r(),f(ma.$$.fragment),Ju=r(),_a=s("div"),f(zn.$$.fragment),Pu=r(),qd=s("p"),qd.textContent=Zx,Hu=r(),lo=s("div"),f(Yn.$$.fragment),ju=r(),Nd=s("p"),Nd.innerHTML=Gx,Zu=r(),f(ua.$$.fragment),Lc=r(),f(Qn.$$.fragment),bc=r(),S=s("div"),f(On.$$.fragment),Gu=r(),zd=s("p"),zd.textContent=Bx,Bu=r(),co=s("div"),f(Kn.$$.fragment),Eu=r(),Yd=s("p"),Yd.textContent=Ex,qu=r(),f(ha.$$.fragment),Nu=r(),fo=s("div"),f(es.$$.fragment),zu=r(),Qd=s("p"),Qd.textContent=qx,Yu=r(),f(ga.$$.fragment),Qu=r(),po=s("div"),f(os.$$.fragment),Ou=r(),Od=s("p"),Od.textContent=Nx,Ku=r(),f(xa.$$.fragment),eh=r(),La=s("div"),f(ts.$$.fragment),oh=r(),Kd=s("p"),Kd.textContent=zx,th=r(),ve=s("div"),f(as.$$.fragment),ah=r(),el=s("p"),el.textContent=Yx,rh=r(),f(ba.$$.fragment),nh=r(),f(wa.$$.fragment),sh=r(),mo=s("div"),f(rs.$$.fragment),ih=r(),ol=s("p"),ol.textContent=Qx,dh=r(),f(va.$$.fragment),lh=r(),$a=s("div"),f(ns.$$.fragment),ch=r(),tl=s("p"),tl.textContent=Ox,fh=r(),_o=s("div"),f(ss.$$.fragment),ph=r(),al=s("p"),al.textContent=Kx,mh=r(),f(ya.$$.fragment),_h=r(),$e=s("div"),f(is.$$.fragment),uh=r(),rl=s("p"),rl.innerHTML=eL,hh=r(),nl=s("p"),nl.textContent=oL,gh=r(),f(Ma.$$.fragment),xh=r(),uo=s("div"),f(ds.$$.fragment),Lh=r(),sl=s("p"),sl.innerHTML=tL,bh=r(),f(Ta.$$.fragment),wh=r(),ho=s("div"),f(ls.$$.fragment),vh=r(),il=s("p"),il.textContent=aL,$h=r(),f(Da.$$.fragment),yh=r(),Ca=s("div"),f(cs.$$.fragment),Mh=r(),dl=s("p"),dl.textContent=rL,wc=r(),f(fs.$$.fragment),vc=r(),Wl=s("p"),this.h()},l(e){const x=lL("svelte-u9bgzb",document.head);t=i(x,"META",{name:!0,content:!0}),x.forEach(l),L=n(e),c=i(e,"P",{}),$(c).forEach(l),d=n(e),p(w.$$.fragment,e),a=n(e),v=i(e,"P",{"data-svelte-h":!0}),g(v)!=="svelte-dxus99"&&(v.innerHTML=Th),Xl=n(e),Ra=i(e,"UL",{"data-svelte-h":!0}),g(Ra)!=="svelte-1xyawm1"&&(Ra.innerHTML=Dh),Fl=n(e),p(Vo.$$.fragment,e),Jl=n(e),p(Aa.$$.fragment,e),Pl=n(e),C=i(e,"DIV",{class:!0});var R=$(C);p(Ua.$$.fragment,R),af=n(R),As=i(R,"P",{"data-svelte-h":!0}),g(As)!=="svelte-1q4bbx"&&(As.textContent=Ch),rf=n(R),De=i(R,"DIV",{class:!0});var go=$(De);p(Va.$$.fragment,go),nf=n(go),Us=i(go,"P",{"data-svelte-h":!0}),g(Us)!=="svelte-197ly1e"&&(Us.textContent=Sh),sf=n(go),p(Io.$$.fragment,go),go.forEach(l),df=n(R),Ce=i(R,"DIV",{class:!0});var xo=$(Ce);p(Ia.$$.fragment,xo),lf=n(xo),Vs=i(xo,"P",{"data-svelte-h":!0}),g(Vs)!=="svelte-1k7sb6g"&&(Vs.textContent=kh),cf=n(xo),p(Wo.$$.fragment,xo),xo.forEach(l),ff=n(R),Se=i(R,"DIV",{class:!0});var Lo=$(Se);p(Wa.$$.fragment,Lo),pf=n(Lo),Is=i(Lo,"P",{"data-svelte-h":!0}),g(Is)!=="svelte-1270mz9"&&(Is.textContent=Rh),mf=n(Lo),p(Xo.$$.fragment,Lo),Lo.forEach(l),_f=n(R),Fo=i(R,"DIV",{class:!0});var ps=$(Fo);p(Xa.$$.fragment,ps),uf=n(ps),Ws=i(ps,"P",{"data-svelte-h":!0}),g(Ws)!=="svelte-aqzrjr"&&(Ws.textContent=Ah),ps.forEach(l),hf=n(R),be=i(R,"DIV",{class:!0});var Me=$(be);p(Fa.$$.fragment,Me),gf=n(Me),Xs=i(Me,"P",{"data-svelte-h":!0}),g(Xs)!=="svelte-1nr2dy0"&&(Xs.textContent=Uh),xf=n(Me),p(Jo.$$.fragment,Me),Lf=n(Me),p(Po.$$.fragment,Me),Me.forEach(l),bf=n(R),ke=i(R,"DIV",{class:!0});var bo=$(ke);p(Ja.$$.fragment,bo),wf=n(bo),Fs=i(bo,"P",{"data-svelte-h":!0}),g(Fs)!=="svelte-h0os0v"&&(Fs.textContent=Vh),vf=n(bo),p(Ho.$$.fragment,bo),bo.forEach(l),$f=n(R),jo=i(R,"DIV",{class:!0});var ms=$(jo);p(Pa.$$.fragment,ms),yf=n(ms),Js=i(ms,"P",{"data-svelte-h":!0}),g(Js)!=="svelte-1825k9e"&&(Js.textContent=Ih),ms.forEach(l),Mf=n(R),Re=i(R,"DIV",{class:!0});var wo=$(Re);p(Ha.$$.fragment,wo),Tf=n(wo),Ps=i(wo,"P",{"data-svelte-h":!0}),g(Ps)!=="svelte-1nht1gz"&&(Ps.textContent=Wh),Df=n(wo),p(Zo.$$.fragment,wo),wo.forEach(l),Cf=n(R),we=i(R,"DIV",{class:!0});var Te=$(we);p(ja.$$.fragment,Te),Sf=n(Te),Hs=i(Te,"P",{"data-svelte-h":!0}),g(Hs)!=="svelte-rvubqa"&&(Hs.innerHTML=Xh),kf=n(Te),js=i(Te,"P",{"data-svelte-h":!0}),g(js)!=="svelte-x8llv0"&&(js.textContent=Fh),Rf=n(Te),p(Go.$$.fragment,Te),Te.forEach(l),Af=n(R),Ae=i(R,"DIV",{class:!0});var vo=$(Ae);p(Za.$$.fragment,vo),Uf=n(vo),Zs=i(vo,"P",{"data-svelte-h":!0}),g(Zs)!=="svelte-ioswce"&&(Zs.innerHTML=Jh),Vf=n(vo),p(Bo.$$.fragment,vo),vo.forEach(l),If=n(R),Ue=i(R,"DIV",{class:!0});var $o=$(Ue);p(Ga.$$.fragment,$o),Wf=n($o),Gs=i($o,"P",{"data-svelte-h":!0}),g(Gs)!=="svelte-119cgd9"&&(Gs.textContent=Ph),Xf=n($o),p(Eo.$$.fragment,$o),$o.forEach(l),Ff=n(R),qo=i(R,"DIV",{class:!0});var _s=$(qo);p(Ba.$$.fragment,_s),Jf=n(_s),Bs=i(_s,"P",{"data-svelte-h":!0}),g(Bs)!=="svelte-1rtya5j"&&(Bs.textContent=Hh),_s.forEach(l),R.forEach(l),Hl=n(e),p(Ea.$$.fragment,e),jl=n(e),X=i(e,"DIV",{class:!0});var Q=$(X);p(qa.$$.fragment,Q),Pf=n(Q),Es=i(Q,"P",{"data-svelte-h":!0}),g(Es)!=="svelte-z85860"&&(Es.innerHTML=jh),Hf=n(Q),No=i(Q,"DIV",{class:!0});var us=$(No);p(Na.$$.fragment,us),jf=n(us),qs=i(us,"P",{"data-svelte-h":!0}),g(qs)!=="svelte-1062ci4"&&(qs.innerHTML=Zh),us.forEach(l),Zf=n(Q),zo=i(Q,"DIV",{class:!0});var hs=$(zo);p(za.$$.fragment,hs),Gf=n(hs),Ns=i(hs,"P",{"data-svelte-h":!0}),g(Ns)!=="svelte-u3q4so"&&(Ns.innerHTML=Gh),hs.forEach(l),Bf=n(Q),ae=i(Q,"DIV",{class:!0});var ne=$(ae);p(Ya.$$.fragment,ne),Ef=n(ne),zs=i(ne,"P",{"data-svelte-h":!0}),g(zs)!=="svelte-vs7s0z"&&(zs.innerHTML=Bh),qf=n(ne),Ys=i(ne,"P",{"data-svelte-h":!0}),g(Ys)!=="svelte-15b960v"&&(Ys.innerHTML=Eh),Nf=n(ne),Qs=i(ne,"P",{"data-svelte-h":!0}),g(Qs)!=="svelte-17jjwop"&&(Qs.innerHTML=qh),zf=n(ne),Os=i(ne,"P",{"data-svelte-h":!0}),g(Os)!=="svelte-9lmm3e"&&(Os.innerHTML=Nh),Yf=n(ne),Ks=i(ne,"P",{"data-svelte-h":!0}),g(Ks)!=="svelte-5psfno"&&(Ks.innerHTML=zh),ne.forEach(l),Qf=n(Q),Ve=i(Q,"DIV",{class:!0});var yo=$(Ve);p(Qa.$$.fragment,yo),Of=n(yo),ei=i(yo,"P",{"data-svelte-h":!0}),g(ei)!=="svelte-flusvq"&&(ei.textContent=Yh),Kf=n(yo),p(Yo.$$.fragment,yo),yo.forEach(l),ep=n(Q),Qo=i(Q,"DIV",{class:!0});var gs=$(Qo);p(Oa.$$.fragment,gs),op=n(gs),oi=i(gs,"P",{"data-svelte-h":!0}),g(oi)!=="svelte-1ufq5ot"&&(oi.textContent=Qh),gs.forEach(l),Q.forEach(l),Zl=n(e),p(Ka.$$.fragment,e),Gl=n(e),F=i(e,"DIV",{class:!0});var O=$(F);p(er.$$.fragment,O),tp=n(O),ti=i(O,"P",{"data-svelte-h":!0}),g(ti)!=="svelte-1hum8zt"&&(ti.innerHTML=Oh),ap=n(O),Oo=i(O,"DIV",{class:!0});var xs=$(Oo);p(or.$$.fragment,xs),rp=n(xs),ai=i(xs,"P",{"data-svelte-h":!0}),g(ai)!=="svelte-1062ci4"&&(ai.innerHTML=Kh),xs.forEach(l),np=n(O),Ko=i(O,"DIV",{class:!0});var Ls=$(Ko);p(tr.$$.fragment,Ls),sp=n(Ls),ri=i(Ls,"P",{"data-svelte-h":!0}),g(ri)!=="svelte-u3q4so"&&(ri.innerHTML=eg),Ls.forEach(l),ip=n(O),re=i(O,"DIV",{class:!0});var se=$(re);p(ar.$$.fragment,se),dp=n(se),ni=i(se,"P",{"data-svelte-h":!0}),g(ni)!=="svelte-vs7s0z"&&(ni.innerHTML=og),lp=n(se),si=i(se,"P",{"data-svelte-h":!0}),g(si)!=="svelte-15b960v"&&(si.innerHTML=tg),cp=n(se),ii=i(se,"P",{"data-svelte-h":!0}),g(ii)!=="svelte-17jjwop"&&(ii.innerHTML=ag),fp=n(se),di=i(se,"P",{"data-svelte-h":!0}),g(di)!=="svelte-9lmm3e"&&(di.innerHTML=rg),pp=n(se),li=i(se,"P",{"data-svelte-h":!0}),g(li)!=="svelte-5psfno"&&(li.innerHTML=ng),se.forEach(l),mp=n(O),Ie=i(O,"DIV",{class:!0});var Mo=$(Ie);p(rr.$$.fragment,Mo),_p=n(Mo),ci=i(Mo,"P",{"data-svelte-h":!0}),g(ci)!=="svelte-flusvq"&&(ci.textContent=sg),up=n(Mo),p(et.$$.fragment,Mo),Mo.forEach(l),hp=n(O),ot=i(O,"DIV",{class:!0});var bs=$(ot);p(nr.$$.fragment,bs),gp=n(bs),fi=i(bs,"P",{"data-svelte-h":!0}),g(fi)!=="svelte-1ufq5ot"&&(fi.textContent=ig),bs.forEach(l),O.forEach(l),Bl=n(e),p(sr.$$.fragment,e),El=n(e),V=i(e,"DIV",{class:!0});var W=$(V);p(ir.$$.fragment,W),xp=n(W),pi=i(W,"P",{"data-svelte-h":!0}),g(pi)!=="svelte-1lbdgsk"&&(pi.innerHTML=dg),Lp=n(W),mi=i(W,"P",{"data-svelte-h":!0}),g(mi)!=="svelte-ps7ube"&&(mi.innerHTML=lg),bp=n(W),tt=i(W,"DIV",{class:!0});var ws=$(tt);p(dr.$$.fragment,ws),wp=n(ws),_i=i(ws,"P",{"data-svelte-h":!0}),g(_i)!=="svelte-1062ci4"&&(_i.innerHTML=cg),ws.forEach(l),vp=n(W),at=i(W,"DIV",{class:!0});var vs=$(at);p(lr.$$.fragment,vs),$p=n(vs),ui=i(vs,"P",{"data-svelte-h":!0}),g(ui)!=="svelte-1lgbsz7"&&(ui.innerHTML=fg),vs.forEach(l),yp=n(W),ie=i(W,"DIV",{class:!0});var xe=$(ie);p(cr.$$.fragment,xe),Mp=n(xe),hi=i(xe,"P",{"data-svelte-h":!0}),g(hi)!=="svelte-vs7s0z"&&(hi.innerHTML=pg),Tp=n(xe),gi=i(xe,"P",{"data-svelte-h":!0}),g(gi)!=="svelte-15b960v"&&(gi.innerHTML=mg),Dp=n(xe),xi=i(xe,"P",{"data-svelte-h":!0}),g(xi)!=="svelte-17jjwop"&&(xi.innerHTML=_g),Cp=n(xe),Li=i(xe,"P",{"data-svelte-h":!0}),g(Li)!=="svelte-1ukghd4"&&(Li.innerHTML=ug),xe.forEach(l),Sp=n(W),We=i(W,"DIV",{class:!0});var To=$(We);p(fr.$$.fragment,To),kp=n(To),bi=i(To,"P",{"data-svelte-h":!0}),g(bi)!=="svelte-flusvq"&&(bi.textContent=hg),Rp=n(To),p(rt.$$.fragment,To),To.forEach(l),Ap=n(W),nt=i(W,"DIV",{class:!0});var $s=$(nt);p(pr.$$.fragment,$s),Up=n($s),wi=i($s,"P",{"data-svelte-h":!0}),g(wi)!=="svelte-1ufq5ot"&&(wi.textContent=gg),$s.forEach(l),Vp=n(W),Xe=i(W,"DIV",{class:!0});var Do=$(Xe);p(mr.$$.fragment,Do),Ip=n(Do),vi=i(Do,"P",{"data-svelte-h":!0}),g(vi)!=="svelte-ioswce"&&(vi.innerHTML=xg),Wp=n(Do),p(st.$$.fragment,Do),Do.forEach(l),W.forEach(l),ql=n(e),p(_r.$$.fragment,e),Nl=n(e),U=i(e,"DIV",{class:!0});var I=$(U);p(ur.$$.fragment,I),Xp=n(I),$i=i(I,"P",{"data-svelte-h":!0}),g($i)!=="svelte-gm06kd"&&($i.innerHTML=Lg),Fp=n(I),yi=i(I,"P",{"data-svelte-h":!0}),g(yi)!=="svelte-ps7ube"&&(yi.innerHTML=bg),Jp=n(I),it=i(I,"DIV",{class:!0});var ys=$(it);p(hr.$$.fragment,ys),Pp=n(ys),Mi=i(ys,"P",{"data-svelte-h":!0}),g(Mi)!=="svelte-1062ci4"&&(Mi.innerHTML=wg),ys.forEach(l),Hp=n(I),dt=i(I,"DIV",{class:!0});var Ms=$(dt);p(gr.$$.fragment,Ms),jp=n(Ms),Ti=i(Ms,"P",{"data-svelte-h":!0}),g(Ti)!=="svelte-1lgbsz7"&&(Ti.innerHTML=vg),Ms.forEach(l),Zp=n(I),de=i(I,"DIV",{class:!0});var Le=$(de);p(xr.$$.fragment,Le),Gp=n(Le),Di=i(Le,"P",{"data-svelte-h":!0}),g(Di)!=="svelte-178gcly"&&(Di.innerHTML=$g),Bp=n(Le),Ci=i(Le,"P",{"data-svelte-h":!0}),g(Ci)!=="svelte-15b960v"&&(Ci.innerHTML=yg),Ep=n(Le),Si=i(Le,"P",{"data-svelte-h":!0}),g(Si)!=="svelte-17jjwop"&&(Si.innerHTML=Mg),qp=n(Le),ki=i(Le,"P",{"data-svelte-h":!0}),g(ki)!=="svelte-1ukghd4"&&(ki.innerHTML=Tg),Le.forEach(l),Np=n(I),Fe=i(I,"DIV",{class:!0});var Co=$(Fe);p(Lr.$$.fragment,Co),zp=n(Co),Ri=i(Co,"P",{"data-svelte-h":!0}),g(Ri)!=="svelte-flusvq"&&(Ri.textContent=Dg),Yp=n(Co),p(lt.$$.fragment,Co),Co.forEach(l),Qp=n(I),ct=i(I,"DIV",{class:!0});var Ts=$(ct);p(br.$$.fragment,Ts),Op=n(Ts),Ai=i(Ts,"P",{"data-svelte-h":!0}),g(Ai)!=="svelte-1ufq5ot"&&(Ai.textContent=Cg),Ts.forEach(l),Kp=n(I),Je=i(I,"DIV",{class:!0});var So=$(Je);p(wr.$$.fragment,So),em=n(So),Ui=i(So,"P",{"data-svelte-h":!0}),g(Ui)!=="svelte-ioswce"&&(Ui.innerHTML=Sg),om=n(So),p(ft.$$.fragment,So),So.forEach(l),tm=n(I),Pe=i(I,"DIV",{class:!0});var ko=$(Pe);p(vr.$$.fragment,ko),am=n(ko),Vi=i(ko,"P",{"data-svelte-h":!0}),g(Vi)!=="svelte-119cgd9"&&(Vi.textContent=kg),rm=n(ko),p(pt.$$.fragment,ko),ko.forEach(l),I.forEach(l),zl=n(e),p($r.$$.fragment,e),Yl=n(e),J=i(e,"DIV",{class:!0});var K=$(J);p(yr.$$.fragment,K),nm=n(K),Ii=i(K,"P",{"data-svelte-h":!0}),g(Ii)!=="svelte-wn3m0d"&&(Ii.innerHTML=Rg),sm=n(K),mt=i(K,"DIV",{class:!0});var Ds=$(mt);p(Mr.$$.fragment,Ds),im=n(Ds),Wi=i(Ds,"P",{"data-svelte-h":!0}),g(Wi)!=="svelte-1lgbsz7"&&(Wi.innerHTML=Ag),Ds.forEach(l),dm=n(K),_t=i(K,"DIV",{class:!0});var Cs=$(_t);p(Tr.$$.fragment,Cs),lm=n(Cs),Xi=i(Cs,"P",{"data-svelte-h":!0}),g(Xi)!=="svelte-165kp84"&&(Xi.innerHTML=Ug),Cs.forEach(l),cm=n(K),He=i(K,"DIV",{class:!0});var Ro=$(He);p(Dr.$$.fragment,Ro),fm=n(Ro),Fi=i(Ro,"P",{"data-svelte-h":!0}),g(Fi)!=="svelte-flusvq"&&(Fi.textContent=Vg),pm=n(Ro),p(ut.$$.fragment,Ro),Ro.forEach(l),mm=n(K),ht=i(K,"DIV",{class:!0});var Ss=$(ht);p(Cr.$$.fragment,Ss),_m=n(Ss),Ji=i(Ss,"P",{"data-svelte-h":!0}),g(Ji)!=="svelte-1gl6t2c"&&(Ji.textContent=Ig),Ss.forEach(l),um=n(K),je=i(K,"DIV",{class:!0});var Ao=$(je);p(Sr.$$.fragment,Ao),hm=n(Ao),Pi=i(Ao,"P",{"data-svelte-h":!0}),g(Pi)!=="svelte-ioswce"&&(Pi.innerHTML=Wg),gm=n(Ao),p(gt.$$.fragment,Ao),Ao.forEach(l),K.forEach(l),Ql=n(e),p(kr.$$.fragment,e),Ol=n(e),P=i(e,"DIV",{class:!0});var ee=$(P);p(Rr.$$.fragment,ee),xm=n(ee),Hi=i(ee,"P",{"data-svelte-h":!0}),g(Hi)!=="svelte-juxhhl"&&(Hi.innerHTML=Xg),Lm=n(ee),xt=i(ee,"DIV",{class:!0});var ks=$(xt);p(Ar.$$.fragment,ks),bm=n(ks),ji=i(ks,"P",{"data-svelte-h":!0}),g(ji)!=="svelte-1lgbsz7"&&(ji.innerHTML=Fg),ks.forEach(l),wm=n(ee),Lt=i(ee,"DIV",{class:!0});var Rs=$(Lt);p(Ur.$$.fragment,Rs),vm=n(Rs),Zi=i(Rs,"P",{"data-svelte-h":!0}),g(Zi)!=="svelte-165kp84"&&(Zi.innerHTML=Jg),Rs.forEach(l),$m=n(ee),Ze=i(ee,"DIV",{class:!0});var Uo=$(Ze);p(Vr.$$.fragment,Uo),ym=n(Uo),Gi=i(Uo,"P",{"data-svelte-h":!0}),g(Gi)!=="svelte-flusvq"&&(Gi.textContent=Pg),Mm=n(Uo),p(bt.$$.fragment,Uo),Uo.forEach(l),Tm=n(ee),wt=i(ee,"DIV",{class:!0});var yc=$(wt);p(Ir.$$.fragment,yc),Dm=n(yc),Bi=i(yc,"P",{"data-svelte-h":!0}),g(Bi)!=="svelte-1gl6t2c"&&(Bi.textContent=Hg),yc.forEach(l),Cm=n(ee),Ge=i(ee,"DIV",{class:!0});var ll=$(Ge);p(Wr.$$.fragment,ll),Sm=n(ll),Ei=i(ll,"P",{"data-svelte-h":!0}),g(Ei)!=="svelte-ioswce"&&(Ei.innerHTML=jg),km=n(ll),p(vt.$$.fragment,ll),ll.forEach(l),ee.forEach(l),Kl=n(e),p(Xr.$$.fragment,e),ec=n(e),H=i(e,"DIV",{class:!0});var le=$(H);p(Fr.$$.fragment,le),Rm=n(le),qi=i(le,"P",{"data-svelte-h":!0}),g(qi)!=="svelte-lu0z20"&&(qi.innerHTML=Zg),Am=n(le),$t=i(le,"DIV",{class:!0});var Mc=$($t);p(Jr.$$.fragment,Mc),Um=n(Mc),Ni=i(Mc,"P",{"data-svelte-h":!0}),g(Ni)!=="svelte-1lgbsz7"&&(Ni.innerHTML=Gg),Mc.forEach(l),Vm=n(le),yt=i(le,"DIV",{class:!0});var Tc=$(yt);p(Pr.$$.fragment,Tc),Im=n(Tc),zi=i(Tc,"P",{"data-svelte-h":!0}),g(zi)!=="svelte-165kp84"&&(zi.innerHTML=Bg),Tc.forEach(l),Wm=n(le),Be=i(le,"DIV",{class:!0});var cl=$(Be);p(Hr.$$.fragment,cl),Xm=n(cl),Yi=i(cl,"P",{"data-svelte-h":!0}),g(Yi)!=="svelte-flusvq"&&(Yi.textContent=Eg),Fm=n(cl),p(Mt.$$.fragment,cl),cl.forEach(l),Jm=n(le),Tt=i(le,"DIV",{class:!0});var Dc=$(Tt);p(jr.$$.fragment,Dc),Pm=n(Dc),Qi=i(Dc,"P",{"data-svelte-h":!0}),g(Qi)!=="svelte-1gl6t2c"&&(Qi.textContent=qg),Dc.forEach(l),Hm=n(le),Ee=i(le,"DIV",{class:!0});var fl=$(Ee);p(Zr.$$.fragment,fl),jm=n(fl),Oi=i(fl,"P",{"data-svelte-h":!0}),g(Oi)!=="svelte-ioswce"&&(Oi.innerHTML=Ng),Zm=n(fl),p(Dt.$$.fragment,fl),fl.forEach(l),le.forEach(l),oc=n(e),p(Gr.$$.fragment,e),tc=n(e),j=i(e,"DIV",{class:!0});var ce=$(j);p(Br.$$.fragment,ce),Gm=n(ce),Ki=i(ce,"P",{"data-svelte-h":!0}),g(Ki)!=="svelte-j3tggx"&&(Ki.innerHTML=zg),Bm=n(ce),Ct=i(ce,"DIV",{class:!0});var Cc=$(Ct);p(Er.$$.fragment,Cc),Em=n(Cc),ed=i(Cc,"P",{"data-svelte-h":!0}),g(ed)!=="svelte-1lgbsz7"&&(ed.innerHTML=Yg),Cc.forEach(l),qm=n(ce),St=i(ce,"DIV",{class:!0});var Sc=$(St);p(qr.$$.fragment,Sc),Nm=n(Sc),od=i(Sc,"P",{"data-svelte-h":!0}),g(od)!=="svelte-165kp84"&&(od.innerHTML=Qg),Sc.forEach(l),zm=n(ce),qe=i(ce,"DIV",{class:!0});var pl=$(qe);p(Nr.$$.fragment,pl),Ym=n(pl),td=i(pl,"P",{"data-svelte-h":!0}),g(td)!=="svelte-flusvq"&&(td.textContent=Og),Qm=n(pl),p(kt.$$.fragment,pl),pl.forEach(l),Om=n(ce),Rt=i(ce,"DIV",{class:!0});var kc=$(Rt);p(zr.$$.fragment,kc),Km=n(kc),ad=i(kc,"P",{"data-svelte-h":!0}),g(ad)!=="svelte-1gl6t2c"&&(ad.textContent=Kg),kc.forEach(l),e_=n(ce),Ne=i(ce,"DIV",{class:!0});var ml=$(Ne);p(Yr.$$.fragment,ml),o_=n(ml),rd=i(ml,"P",{"data-svelte-h":!0}),g(rd)!=="svelte-ioswce"&&(rd.innerHTML=ex),t_=n(ml),p(At.$$.fragment,ml),ml.forEach(l),ce.forEach(l),ac=n(e),p(Qr.$$.fragment,e),rc=n(e),Z=i(e,"DIV",{class:!0});var fe=$(Z);p(Or.$$.fragment,fe),a_=n(fe),nd=i(fe,"P",{"data-svelte-h":!0}),g(nd)!=="svelte-11wdtok"&&(nd.innerHTML=ox),r_=n(fe),Ut=i(fe,"DIV",{class:!0});var Rc=$(Ut);p(Kr.$$.fragment,Rc),n_=n(Rc),sd=i(Rc,"P",{"data-svelte-h":!0}),g(sd)!=="svelte-1lgbsz7"&&(sd.innerHTML=tx),Rc.forEach(l),s_=n(fe),Vt=i(fe,"DIV",{class:!0});var Ac=$(Vt);p(en.$$.fragment,Ac),i_=n(Ac),id=i(Ac,"P",{"data-svelte-h":!0}),g(id)!=="svelte-165kp84"&&(id.innerHTML=ax),Ac.forEach(l),d_=n(fe),ze=i(fe,"DIV",{class:!0});var _l=$(ze);p(on.$$.fragment,_l),l_=n(_l),dd=i(_l,"P",{"data-svelte-h":!0}),g(dd)!=="svelte-flusvq"&&(dd.textContent=rx),c_=n(_l),p(It.$$.fragment,_l),_l.forEach(l),f_=n(fe),Wt=i(fe,"DIV",{class:!0});var Uc=$(Wt);p(tn.$$.fragment,Uc),p_=n(Uc),ld=i(Uc,"P",{"data-svelte-h":!0}),g(ld)!=="svelte-1gl6t2c"&&(ld.textContent=nx),Uc.forEach(l),m_=n(fe),Ye=i(fe,"DIV",{class:!0});var ul=$(Ye);p(an.$$.fragment,ul),__=n(ul),cd=i(ul,"P",{"data-svelte-h":!0}),g(cd)!=="svelte-ioswce"&&(cd.innerHTML=sx),u_=n(ul),p(Xt.$$.fragment,ul),ul.forEach(l),fe.forEach(l),nc=n(e),p(rn.$$.fragment,e),sc=n(e),G=i(e,"DIV",{class:!0});var pe=$(G);p(nn.$$.fragment,pe),h_=n(pe),fd=i(pe,"P",{"data-svelte-h":!0}),g(fd)!=="svelte-nuy388"&&(fd.innerHTML=ix),g_=n(pe),Ft=i(pe,"DIV",{class:!0});var Vc=$(Ft);p(sn.$$.fragment,Vc),x_=n(Vc),pd=i(Vc,"P",{"data-svelte-h":!0}),g(pd)!=="svelte-1lgbsz7"&&(pd.innerHTML=dx),Vc.forEach(l),L_=n(pe),Jt=i(pe,"DIV",{class:!0});var Ic=$(Jt);p(dn.$$.fragment,Ic),b_=n(Ic),md=i(Ic,"P",{"data-svelte-h":!0}),g(md)!=="svelte-165kp84"&&(md.innerHTML=lx),Ic.forEach(l),w_=n(pe),Qe=i(pe,"DIV",{class:!0});var hl=$(Qe);p(ln.$$.fragment,hl),v_=n(hl),_d=i(hl,"P",{"data-svelte-h":!0}),g(_d)!=="svelte-flusvq"&&(_d.textContent=cx),$_=n(hl),p(Pt.$$.fragment,hl),hl.forEach(l),y_=n(pe),Ht=i(pe,"DIV",{class:!0});var Wc=$(Ht);p(cn.$$.fragment,Wc),M_=n(Wc),ud=i(Wc,"P",{"data-svelte-h":!0}),g(ud)!=="svelte-1gl6t2c"&&(ud.textContent=fx),Wc.forEach(l),T_=n(pe),Oe=i(pe,"DIV",{class:!0});var gl=$(Oe);p(fn.$$.fragment,gl),D_=n(gl),hd=i(gl,"P",{"data-svelte-h":!0}),g(hd)!=="svelte-ioswce"&&(hd.innerHTML=px),C_=n(gl),p(jt.$$.fragment,gl),gl.forEach(l),pe.forEach(l),ic=n(e),p(pn.$$.fragment,e),dc=n(e),B=i(e,"DIV",{class:!0});var me=$(B);p(mn.$$.fragment,me),S_=n(me),gd=i(me,"P",{"data-svelte-h":!0}),g(gd)!=="svelte-1kwwj9b"&&(gd.innerHTML=mx),k_=n(me),Zt=i(me,"DIV",{class:!0});var Xc=$(Zt);p(_n.$$.fragment,Xc),R_=n(Xc),xd=i(Xc,"P",{"data-svelte-h":!0}),g(xd)!=="svelte-1lgbsz7"&&(xd.innerHTML=_x),Xc.forEach(l),A_=n(me),Gt=i(me,"DIV",{class:!0});var Fc=$(Gt);p(un.$$.fragment,Fc),U_=n(Fc),Ld=i(Fc,"P",{"data-svelte-h":!0}),g(Ld)!=="svelte-165kp84"&&(Ld.innerHTML=ux),Fc.forEach(l),V_=n(me),Ke=i(me,"DIV",{class:!0});var xl=$(Ke);p(hn.$$.fragment,xl),I_=n(xl),bd=i(xl,"P",{"data-svelte-h":!0}),g(bd)!=="svelte-flusvq"&&(bd.textContent=hx),W_=n(xl),p(Bt.$$.fragment,xl),xl.forEach(l),X_=n(me),Et=i(me,"DIV",{class:!0});var Jc=$(Et);p(gn.$$.fragment,Jc),F_=n(Jc),wd=i(Jc,"P",{"data-svelte-h":!0}),g(wd)!=="svelte-1gl6t2c"&&(wd.textContent=gx),Jc.forEach(l),J_=n(me),eo=i(me,"DIV",{class:!0});var Ll=$(eo);p(xn.$$.fragment,Ll),P_=n(Ll),vd=i(Ll,"P",{"data-svelte-h":!0}),g(vd)!=="svelte-ioswce"&&(vd.innerHTML=xx),H_=n(Ll),p(qt.$$.fragment,Ll),Ll.forEach(l),me.forEach(l),lc=n(e),p(Ln.$$.fragment,e),cc=n(e),E=i(e,"DIV",{class:!0});var _e=$(E);p(bn.$$.fragment,_e),j_=n(_e),$d=i(_e,"P",{"data-svelte-h":!0}),g($d)!=="svelte-15c2eby"&&($d.innerHTML=Lx),Z_=n(_e),Nt=i(_e,"DIV",{class:!0});var Pc=$(Nt);p(wn.$$.fragment,Pc),G_=n(Pc),yd=i(Pc,"P",{"data-svelte-h":!0}),g(yd)!=="svelte-1lgbsz7"&&(yd.innerHTML=bx),Pc.forEach(l),B_=n(_e),zt=i(_e,"DIV",{class:!0});var Hc=$(zt);p(vn.$$.fragment,Hc),E_=n(Hc),Md=i(Hc,"P",{"data-svelte-h":!0}),g(Md)!=="svelte-165kp84"&&(Md.innerHTML=wx),Hc.forEach(l),q_=n(_e),oo=i(_e,"DIV",{class:!0});var bl=$(oo);p($n.$$.fragment,bl),N_=n(bl),Td=i(bl,"P",{"data-svelte-h":!0}),g(Td)!=="svelte-flusvq"&&(Td.textContent=vx),z_=n(bl),p(Yt.$$.fragment,bl),bl.forEach(l),Y_=n(_e),Qt=i(_e,"DIV",{class:!0});var jc=$(Qt);p(yn.$$.fragment,jc),Q_=n(jc),Dd=i(jc,"P",{"data-svelte-h":!0}),g(Dd)!=="svelte-1gl6t2c"&&(Dd.textContent=$x),jc.forEach(l),O_=n(_e),to=i(_e,"DIV",{class:!0});var wl=$(to);p(Mn.$$.fragment,wl),K_=n(wl),Cd=i(wl,"P",{"data-svelte-h":!0}),g(Cd)!=="svelte-ioswce"&&(Cd.innerHTML=yx),eu=n(wl),p(Ot.$$.fragment,wl),wl.forEach(l),_e.forEach(l),fc=n(e),p(Tn.$$.fragment,e),pc=n(e),q=i(e,"DIV",{class:!0});var ue=$(q);p(Dn.$$.fragment,ue),ou=n(ue),Sd=i(ue,"P",{"data-svelte-h":!0}),g(Sd)!=="svelte-tblp4l"&&(Sd.innerHTML=Mx),tu=n(ue),Kt=i(ue,"DIV",{class:!0});var Zc=$(Kt);p(Cn.$$.fragment,Zc),au=n(Zc),kd=i(Zc,"P",{"data-svelte-h":!0}),g(kd)!=="svelte-1lgbsz7"&&(kd.innerHTML=Tx),Zc.forEach(l),ru=n(ue),ea=i(ue,"DIV",{class:!0});var Gc=$(ea);p(Sn.$$.fragment,Gc),nu=n(Gc),Rd=i(Gc,"P",{"data-svelte-h":!0}),g(Rd)!=="svelte-165kp84"&&(Rd.innerHTML=Dx),Gc.forEach(l),su=n(ue),ao=i(ue,"DIV",{class:!0});var vl=$(ao);p(kn.$$.fragment,vl),iu=n(vl),Ad=i(vl,"P",{"data-svelte-h":!0}),g(Ad)!=="svelte-flusvq"&&(Ad.textContent=Cx),du=n(vl),p(oa.$$.fragment,vl),vl.forEach(l),lu=n(ue),ta=i(ue,"DIV",{class:!0});var Bc=$(ta);p(Rn.$$.fragment,Bc),cu=n(Bc),Ud=i(Bc,"P",{"data-svelte-h":!0}),g(Ud)!=="svelte-1gl6t2c"&&(Ud.textContent=Sx),Bc.forEach(l),fu=n(ue),ro=i(ue,"DIV",{class:!0});var $l=$(ro);p(An.$$.fragment,$l),pu=n($l),Vd=i($l,"P",{"data-svelte-h":!0}),g(Vd)!=="svelte-ioswce"&&(Vd.innerHTML=kx),mu=n($l),p(aa.$$.fragment,$l),$l.forEach(l),ue.forEach(l),mc=n(e),p(Un.$$.fragment,e),_c=n(e),N=i(e,"DIV",{class:!0});var he=$(N);p(Vn.$$.fragment,he),_u=n(he),Id=i(he,"P",{"data-svelte-h":!0}),g(Id)!=="svelte-25otv4"&&(Id.innerHTML=Rx),uu=n(he),ra=i(he,"DIV",{class:!0});var Ec=$(ra);p(In.$$.fragment,Ec),hu=n(Ec),Wd=i(Ec,"P",{"data-svelte-h":!0}),g(Wd)!=="svelte-1lgbsz7"&&(Wd.innerHTML=Ax),Ec.forEach(l),gu=n(he),na=i(he,"DIV",{class:!0});var qc=$(na);p(Wn.$$.fragment,qc),xu=n(qc),Xd=i(qc,"P",{"data-svelte-h":!0}),g(Xd)!=="svelte-165kp84"&&(Xd.innerHTML=Ux),qc.forEach(l),Lu=n(he),no=i(he,"DIV",{class:!0});var yl=$(no);p(Xn.$$.fragment,yl),bu=n(yl),Fd=i(yl,"P",{"data-svelte-h":!0}),g(Fd)!=="svelte-flusvq"&&(Fd.textContent=Vx),wu=n(yl),p(sa.$$.fragment,yl),yl.forEach(l),vu=n(he),ia=i(he,"DIV",{class:!0});var Nc=$(ia);p(Fn.$$.fragment,Nc),$u=n(Nc),Jd=i(Nc,"P",{"data-svelte-h":!0}),g(Jd)!=="svelte-1gl6t2c"&&(Jd.textContent=Ix),Nc.forEach(l),yu=n(he),so=i(he,"DIV",{class:!0});var Ml=$(so);p(Jn.$$.fragment,Ml),Mu=n(Ml),Pd=i(Ml,"P",{"data-svelte-h":!0}),g(Pd)!=="svelte-ioswce"&&(Pd.innerHTML=Wx),Tu=n(Ml),p(da.$$.fragment,Ml),Ml.forEach(l),he.forEach(l),uc=n(e),p(Pn.$$.fragment,e),hc=n(e),ye=i(e,"DIV",{class:!0});var Tl=$(ye);p(Hn.$$.fragment,Tl),Du=n(Tl),la=i(Tl,"DIV",{class:!0});var zc=$(la);p(jn.$$.fragment,zc),Cu=n(zc),Hd=i(zc,"P",{"data-svelte-h":!0}),g(Hd)!=="svelte-1lgbsz7"&&(Hd.innerHTML=Xx),zc.forEach(l),Su=n(Tl),ca=i(Tl,"DIV",{class:!0});var Yc=$(ca);p(Zn.$$.fragment,Yc),ku=n(Yc),jd=i(Yc,"P",{"data-svelte-h":!0}),g(jd)!=="svelte-1ufq5ot"&&(jd.textContent=Fx),Yc.forEach(l),Tl.forEach(l),gc=n(e),p(Gn.$$.fragment,e),xc=n(e),z=i(e,"DIV",{class:!0});var ge=$(z);p(Bn.$$.fragment,ge),Ru=n(ge),Zd=i(ge,"P",{"data-svelte-h":!0}),g(Zd)!=="svelte-1b7416s"&&(Zd.innerHTML=Jx),Au=n(ge),fa=i(ge,"DIV",{class:!0});var Qc=$(fa);p(En.$$.fragment,Qc),Uu=n(Qc),Gd=i(Qc,"P",{"data-svelte-h":!0}),g(Gd)!=="svelte-1lgbsz7"&&(Gd.innerHTML=Px),Qc.forEach(l),Vu=n(ge),pa=i(ge,"DIV",{class:!0});var Oc=$(pa);p(qn.$$.fragment,Oc),Iu=n(Oc),Bd=i(Oc,"P",{"data-svelte-h":!0}),g(Bd)!=="svelte-165kp84"&&(Bd.innerHTML=Hx),Oc.forEach(l),Wu=n(ge),io=i(ge,"DIV",{class:!0});var Dl=$(io);p(Nn.$$.fragment,Dl),Xu=n(Dl),Ed=i(Dl,"P",{"data-svelte-h":!0}),g(Ed)!=="svelte-flusvq"&&(Ed.textContent=jx),Fu=n(Dl),p(ma.$$.fragment,Dl),Dl.forEach(l),Ju=n(ge),_a=i(ge,"DIV",{class:!0});var Kc=$(_a);p(zn.$$.fragment,Kc),Pu=n(Kc),qd=i(Kc,"P",{"data-svelte-h":!0}),g(qd)!=="svelte-1gl6t2c"&&(qd.textContent=Zx),Kc.forEach(l),Hu=n(ge),lo=i(ge,"DIV",{class:!0});var Cl=$(lo);p(Yn.$$.fragment,Cl),ju=n(Cl),Nd=i(Cl,"P",{"data-svelte-h":!0}),g(Nd)!=="svelte-ioswce"&&(Nd.innerHTML=Gx),Zu=n(Cl),p(ua.$$.fragment,Cl),Cl.forEach(l),ge.forEach(l),Lc=n(e),p(Qn.$$.fragment,e),bc=n(e),S=i(e,"DIV",{class:!0});var A=$(S);p(On.$$.fragment,A),Gu=n(A),zd=i(A,"P",{"data-svelte-h":!0}),g(zd)!=="svelte-1q4bbx"&&(zd.textContent=Bx),Bu=n(A),co=i(A,"DIV",{class:!0});var Sl=$(co);p(Kn.$$.fragment,Sl),Eu=n(Sl),Yd=i(Sl,"P",{"data-svelte-h":!0}),g(Yd)!=="svelte-197ly1e"&&(Yd.textContent=Ex),qu=n(Sl),p(ha.$$.fragment,Sl),Sl.forEach(l),Nu=n(A),fo=i(A,"DIV",{class:!0});var kl=$(fo);p(es.$$.fragment,kl),zu=n(kl),Qd=i(kl,"P",{"data-svelte-h":!0}),g(Qd)!=="svelte-1k7sb6g"&&(Qd.textContent=qx),Yu=n(kl),p(ga.$$.fragment,kl),kl.forEach(l),Qu=n(A),po=i(A,"DIV",{class:!0});var Rl=$(po);p(os.$$.fragment,Rl),Ou=n(Rl),Od=i(Rl,"P",{"data-svelte-h":!0}),g(Od)!=="svelte-1270mz9"&&(Od.textContent=Nx),Ku=n(Rl),p(xa.$$.fragment,Rl),Rl.forEach(l),eh=n(A),La=i(A,"DIV",{class:!0});var ef=$(La);p(ts.$$.fragment,ef),oh=n(ef),Kd=i(ef,"P",{"data-svelte-h":!0}),g(Kd)!=="svelte-aqzrjr"&&(Kd.textContent=zx),ef.forEach(l),th=n(A),ve=i(A,"DIV",{class:!0});var Sa=$(ve);p(as.$$.fragment,Sa),ah=n(Sa),el=i(Sa,"P",{"data-svelte-h":!0}),g(el)!=="svelte-1nr2dy0"&&(el.textContent=Yx),rh=n(Sa),p(ba.$$.fragment,Sa),nh=n(Sa),p(wa.$$.fragment,Sa),Sa.forEach(l),sh=n(A),mo=i(A,"DIV",{class:!0});var Al=$(mo);p(rs.$$.fragment,Al),ih=n(Al),ol=i(Al,"P",{"data-svelte-h":!0}),g(ol)!=="svelte-h0os0v"&&(ol.textContent=Qx),dh=n(Al),p(va.$$.fragment,Al),Al.forEach(l),lh=n(A),$a=i(A,"DIV",{class:!0});var of=$($a);p(ns.$$.fragment,of),ch=n(of),tl=i(of,"P",{"data-svelte-h":!0}),g(tl)!=="svelte-1825k9e"&&(tl.textContent=Ox),of.forEach(l),fh=n(A),_o=i(A,"DIV",{class:!0});var Ul=$(_o);p(ss.$$.fragment,Ul),ph=n(Ul),al=i(Ul,"P",{"data-svelte-h":!0}),g(al)!=="svelte-1nht1gz"&&(al.textContent=Kx),mh=n(Ul),p(ya.$$.fragment,Ul),Ul.forEach(l),_h=n(A),$e=i(A,"DIV",{class:!0});var ka=$($e);p(is.$$.fragment,ka),uh=n(ka),rl=i(ka,"P",{"data-svelte-h":!0}),g(rl)!=="svelte-rvubqa"&&(rl.innerHTML=eL),hh=n(ka),nl=i(ka,"P",{"data-svelte-h":!0}),g(nl)!=="svelte-x8llv0"&&(nl.textContent=oL),gh=n(ka),p(Ma.$$.fragment,ka),ka.forEach(l),xh=n(A),uo=i(A,"DIV",{class:!0});var Vl=$(uo);p(ds.$$.fragment,Vl),Lh=n(Vl),sl=i(Vl,"P",{"data-svelte-h":!0}),g(sl)!=="svelte-ioswce"&&(sl.innerHTML=tL),bh=n(Vl),p(Ta.$$.fragment,Vl),Vl.forEach(l),wh=n(A),ho=i(A,"DIV",{class:!0});var Il=$(ho);p(ls.$$.fragment,Il),vh=n(Il),il=i(Il,"P",{"data-svelte-h":!0}),g(il)!=="svelte-119cgd9"&&(il.textContent=aL),$h=n(Il),p(Da.$$.fragment,Il),Il.forEach(l),yh=n(A),Ca=i(A,"DIV",{class:!0});var tf=$(Ca);p(cs.$$.fragment,tf),Mh=n(tf),dl=i(tf,"P",{"data-svelte-h":!0}),g(dl)!=="svelte-1rtya5j"&&(dl.textContent=rL),tf.forEach(l),A.forEach(l),wc=n(e),p(fs.$$.fragment,e),vc=n(e),Wl=i(e,"P",{}),$(Wl).forEach(l),this.h()},h(){y(t,"name","hf:doc:metadata"),y(t,"content",db),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(Ce,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),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(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(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(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(jo,"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(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(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(qo,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(C,"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(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(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(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(Qo,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(X,"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(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(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(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(ot,"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(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(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(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(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(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(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(V,"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(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(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(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(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(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(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(_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(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(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(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(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(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(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($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(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(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(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(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(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(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(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(Vt,"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(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(Jt,"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(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(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(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(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(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(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(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(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(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(fa,"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(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(_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(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(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(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(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(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(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(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($a,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y(_o,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),y($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(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(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(S,"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),b(e,L,x),b(e,c,x),b(e,d,x),m(w,e,x),b(e,a,x),b(e,v,x),b(e,Xl,x),b(e,Ra,x),b(e,Fl,x),m(Vo,e,x),b(e,Jl,x),m(Aa,e,x),b(e,Pl,x),b(e,C,x),m(Ua,C,null),o(C,af),o(C,As),o(C,rf),o(C,De),m(Va,De,null),o(De,nf),o(De,Us),o(De,sf),m(Io,De,null),o(C,df),o(C,Ce),m(Ia,Ce,null),o(Ce,lf),o(Ce,Vs),o(Ce,cf),m(Wo,Ce,null),o(C,ff),o(C,Se),m(Wa,Se,null),o(Se,pf),o(Se,Is),o(Se,mf),m(Xo,Se,null),o(C,_f),o(C,Fo),m(Xa,Fo,null),o(Fo,uf),o(Fo,Ws),o(C,hf),o(C,be),m(Fa,be,null),o(be,gf),o(be,Xs),o(be,xf),m(Jo,be,null),o(be,Lf),m(Po,be,null),o(C,bf),o(C,ke),m(Ja,ke,null),o(ke,wf),o(ke,Fs),o(ke,vf),m(Ho,ke,null),o(C,$f),o(C,jo),m(Pa,jo,null),o(jo,yf),o(jo,Js),o(C,Mf),o(C,Re),m(Ha,Re,null),o(Re,Tf),o(Re,Ps),o(Re,Df),m(Zo,Re,null),o(C,Cf),o(C,we),m(ja,we,null),o(we,Sf),o(we,Hs),o(we,kf),o(we,js),o(we,Rf),m(Go,we,null),o(C,Af),o(C,Ae),m(Za,Ae,null),o(Ae,Uf),o(Ae,Zs),o(Ae,Vf),m(Bo,Ae,null),o(C,If),o(C,Ue),m(Ga,Ue,null),o(Ue,Wf),o(Ue,Gs),o(Ue,Xf),m(Eo,Ue,null),o(C,Ff),o(C,qo),m(Ba,qo,null),o(qo,Jf),o(qo,Bs),b(e,Hl,x),m(Ea,e,x),b(e,jl,x),b(e,X,x),m(qa,X,null),o(X,Pf),o(X,Es),o(X,Hf),o(X,No),m(Na,No,null),o(No,jf),o(No,qs),o(X,Zf),o(X,zo),m(za,zo,null),o(zo,Gf),o(zo,Ns),o(X,Bf),o(X,ae),m(Ya,ae,null),o(ae,Ef),o(ae,zs),o(ae,qf),o(ae,Ys),o(ae,Nf),o(ae,Qs),o(ae,zf),o(ae,Os),o(ae,Yf),o(ae,Ks),o(X,Qf),o(X,Ve),m(Qa,Ve,null),o(Ve,Of),o(Ve,ei),o(Ve,Kf),m(Yo,Ve,null),o(X,ep),o(X,Qo),m(Oa,Qo,null),o(Qo,op),o(Qo,oi),b(e,Zl,x),m(Ka,e,x),b(e,Gl,x),b(e,F,x),m(er,F,null),o(F,tp),o(F,ti),o(F,ap),o(F,Oo),m(or,Oo,null),o(Oo,rp),o(Oo,ai),o(F,np),o(F,Ko),m(tr,Ko,null),o(Ko,sp),o(Ko,ri),o(F,ip),o(F,re),m(ar,re,null),o(re,dp),o(re,ni),o(re,lp),o(re,si),o(re,cp),o(re,ii),o(re,fp),o(re,di),o(re,pp),o(re,li),o(F,mp),o(F,Ie),m(rr,Ie,null),o(Ie,_p),o(Ie,ci),o(Ie,up),m(et,Ie,null),o(F,hp),o(F,ot),m(nr,ot,null),o(ot,gp),o(ot,fi),b(e,Bl,x),m(sr,e,x),b(e,El,x),b(e,V,x),m(ir,V,null),o(V,xp),o(V,pi),o(V,Lp),o(V,mi),o(V,bp),o(V,tt),m(dr,tt,null),o(tt,wp),o(tt,_i),o(V,vp),o(V,at),m(lr,at,null),o(at,$p),o(at,ui),o(V,yp),o(V,ie),m(cr,ie,null),o(ie,Mp),o(ie,hi),o(ie,Tp),o(ie,gi),o(ie,Dp),o(ie,xi),o(ie,Cp),o(ie,Li),o(V,Sp),o(V,We),m(fr,We,null),o(We,kp),o(We,bi),o(We,Rp),m(rt,We,null),o(V,Ap),o(V,nt),m(pr,nt,null),o(nt,Up),o(nt,wi),o(V,Vp),o(V,Xe),m(mr,Xe,null),o(Xe,Ip),o(Xe,vi),o(Xe,Wp),m(st,Xe,null),b(e,ql,x),m(_r,e,x),b(e,Nl,x),b(e,U,x),m(ur,U,null),o(U,Xp),o(U,$i),o(U,Fp),o(U,yi),o(U,Jp),o(U,it),m(hr,it,null),o(it,Pp),o(it,Mi),o(U,Hp),o(U,dt),m(gr,dt,null),o(dt,jp),o(dt,Ti),o(U,Zp),o(U,de),m(xr,de,null),o(de,Gp),o(de,Di),o(de,Bp),o(de,Ci),o(de,Ep),o(de,Si),o(de,qp),o(de,ki),o(U,Np),o(U,Fe),m(Lr,Fe,null),o(Fe,zp),o(Fe,Ri),o(Fe,Yp),m(lt,Fe,null),o(U,Qp),o(U,ct),m(br,ct,null),o(ct,Op),o(ct,Ai),o(U,Kp),o(U,Je),m(wr,Je,null),o(Je,em),o(Je,Ui),o(Je,om),m(ft,Je,null),o(U,tm),o(U,Pe),m(vr,Pe,null),o(Pe,am),o(Pe,Vi),o(Pe,rm),m(pt,Pe,null),b(e,zl,x),m($r,e,x),b(e,Yl,x),b(e,J,x),m(yr,J,null),o(J,nm),o(J,Ii),o(J,sm),o(J,mt),m(Mr,mt,null),o(mt,im),o(mt,Wi),o(J,dm),o(J,_t),m(Tr,_t,null),o(_t,lm),o(_t,Xi),o(J,cm),o(J,He),m(Dr,He,null),o(He,fm),o(He,Fi),o(He,pm),m(ut,He,null),o(J,mm),o(J,ht),m(Cr,ht,null),o(ht,_m),o(ht,Ji),o(J,um),o(J,je),m(Sr,je,null),o(je,hm),o(je,Pi),o(je,gm),m(gt,je,null),b(e,Ql,x),m(kr,e,x),b(e,Ol,x),b(e,P,x),m(Rr,P,null),o(P,xm),o(P,Hi),o(P,Lm),o(P,xt),m(Ar,xt,null),o(xt,bm),o(xt,ji),o(P,wm),o(P,Lt),m(Ur,Lt,null),o(Lt,vm),o(Lt,Zi),o(P,$m),o(P,Ze),m(Vr,Ze,null),o(Ze,ym),o(Ze,Gi),o(Ze,Mm),m(bt,Ze,null),o(P,Tm),o(P,wt),m(Ir,wt,null),o(wt,Dm),o(wt,Bi),o(P,Cm),o(P,Ge),m(Wr,Ge,null),o(Ge,Sm),o(Ge,Ei),o(Ge,km),m(vt,Ge,null),b(e,Kl,x),m(Xr,e,x),b(e,ec,x),b(e,H,x),m(Fr,H,null),o(H,Rm),o(H,qi),o(H,Am),o(H,$t),m(Jr,$t,null),o($t,Um),o($t,Ni),o(H,Vm),o(H,yt),m(Pr,yt,null),o(yt,Im),o(yt,zi),o(H,Wm),o(H,Be),m(Hr,Be,null),o(Be,Xm),o(Be,Yi),o(Be,Fm),m(Mt,Be,null),o(H,Jm),o(H,Tt),m(jr,Tt,null),o(Tt,Pm),o(Tt,Qi),o(H,Hm),o(H,Ee),m(Zr,Ee,null),o(Ee,jm),o(Ee,Oi),o(Ee,Zm),m(Dt,Ee,null),b(e,oc,x),m(Gr,e,x),b(e,tc,x),b(e,j,x),m(Br,j,null),o(j,Gm),o(j,Ki),o(j,Bm),o(j,Ct),m(Er,Ct,null),o(Ct,Em),o(Ct,ed),o(j,qm),o(j,St),m(qr,St,null),o(St,Nm),o(St,od),o(j,zm),o(j,qe),m(Nr,qe,null),o(qe,Ym),o(qe,td),o(qe,Qm),m(kt,qe,null),o(j,Om),o(j,Rt),m(zr,Rt,null),o(Rt,Km),o(Rt,ad),o(j,e_),o(j,Ne),m(Yr,Ne,null),o(Ne,o_),o(Ne,rd),o(Ne,t_),m(At,Ne,null),b(e,ac,x),m(Qr,e,x),b(e,rc,x),b(e,Z,x),m(Or,Z,null),o(Z,a_),o(Z,nd),o(Z,r_),o(Z,Ut),m(Kr,Ut,null),o(Ut,n_),o(Ut,sd),o(Z,s_),o(Z,Vt),m(en,Vt,null),o(Vt,i_),o(Vt,id),o(Z,d_),o(Z,ze),m(on,ze,null),o(ze,l_),o(ze,dd),o(ze,c_),m(It,ze,null),o(Z,f_),o(Z,Wt),m(tn,Wt,null),o(Wt,p_),o(Wt,ld),o(Z,m_),o(Z,Ye),m(an,Ye,null),o(Ye,__),o(Ye,cd),o(Ye,u_),m(Xt,Ye,null),b(e,nc,x),m(rn,e,x),b(e,sc,x),b(e,G,x),m(nn,G,null),o(G,h_),o(G,fd),o(G,g_),o(G,Ft),m(sn,Ft,null),o(Ft,x_),o(Ft,pd),o(G,L_),o(G,Jt),m(dn,Jt,null),o(Jt,b_),o(Jt,md),o(G,w_),o(G,Qe),m(ln,Qe,null),o(Qe,v_),o(Qe,_d),o(Qe,$_),m(Pt,Qe,null),o(G,y_),o(G,Ht),m(cn,Ht,null),o(Ht,M_),o(Ht,ud),o(G,T_),o(G,Oe),m(fn,Oe,null),o(Oe,D_),o(Oe,hd),o(Oe,C_),m(jt,Oe,null),b(e,ic,x),m(pn,e,x),b(e,dc,x),b(e,B,x),m(mn,B,null),o(B,S_),o(B,gd),o(B,k_),o(B,Zt),m(_n,Zt,null),o(Zt,R_),o(Zt,xd),o(B,A_),o(B,Gt),m(un,Gt,null),o(Gt,U_),o(Gt,Ld),o(B,V_),o(B,Ke),m(hn,Ke,null),o(Ke,I_),o(Ke,bd),o(Ke,W_),m(Bt,Ke,null),o(B,X_),o(B,Et),m(gn,Et,null),o(Et,F_),o(Et,wd),o(B,J_),o(B,eo),m(xn,eo,null),o(eo,P_),o(eo,vd),o(eo,H_),m(qt,eo,null),b(e,lc,x),m(Ln,e,x),b(e,cc,x),b(e,E,x),m(bn,E,null),o(E,j_),o(E,$d),o(E,Z_),o(E,Nt),m(wn,Nt,null),o(Nt,G_),o(Nt,yd),o(E,B_),o(E,zt),m(vn,zt,null),o(zt,E_),o(zt,Md),o(E,q_),o(E,oo),m($n,oo,null),o(oo,N_),o(oo,Td),o(oo,z_),m(Yt,oo,null),o(E,Y_),o(E,Qt),m(yn,Qt,null),o(Qt,Q_),o(Qt,Dd),o(E,O_),o(E,to),m(Mn,to,null),o(to,K_),o(to,Cd),o(to,eu),m(Ot,to,null),b(e,fc,x),m(Tn,e,x),b(e,pc,x),b(e,q,x),m(Dn,q,null),o(q,ou),o(q,Sd),o(q,tu),o(q,Kt),m(Cn,Kt,null),o(Kt,au),o(Kt,kd),o(q,ru),o(q,ea),m(Sn,ea,null),o(ea,nu),o(ea,Rd),o(q,su),o(q,ao),m(kn,ao,null),o(ao,iu),o(ao,Ad),o(ao,du),m(oa,ao,null),o(q,lu),o(q,ta),m(Rn,ta,null),o(ta,cu),o(ta,Ud),o(q,fu),o(q,ro),m(An,ro,null),o(ro,pu),o(ro,Vd),o(ro,mu),m(aa,ro,null),b(e,mc,x),m(Un,e,x),b(e,_c,x),b(e,N,x),m(Vn,N,null),o(N,_u),o(N,Id),o(N,uu),o(N,ra),m(In,ra,null),o(ra,hu),o(ra,Wd),o(N,gu),o(N,na),m(Wn,na,null),o(na,xu),o(na,Xd),o(N,Lu),o(N,no),m(Xn,no,null),o(no,bu),o(no,Fd),o(no,wu),m(sa,no,null),o(N,vu),o(N,ia),m(Fn,ia,null),o(ia,$u),o(ia,Jd),o(N,yu),o(N,so),m(Jn,so,null),o(so,Mu),o(so,Pd),o(so,Tu),m(da,so,null),b(e,uc,x),m(Pn,e,x),b(e,hc,x),b(e,ye,x),m(Hn,ye,null),o(ye,Du),o(ye,la),m(jn,la,null),o(la,Cu),o(la,Hd),o(ye,Su),o(ye,ca),m(Zn,ca,null),o(ca,ku),o(ca,jd),b(e,gc,x),m(Gn,e,x),b(e,xc,x),b(e,z,x),m(Bn,z,null),o(z,Ru),o(z,Zd),o(z,Au),o(z,fa),m(En,fa,null),o(fa,Uu),o(fa,Gd),o(z,Vu),o(z,pa),m(qn,pa,null),o(pa,Iu),o(pa,Bd),o(z,Wu),o(z,io),m(Nn,io,null),o(io,Xu),o(io,Ed),o(io,Fu),m(ma,io,null),o(z,Ju),o(z,_a),m(zn,_a,null),o(_a,Pu),o(_a,qd),o(z,Hu),o(z,lo),m(Yn,lo,null),o(lo,ju),o(lo,Nd),o(lo,Zu),m(ua,lo,null),b(e,Lc,x),m(Qn,e,x),b(e,bc,x),b(e,S,x),m(On,S,null),o(S,Gu),o(S,zd),o(S,Bu),o(S,co),m(Kn,co,null),o(co,Eu),o(co,Yd),o(co,qu),m(ha,co,null),o(S,Nu),o(S,fo),m(es,fo,null),o(fo,zu),o(fo,Qd),o(fo,Yu),m(ga,fo,null),o(S,Qu),o(S,po),m(os,po,null),o(po,Ou),o(po,Od),o(po,Ku),m(xa,po,null),o(S,eh),o(S,La),m(ts,La,null),o(La,oh),o(La,Kd),o(S,th),o(S,ve),m(as,ve,null),o(ve,ah),o(ve,el),o(ve,rh),m(ba,ve,null),o(ve,nh),m(wa,ve,null),o(S,sh),o(S,mo),m(rs,mo,null),o(mo,ih),o(mo,ol),o(mo,dh),m(va,mo,null),o(S,lh),o(S,$a),m(ns,$a,null),o($a,ch),o($a,tl),o(S,fh),o(S,_o),m(ss,_o,null),o(_o,ph),o(_o,al),o(_o,mh),m(ya,_o,null),o(S,_h),o(S,$e),m(is,$e,null),o($e,uh),o($e,rl),o($e,hh),o($e,nl),o($e,gh),m(Ma,$e,null),o(S,xh),o(S,uo),m(ds,uo,null),o(uo,Lh),o(uo,sl),o(uo,bh),m(Ta,uo,null),o(S,wh),o(S,ho),m(ls,ho,null),o(ho,vh),o(ho,il),o(ho,$h),m(Da,ho,null),o(S,yh),o(S,Ca),m(cs,Ca,null),o(Ca,Mh),o(Ca,dl),b(e,wc,x),m(fs,e,x),b(e,vc,x),b(e,Wl,x),$c=!0},p(e,[x]){const R={};x&2&&(R.$$scope={dirty:x,ctx:e}),Vo.$set(R);const go={};x&2&&(go.$$scope={dirty:x,ctx:e}),Io.$set(go);const xo={};x&2&&(xo.$$scope={dirty:x,ctx:e}),Wo.$set(xo);const Lo={};x&2&&(Lo.$$scope={dirty:x,ctx:e}),Xo.$set(Lo);const ps={};x&2&&(ps.$$scope={dirty:x,ctx:e}),Jo.$set(ps);const Me={};x&2&&(Me.$$scope={dirty:x,ctx:e}),Po.$set(Me);const bo={};x&2&&(bo.$$scope={dirty:x,ctx:e}),Ho.$set(bo);const ms={};x&2&&(ms.$$scope={dirty:x,ctx:e}),Zo.$set(ms);const wo={};x&2&&(wo.$$scope={dirty:x,ctx:e}),Go.$set(wo);const Te={};x&2&&(Te.$$scope={dirty:x,ctx:e}),Bo.$set(Te);const vo={};x&2&&(vo.$$scope={dirty:x,ctx:e}),Eo.$set(vo);const $o={};x&2&&($o.$$scope={dirty:x,ctx:e}),Yo.$set($o);const _s={};x&2&&(_s.$$scope={dirty:x,ctx:e}),et.$set(_s);const Q={};x&2&&(Q.$$scope={dirty:x,ctx:e}),rt.$set(Q);const us={};x&2&&(us.$$scope={dirty:x,ctx:e}),st.$set(us);const hs={};x&2&&(hs.$$scope={dirty:x,ctx:e}),lt.$set(hs);const ne={};x&2&&(ne.$$scope={dirty:x,ctx:e}),ft.$set(ne);const yo={};x&2&&(yo.$$scope={dirty:x,ctx:e}),pt.$set(yo);const gs={};x&2&&(gs.$$scope={dirty:x,ctx:e}),ut.$set(gs);const O={};x&2&&(O.$$scope={dirty:x,ctx:e}),gt.$set(O);const xs={};x&2&&(xs.$$scope={dirty:x,ctx:e}),bt.$set(xs);const Ls={};x&2&&(Ls.$$scope={dirty:x,ctx:e}),vt.$set(Ls);const se={};x&2&&(se.$$scope={dirty:x,ctx:e}),Mt.$set(se);const Mo={};x&2&&(Mo.$$scope={dirty:x,ctx:e}),Dt.$set(Mo);const bs={};x&2&&(bs.$$scope={dirty:x,ctx:e}),kt.$set(bs);const W={};x&2&&(W.$$scope={dirty:x,ctx:e}),At.$set(W);const ws={};x&2&&(ws.$$scope={dirty:x,ctx:e}),It.$set(ws);const vs={};x&2&&(vs.$$scope={dirty:x,ctx:e}),Xt.$set(vs);const xe={};x&2&&(xe.$$scope={dirty:x,ctx:e}),Pt.$set(xe);const To={};x&2&&(To.$$scope={dirty:x,ctx:e}),jt.$set(To);const $s={};x&2&&($s.$$scope={dirty:x,ctx:e}),Bt.$set($s);const Do={};x&2&&(Do.$$scope={dirty:x,ctx:e}),qt.$set(Do);const I={};x&2&&(I.$$scope={dirty:x,ctx:e}),Yt.$set(I);const ys={};x&2&&(ys.$$scope={dirty:x,ctx:e}),Ot.$set(ys);const Ms={};x&2&&(Ms.$$scope={dirty:x,ctx:e}),oa.$set(Ms);const Le={};x&2&&(Le.$$scope={dirty:x,ctx:e}),aa.$set(Le);const Co={};x&2&&(Co.$$scope={dirty:x,ctx:e}),sa.$set(Co);const Ts={};x&2&&(Ts.$$scope={dirty:x,ctx:e}),da.$set(Ts);const So={};x&2&&(So.$$scope={dirty:x,ctx:e}),ma.$set(So);const ko={};x&2&&(ko.$$scope={dirty:x,ctx:e}),ua.$set(ko);const K={};x&2&&(K.$$scope={dirty:x,ctx:e}),ha.$set(K);const Ds={};x&2&&(Ds.$$scope={dirty:x,ctx:e}),ga.$set(Ds);const Cs={};x&2&&(Cs.$$scope={dirty:x,ctx:e}),xa.$set(Cs);const Ro={};x&2&&(Ro.$$scope={dirty:x,ctx:e}),ba.$set(Ro);const Ss={};x&2&&(Ss.$$scope={dirty:x,ctx:e}),wa.$set(Ss);const Ao={};x&2&&(Ao.$$scope={dirty:x,ctx:e}),va.$set(Ao);const ee={};x&2&&(ee.$$scope={dirty:x,ctx:e}),ya.$set(ee);const ks={};x&2&&(ks.$$scope={dirty:x,ctx:e}),Ma.$set(ks);const Rs={};x&2&&(Rs.$$scope={dirty:x,ctx:e}),Ta.$set(Rs);const Uo={};x&2&&(Uo.$$scope={dirty:x,ctx:e}),Da.$set(Uo)},i(e){$c||(_(w.$$.fragment,e),_(Vo.$$.fragment,e),_(Aa.$$.fragment,e),_(Ua.$$.fragment,e),_(Va.$$.fragment,e),_(Io.$$.fragment,e),_(Ia.$$.fragment,e),_(Wo.$$.fragment,e),_(Wa.$$.fragment,e),_(Xo.$$.fragment,e),_(Xa.$$.fragment,e),_(Fa.$$.fragment,e),_(Jo.$$.fragment,e),_(Po.$$.fragment,e),_(Ja.$$.fragment,e),_(Ho.$$.fragment,e),_(Pa.$$.fragment,e),_(Ha.$$.fragment,e),_(Zo.$$.fragment,e),_(ja.$$.fragment,e),_(Go.$$.fragment,e),_(Za.$$.fragment,e),_(Bo.$$.fragment,e),_(Ga.$$.fragment,e),_(Eo.$$.fragment,e),_(Ba.$$.fragment,e),_(Ea.$$.fragment,e),_(qa.$$.fragment,e),_(Na.$$.fragment,e),_(za.$$.fragment,e),_(Ya.$$.fragment,e),_(Qa.$$.fragment,e),_(Yo.$$.fragment,e),_(Oa.$$.fragment,e),_(Ka.$$.fragment,e),_(er.$$.fragment,e),_(or.$$.fragment,e),_(tr.$$.fragment,e),_(ar.$$.fragment,e),_(rr.$$.fragment,e),_(et.$$.fragment,e),_(nr.$$.fragment,e),_(sr.$$.fragment,e),_(ir.$$.fragment,e),_(dr.$$.fragment,e),_(lr.$$.fragment,e),_(cr.$$.fragment,e),_(fr.$$.fragment,e),_(rt.$$.fragment,e),_(pr.$$.fragment,e),_(mr.$$.fragment,e),_(st.$$.fragment,e),_(_r.$$.fragment,e),_(ur.$$.fragment,e),_(hr.$$.fragment,e),_(gr.$$.fragment,e),_(xr.$$.fragment,e),_(Lr.$$.fragment,e),_(lt.$$.fragment,e),_(br.$$.fragment,e),_(wr.$$.fragment,e),_(ft.$$.fragment,e),_(vr.$$.fragment,e),_(pt.$$.fragment,e),_($r.$$.fragment,e),_(yr.$$.fragment,e),_(Mr.$$.fragment,e),_(Tr.$$.fragment,e),_(Dr.$$.fragment,e),_(ut.$$.fragment,e),_(Cr.$$.fragment,e),_(Sr.$$.fragment,e),_(gt.$$.fragment,e),_(kr.$$.fragment,e),_(Rr.$$.fragment,e),_(Ar.$$.fragment,e),_(Ur.$$.fragment,e),_(Vr.$$.fragment,e),_(bt.$$.fragment,e),_(Ir.$$.fragment,e),_(Wr.$$.fragment,e),_(vt.$$.fragment,e),_(Xr.$$.fragment,e),_(Fr.$$.fragment,e),_(Jr.$$.fragment,e),_(Pr.$$.fragment,e),_(Hr.$$.fragment,e),_(Mt.$$.fragment,e),_(jr.$$.fragment,e),_(Zr.$$.fragment,e),_(Dt.$$.fragment,e),_(Gr.$$.fragment,e),_(Br.$$.fragment,e),_(Er.$$.fragment,e),_(qr.$$.fragment,e),_(Nr.$$.fragment,e),_(kt.$$.fragment,e),_(zr.$$.fragment,e),_(Yr.$$.fragment,e),_(At.$$.fragment,e),_(Qr.$$.fragment,e),_(Or.$$.fragment,e),_(Kr.$$.fragment,e),_(en.$$.fragment,e),_(on.$$.fragment,e),_(It.$$.fragment,e),_(tn.$$.fragment,e),_(an.$$.fragment,e),_(Xt.$$.fragment,e),_(rn.$$.fragment,e),_(nn.$$.fragment,e),_(sn.$$.fragment,e),_(dn.$$.fragment,e),_(ln.$$.fragment,e),_(Pt.$$.fragment,e),_(cn.$$.fragment,e),_(fn.$$.fragment,e),_(jt.$$.fragment,e),_(pn.$$.fragment,e),_(mn.$$.fragment,e),_(_n.$$.fragment,e),_(un.$$.fragment,e),_(hn.$$.fragment,e),_(Bt.$$.fragment,e),_(gn.$$.fragment,e),_(xn.$$.fragment,e),_(qt.$$.fragment,e),_(Ln.$$.fragment,e),_(bn.$$.fragment,e),_(wn.$$.fragment,e),_(vn.$$.fragment,e),_($n.$$.fragment,e),_(Yt.$$.fragment,e),_(yn.$$.fragment,e),_(Mn.$$.fragment,e),_(Ot.$$.fragment,e),_(Tn.$$.fragment,e),_(Dn.$$.fragment,e),_(Cn.$$.fragment,e),_(Sn.$$.fragment,e),_(kn.$$.fragment,e),_(oa.$$.fragment,e),_(Rn.$$.fragment,e),_(An.$$.fragment,e),_(aa.$$.fragment,e),_(Un.$$.fragment,e),_(Vn.$$.fragment,e),_(In.$$.fragment,e),_(Wn.$$.fragment,e),_(Xn.$$.fragment,e),_(sa.$$.fragment,e),_(Fn.$$.fragment,e),_(Jn.$$.fragment,e),_(da.$$.fragment,e),_(Pn.$$.fragment,e),_(Hn.$$.fragment,e),_(jn.$$.fragment,e),_(Zn.$$.fragment,e),_(Gn.$$.fragment,e),_(Bn.$$.fragment,e),_(En.$$.fragment,e),_(qn.$$.fragment,e),_(Nn.$$.fragment,e),_(ma.$$.fragment,e),_(zn.$$.fragment,e),_(Yn.$$.fragment,e),_(ua.$$.fragment,e),_(Qn.$$.fragment,e),_(On.$$.fragment,e),_(Kn.$$.fragment,e),_(ha.$$.fragment,e),_(es.$$.fragment,e),_(ga.$$.fragment,e),_(os.$$.fragment,e),_(xa.$$.fragment,e),_(ts.$$.fragment,e),_(as.$$.fragment,e),_(ba.$$.fragment,e),_(wa.$$.fragment,e),_(rs.$$.fragment,e),_(va.$$.fragment,e),_(ns.$$.fragment,e),_(ss.$$.fragment,e),_(ya.$$.fragment,e),_(is.$$.fragment,e),_(Ma.$$.fragment,e),_(ds.$$.fragment,e),_(Ta.$$.fragment,e),_(ls.$$.fragment,e),_(Da.$$.fragment,e),_(cs.$$.fragment,e),_(fs.$$.fragment,e),$c=!0)},o(e){u(w.$$.fragment,e),u(Vo.$$.fragment,e),u(Aa.$$.fragment,e),u(Ua.$$.fragment,e),u(Va.$$.fragment,e),u(Io.$$.fragment,e),u(Ia.$$.fragment,e),u(Wo.$$.fragment,e),u(Wa.$$.fragment,e),u(Xo.$$.fragment,e),u(Xa.$$.fragment,e),u(Fa.$$.fragment,e),u(Jo.$$.fragment,e),u(Po.$$.fragment,e),u(Ja.$$.fragment,e),u(Ho.$$.fragment,e),u(Pa.$$.fragment,e),u(Ha.$$.fragment,e),u(Zo.$$.fragment,e),u(ja.$$.fragment,e),u(Go.$$.fragment,e),u(Za.$$.fragment,e),u(Bo.$$.fragment,e),u(Ga.$$.fragment,e),u(Eo.$$.fragment,e),u(Ba.$$.fragment,e),u(Ea.$$.fragment,e),u(qa.$$.fragment,e),u(Na.$$.fragment,e),u(za.$$.fragment,e),u(Ya.$$.fragment,e),u(Qa.$$.fragment,e),u(Yo.$$.fragment,e),u(Oa.$$.fragment,e),u(Ka.$$.fragment,e),u(er.$$.fragment,e),u(or.$$.fragment,e),u(tr.$$.fragment,e),u(ar.$$.fragment,e),u(rr.$$.fragment,e),u(et.$$.fragment,e),u(nr.$$.fragment,e),u(sr.$$.fragment,e),u(ir.$$.fragment,e),u(dr.$$.fragment,e),u(lr.$$.fragment,e),u(cr.$$.fragment,e),u(fr.$$.fragment,e),u(rt.$$.fragment,e),u(pr.$$.fragment,e),u(mr.$$.fragment,e),u(st.$$.fragment,e),u(_r.$$.fragment,e),u(ur.$$.fragment,e),u(hr.$$.fragment,e),u(gr.$$.fragment,e),u(xr.$$.fragment,e),u(Lr.$$.fragment,e),u(lt.$$.fragment,e),u(br.$$.fragment,e),u(wr.$$.fragment,e),u(ft.$$.fragment,e),u(vr.$$.fragment,e),u(pt.$$.fragment,e),u($r.$$.fragment,e),u(yr.$$.fragment,e),u(Mr.$$.fragment,e),u(Tr.$$.fragment,e),u(Dr.$$.fragment,e),u(ut.$$.fragment,e),u(Cr.$$.fragment,e),u(Sr.$$.fragment,e),u(gt.$$.fragment,e),u(kr.$$.fragment,e),u(Rr.$$.fragment,e),u(Ar.$$.fragment,e),u(Ur.$$.fragment,e),u(Vr.$$.fragment,e),u(bt.$$.fragment,e),u(Ir.$$.fragment,e),u(Wr.$$.fragment,e),u(vt.$$.fragment,e),u(Xr.$$.fragment,e),u(Fr.$$.fragment,e),u(Jr.$$.fragment,e),u(Pr.$$.fragment,e),u(Hr.$$.fragment,e),u(Mt.$$.fragment,e),u(jr.$$.fragment,e),u(Zr.$$.fragment,e),u(Dt.$$.fragment,e),u(Gr.$$.fragment,e),u(Br.$$.fragment,e),u(Er.$$.fragment,e),u(qr.$$.fragment,e),u(Nr.$$.fragment,e),u(kt.$$.fragment,e),u(zr.$$.fragment,e),u(Yr.$$.fragment,e),u(At.$$.fragment,e),u(Qr.$$.fragment,e),u(Or.$$.fragment,e),u(Kr.$$.fragment,e),u(en.$$.fragment,e),u(on.$$.fragment,e),u(It.$$.fragment,e),u(tn.$$.fragment,e),u(an.$$.fragment,e),u(Xt.$$.fragment,e),u(rn.$$.fragment,e),u(nn.$$.fragment,e),u(sn.$$.fragment,e),u(dn.$$.fragment,e),u(ln.$$.fragment,e),u(Pt.$$.fragment,e),u(cn.$$.fragment,e),u(fn.$$.fragment,e),u(jt.$$.fragment,e),u(pn.$$.fragment,e),u(mn.$$.fragment,e),u(_n.$$.fragment,e),u(un.$$.fragment,e),u(hn.$$.fragment,e),u(Bt.$$.fragment,e),u(gn.$$.fragment,e),u(xn.$$.fragment,e),u(qt.$$.fragment,e),u(Ln.$$.fragment,e),u(bn.$$.fragment,e),u(wn.$$.fragment,e),u(vn.$$.fragment,e),u($n.$$.fragment,e),u(Yt.$$.fragment,e),u(yn.$$.fragment,e),u(Mn.$$.fragment,e),u(Ot.$$.fragment,e),u(Tn.$$.fragment,e),u(Dn.$$.fragment,e),u(Cn.$$.fragment,e),u(Sn.$$.fragment,e),u(kn.$$.fragment,e),u(oa.$$.fragment,e),u(Rn.$$.fragment,e),u(An.$$.fragment,e),u(aa.$$.fragment,e),u(Un.$$.fragment,e),u(Vn.$$.fragment,e),u(In.$$.fragment,e),u(Wn.$$.fragment,e),u(Xn.$$.fragment,e),u(sa.$$.fragment,e),u(Fn.$$.fragment,e),u(Jn.$$.fragment,e),u(da.$$.fragment,e),u(Pn.$$.fragment,e),u(Hn.$$.fragment,e),u(jn.$$.fragment,e),u(Zn.$$.fragment,e),u(Gn.$$.fragment,e),u(Bn.$$.fragment,e),u(En.$$.fragment,e),u(qn.$$.fragment,e),u(Nn.$$.fragment,e),u(ma.$$.fragment,e),u(zn.$$.fragment,e),u(Yn.$$.fragment,e),u(ua.$$.fragment,e),u(Qn.$$.fragment,e),u(On.$$.fragment,e),u(Kn.$$.fragment,e),u(ha.$$.fragment,e),u(es.$$.fragment,e),u(ga.$$.fragment,e),u(os.$$.fragment,e),u(xa.$$.fragment,e),u(ts.$$.fragment,e),u(as.$$.fragment,e),u(ba.$$.fragment,e),u(wa.$$.fragment,e),u(rs.$$.fragment,e),u(va.$$.fragment,e),u(ns.$$.fragment,e),u(ss.$$.fragment,e),u(ya.$$.fragment,e),u(is.$$.fragment,e),u(Ma.$$.fragment,e),u(ds.$$.fragment,e),u(Ta.$$.fragment,e),u(ls.$$.fragment,e),u(Da.$$.fragment,e),u(cs.$$.fragment,e),u(fs.$$.fragment,e),$c=!1},d(e){e&&(l(L),l(c),l(d),l(a),l(v),l(Xl),l(Ra),l(Fl),l(Jl),l(Pl),l(C),l(Hl),l(jl),l(X),l(Zl),l(Gl),l(F),l(Bl),l(El),l(V),l(ql),l(Nl),l(U),l(zl),l(Yl),l(J),l(Ql),l(Ol),l(P),l(Kl),l(ec),l(H),l(oc),l(tc),l(j),l(ac),l(rc),l(Z),l(nc),l(sc),l(G),l(ic),l(dc),l(B),l(lc),l(cc),l(E),l(fc),l(pc),l(q),l(mc),l(_c),l(N),l(uc),l(hc),l(ye),l(gc),l(xc),l(z),l(Lc),l(bc),l(S),l(wc),l(vc),l(Wl)),l(t),h(w,e),h(Vo,e),h(Aa,e),h(Ua),h(Va),h(Io),h(Ia),h(Wo),h(Wa),h(Xo),h(Xa),h(Fa),h(Jo),h(Po),h(Ja),h(Ho),h(Pa),h(Ha),h(Zo),h(ja),h(Go),h(Za),h(Bo),h(Ga),h(Eo),h(Ba),h(Ea,e),h(qa),h(Na),h(za),h(Ya),h(Qa),h(Yo),h(Oa),h(Ka,e),h(er),h(or),h(tr),h(ar),h(rr),h(et),h(nr),h(sr,e),h(ir),h(dr),h(lr),h(cr),h(fr),h(rt),h(pr),h(mr),h(st),h(_r,e),h(ur),h(hr),h(gr),h(xr),h(Lr),h(lt),h(br),h(wr),h(ft),h(vr),h(pt),h($r,e),h(yr),h(Mr),h(Tr),h(Dr),h(ut),h(Cr),h(Sr),h(gt),h(kr,e),h(Rr),h(Ar),h(Ur),h(Vr),h(bt),h(Ir),h(Wr),h(vt),h(Xr,e),h(Fr),h(Jr),h(Pr),h(Hr),h(Mt),h(jr),h(Zr),h(Dt),h(Gr,e),h(Br),h(Er),h(qr),h(Nr),h(kt),h(zr),h(Yr),h(At),h(Qr,e),h(Or),h(Kr),h(en),h(on),h(It),h(tn),h(an),h(Xt),h(rn,e),h(nn),h(sn),h(dn),h(ln),h(Pt),h(cn),h(fn),h(jt),h(pn,e),h(mn),h(_n),h(un),h(hn),h(Bt),h(gn),h(xn),h(qt),h(Ln,e),h(bn),h(wn),h(vn),h($n),h(Yt),h(yn),h(Mn),h(Ot),h(Tn,e),h(Dn),h(Cn),h(Sn),h(kn),h(oa),h(Rn),h(An),h(aa),h(Un,e),h(Vn),h(In),h(Wn),h(Xn),h(sa),h(Fn),h(Jn),h(da),h(Pn,e),h(Hn),h(jn),h(Zn),h(Gn,e),h(Bn),h(En),h(qn),h(Nn),h(ma),h(zn),h(Yn),h(ua),h(Qn,e),h(On),h(Kn),h(ha),h(es),h(ga),h(os),h(xa),h(ts),h(as),h(ba),h(wa),h(rs),h(va),h(ns),h(ss),h(ya),h(is),h(Ma),h(ds),h(Ta),h(ls),h(Da),h(cs),h(fs,e)}}}const db='{"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":"LoraBaseMixin","local":"diffusers.loaders.lora_base.LoraBaseMixin","sections":[],"depth":2}],"depth":1}';function lb(T){return sL(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class gb extends iL{constructor(t){super(),dL(this,t,lb,ib,nL,{})}}export{gb as component};