diffusers/pr_10083/en/_app/immutable/nodes/9.d5923007.js

import{s as Da,o as Ta,n as Y}from"../chunks/scheduler.8c3d61f6.js";import{S as Sa,i as ka,g as a,s as t,r as _,A as Aa,h as n,f as d,c as r,j as $,u as m,x as p,k as M,y as o,a as b,v as u,d as h,t as g,w as x}from"../chunks/index.da70eac4.js";import{T as Yo}from"../chunks/Tip.1d9b8c37.js";import{D as y}from"../chunks/Docstring.6b390b9a.js";import{C as Nr}from"../chunks/CodeBlock.00a903b3.js";import{E as Er}from"../chunks/ExampleCodeBlock.db12be95.js";import{H as Qo,E as Ca}from"../chunks/EditOnGithub.1e64e623.js";function Ra(S){let s,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(){s=a("p"),s.innerHTML=L},l(f){s=n(f,"P",{"data-svelte-h":!0}),p(s)!=="svelte-1fw6lx1"&&(s.innerHTML=L)},m(f,l){b(f,s,l)},p:Y,d(f){f&&d(s)}}}function Pa(S){let s,L="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",f,l,v="This function is experimental and might change in the future.";return{c(){s=a("p"),s.textContent=L,f=t(),l=a("p"),l.textContent=v},l(i){s=n(i,"P",{"data-svelte-h":!0}),p(s)!=="svelte-15l1sdn"&&(s.textContent=L),f=r(i),l=n(i,"P",{"data-svelte-h":!0}),p(l)!=="svelte-3fufvn"&&(l.textContent=v)},m(i,w){b(i,s,w),b(i,f,w),b(i,l,w)},p:Y,d(i){i&&(d(s),d(f),d(l))}}}function Ia(S){let s,L="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",f,l,v="This function is experimental and might change in the future.";return{c(){s=a("p"),s.textContent=L,f=t(),l=a("p"),l.textContent=v},l(i){s=n(i,"P",{"data-svelte-h":!0}),p(s)!=="svelte-15l1sdn"&&(s.textContent=L),f=r(i),l=n(i,"P",{"data-svelte-h":!0}),p(l)!=="svelte-3fufvn"&&(l.textContent=v)},m(i,w){b(i,s,w),b(i,f,w),b(i,l,w)},p:Y,d(i){i&&(d(s),d(f),d(l))}}}function Ha(S){let s,L="We support loading A1111 formatted LoRA checkpoints in a limited capacity.",f,l,v="This function is experimental and might change in the future.";return{c(){s=a("p"),s.textContent=L,f=t(),l=a("p"),l.textContent=v},l(i){s=n(i,"P",{"data-svelte-h":!0}),p(s)!=="svelte-15l1sdn"&&(s.textContent=L),f=r(i),l=n(i,"P",{"data-svelte-h":!0}),p(l)!=="svelte-3fufvn"&&(l.textContent=v)},m(i,w){b(i,s,w),b(i,f,w),b(i,l,w)},p:Y,d(i){i&&(d(s),d(f),d(l))}}}function Ua(S){let s,L="This is an experimental API.";return{c(){s=a("p"),s.textContent=L},l(f){s=n(f,"P",{"data-svelte-h":!0}),p(s)!=="svelte-8w79b9"&&(s.textContent=L)},m(f,l){b(f,s,l)},p:Y,d(f){f&&d(s)}}}function Ea(S){let s,L="Example:",f,l,v;return l=new Nr({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(){s=a("p"),s.textContent=L,f=t(),_(l.$$.fragment)},l(i){s=n(i,"P",{"data-svelte-h":!0}),p(s)!=="svelte-11lpom8"&&(s.textContent=L),f=r(i),m(l.$$.fragment,i)},m(i,w){b(i,s,w),b(i,f,w),u(l,i,w),v=!0},p:Y,i(i){v||(h(l.$$.fragment,i),v=!0)},o(i){g(l.$$.fragment,i),v=!1},d(i){i&&(d(s),d(f)),x(l,i)}}}function Na(S){let s,L="Example:",f,l,v;return l=new Nr({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(){s=a("p"),s.textContent=L,f=t(),_(l.$$.fragment)},l(i){s=n(i,"P",{"data-svelte-h":!0}),p(s)!=="svelte-11lpom8"&&(s.textContent=L),f=r(i),m(l.$$.fragment,i)},m(i,w){b(i,s,w),b(i,f,w),u(l,i,w),v=!0},p:Y,i(i){v||(h(l.$$.fragment,i),v=!0)},o(i){g(l.$$.fragment,i),v=!1},d(i){i&&(d(s),d(f)),x(l,i)}}}function Xa(S){let s,L="This is an experimental API.";return{c(){s=a("p"),s.textContent=L},l(f){s=n(f,"P",{"data-svelte-h":!0}),p(s)!=="svelte-8w79b9"&&(s.textContent=L)},m(f,l){b(f,s,l)},p:Y,d(f){f&&d(s)}}}function Wa(S){let s,L="Examples:",f,l,v;return l=new Nr({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(){s=a("p"),s.textContent=L,f=t(),_(l.$$.fragment)},l(i){s=n(i,"P",{"data-svelte-h":!0}),p(s)!=="svelte-kvfsh7"&&(s.textContent=L),f=r(i),m(l.$$.fragment,i)},m(i,w){b(i,s,w),b(i,f,w),u(l,i,w),v=!0},p:Y,i(i){v||(h(l.$$.fragment,i),v=!0)},o(i){g(l.$$.fragment,i),v=!1},d(i){i&&(d(s),d(f)),x(l,i)}}}function Ba(S){let s,L,f,l,v,i,w,Xr='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_10083/en/api/models/unet2d-cond#diffusers.UNet2DConditionModel">UNet2DConditionModel</a>, for example) or a Transformer (<a href="/docs/diffusers/pr_10083/en/api/models/sd3_transformer2d#diffusers.SD3Transformer2DModel">SD3Transformer2DModel</a>, for example). There are several classes for loading LoRA weights:',Oo,be,Wr='<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>AmusedLoraLoaderMixin</code> is for the <a href="/docs/diffusers/pr_10083/en/api/pipelines/amused#diffusers.AmusedPipeline">AmusedPipeline</a>.</li> <li><code>LoraBaseMixin</code> provides a base class with several utility methods to fuse, unfuse, unload, LoRAs and more.</li>',et,Q,ot,Le,tt,k,ve,wt,no,Br=`Load LoRA layers into Stable Diffusion <a href="/docs/diffusers/pr_10083/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>.`,$t,K,we,Mt,so,jr="This will load the LoRA layers specified in <code>state_dict</code> into <code>text_encoder</code>",yt,O,$e,Dt,io,Jr="This will load the LoRA layers specified in <code>state_dict</code> into <code>unet</code>.",Tt,I,Me,St,lo,zr=`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>.`,kt,co,qr="All kwargs are forwarded to <code>self.lora_state_dict</code>.",At,fo,Vr=`See <a href="/docs/diffusers/pr_10083/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is
loaded.`,Ct,po,Zr=`See <a href="/docs/diffusers/pr_10083/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>.`,Rt,_o,Gr=`See <a href="/docs/diffusers/pr_10083/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>.`,Pt,B,ye,It,mo,Fr="Return state dict for lora weights and the network alphas.",Ht,ee,Ut,oe,De,Et,uo,Yr="Save the LoRA parameters corresponding to the UNet and text encoder.",rt,Te,at,A,Se,Nt,ho,Qr=`Load LoRA layers into Stable Diffusion XL <a href="/docs/diffusers/pr_10083/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>.`,Xt,te,ke,Wt,go,Kr="This will load the LoRA layers specified in <code>state_dict</code> into <code>text_encoder</code>",Bt,re,Ae,jt,xo,Or="This will load the LoRA layers specified in <code>state_dict</code> into <code>unet</code>.",Jt,H,Ce,zt,bo,ea=`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>.`,qt,Lo,oa="All kwargs are forwarded to <code>self.lora_state_dict</code>.",Vt,vo,ta=`See <a href="/docs/diffusers/pr_10083/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is
loaded.`,Zt,wo,ra=`See <a href="/docs/diffusers/pr_10083/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>.`,Gt,$o,aa=`See <a href="/docs/diffusers/pr_10083/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>.`,Ft,j,Re,Yt,Mo,na="Return state dict for lora weights and the network alphas.",Qt,ae,Kt,ne,Pe,Ot,yo,sa="Save the LoRA parameters corresponding to the UNet and text encoder.",nt,Ie,st,T,He,er,Do,ia=`Load LoRA layers into <a href="/docs/diffusers/pr_10083/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>.`,or,To,da='Specific to <a href="/docs/diffusers/pr_10083/en/api/pipelines/stable_diffusion/stable_diffusion_3#diffusers.StableDiffusion3Pipeline">StableDiffusion3Pipeline</a>.',tr,se,Ue,rr,So,la="This will load the LoRA layers specified in <code>state_dict</code> into <code>text_encoder</code>",ar,ie,Ee,nr,ko,ca="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",sr,N,Ne,ir,Ao,fa=`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>.`,dr,Co,pa="All kwargs are forwarded to <code>self.lora_state_dict</code>.",lr,Ro,_a=`See <a href="/docs/diffusers/pr_10083/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a> for more details on how the state dict is
loaded.`,cr,Po,ma=`See <code>~loaders.StableDiffusionLoraLoaderMixin.load_lora_into_transformer</code> for more details on how the state
dict is loaded into <code>self.transformer</code>.`,fr,J,Xe,pr,Io,ua="Return state dict for lora weights and the network alphas.",_r,de,mr,le,We,ur,Ho,ha="Save the LoRA parameters corresponding to the UNet and text encoder.",it,Be,dt,G,je,hr,ce,Je,gr,Uo,ga="This will load the LoRA layers specified in <code>state_dict</code> into <code>transformer</code>.",lt,ze,ct,D,qe,xr,Eo,xa="Utility class for handling LoRAs.",br,No,Ve,Lr,X,Ze,vr,Xo,ba="Fuses the LoRA parameters into the original parameters of the corresponding blocks.",wr,fe,$r,pe,Mr,z,Ge,yr,Wo,La="Gets the list of the current active adapters.",Dr,_e,Tr,me,Fe,Sr,Bo,va="Gets the current list of all available adapters in the pipeline.",kr,ue,Ye,Ar,jo,wa=`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.`,Cr,q,Qe,Rr,Jo,$a=`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>.`,Pr,he,Ir,V,Ke,Hr,zo,Ma="Unloads the LoRA parameters.",Ur,ge,ft,Oe,pt,Ko,_t;return v=new Qo({props:{title:"LoRA",local:"lora",headingTag:"h1"}}),Q=new Yo({props:{$$slots:{default:[Ra]},$$scope:{ctx:S}}}),Le=new Qo({props:{title:"StableDiffusionLoraLoaderMixin",local:"diffusers.loaders.StableDiffusionLoraLoaderMixin",headingTag:"h2"}}),ve=new y({props:{name:"class diffusers.loaders.StableDiffusionLoraLoaderMixin",anchor:"diffusers.loaders.StableDiffusionLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L65"}}),we=new y({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"}],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"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L310"}}),$e=new y({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"}],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"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L260"}}),Me=new y({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:" = None"},{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_10083/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.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_10083/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L75"}}),ye=new y({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_10083/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"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L145"}}),ee=new Yo({props:{warning:!0,$$slots:{default:[Pa]},$$scope:{ctx:S}}}),De=new y({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"}],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"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L449"}}),Te=new Qo({props:{title:"StableDiffusionXLLoraLoaderMixin",local:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin",headingTag:"h2"}}),Se=new y({props:{name:"class diffusers.loaders.StableDiffusionXLLoraLoaderMixin",anchor:"diffusers.loaders.StableDiffusionXLLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L567"}}),ke=new y({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"}],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"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L840"}}),Ae=new y({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"}],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"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L789"}}),Ce=new y({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:"**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_10083/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.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_10083/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L578"}}),Re=new y({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_10083/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"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L673"}}),ae=new Yo({props:{warning:!0,$$slots:{default:[Ia]},$$scope:{ctx:S}}}),Pe=new y({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"}],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"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L980"}}),Ie=new Qo({props:{title:"SD3LoraLoaderMixin",local:"diffusers.loaders.SD3LoraLoaderMixin",headingTag:"h2"}}),He=new y({props:{name:"class diffusers.loaders.SD3LoraLoaderMixin",anchor:"diffusers.loaders.SD3LoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L1106"}}),Ue=new y({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"}],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"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L1337"}}),Ee=new y({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"}],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"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L1301"}}),Ne=new y({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:"**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_10083/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.kwargs",description:`<strong>kwargs</strong> (<code>dict</code>, <em>optional</em>) &#x2014;
See <a href="/docs/diffusers/pr_10083/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.lora_state_dict">lora_state_dict()</a>.`,name:"kwargs"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L1216"}}),Xe=new y({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_10083/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"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L1119"}}),de=new Yo({props:{warning:!0,$$slots:{default:[Ha]},$$scope:{ctx:S}}}),We=new y({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, torch.nn.modules.module.Module] = 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"}],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"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L1477"}}),Be=new Qo({props:{title:"AmusedLoraLoaderMixin",local:"diffusers.loaders.AmusedLoraLoaderMixin",headingTag:"h2"}}),je=new y({props:{name:"class diffusers.loaders.AmusedLoraLoaderMixin",anchor:"diffusers.loaders.AmusedLoraLoaderMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L2121"}}),Je=new y({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:"_pipeline",val:" = None"},{name:"low_cpu_mem_usage",val:" = 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"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_pipeline.py#L2126"}}),ze=new Qo({props:{title:"LoraBaseMixin",local:"diffusers.loaders.lora_base.LoraBaseMixin",headingTag:"h2"}}),qe=new y({props:{name:"class diffusers.loaders.lora_base.LoraBaseMixin",anchor:"diffusers.loaders.lora_base.LoraBaseMixin",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_base.py#L300"}}),Ve=new y({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.Deletes",description:`<strong>Deletes</strong> the LoRA layers of <code>adapter_name</code> for the unet and text-encoder(s). &#x2014;
adapter_names (<code>Union[List[str], str]</code>):
The names of the adapter to delete. Can be a single string or a list of strings`,name:"Deletes"}],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_base.py#L615"}}),Ze=new y({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_10083/src/diffusers/loaders/lora_base.py#L387"}}),fe=new Yo({props:{warning:!0,$$slots:{default:[Ua]},$$scope:{ctx:S}}}),pe=new Er({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.fuse_lora.example",$$slots:{default:[Ea]},$$scope:{ctx:S}}}),Ge=new y({props:{name:"get_active_adapters",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.get_active_adapters",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_base.py#L637"}}),_e=new Er({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.get_active_adapters.example",$$slots:{default:[Na]},$$scope:{ctx:S}}}),Fe=new y({props:{name:"get_list_adapters",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.get_list_adapters",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_base.py#L670"}}),Ye=new y({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_10083/src/diffusers/loaders/lora_base.py#L692"}}),Qe=new y({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_10083/src/diffusers/loaders/lora_base.py#L468"}}),he=new Yo({props:{warning:!0,$$slots:{default:[Xa]},$$scope:{ctx:S}}}),Ke=new y({props:{name:"unload_lora_weights",anchor:"diffusers.loaders.lora_base.LoraBaseMixin.unload_lora_weights",parameters:[],source:"https://github.com/huggingface/diffusers/blob/vr_10083/src/diffusers/loaders/lora_base.py#L364"}}),ge=new Er({props:{anchor:"diffusers.loaders.lora_base.LoraBaseMixin.unload_lora_weights.example",$$slots:{default:[Wa]},$$scope:{ctx:S}}}),Oe=new Ca({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/loaders/lora.md"}}),{c(){s=a("meta"),L=t(),f=a("p"),l=t(),_(v.$$.fragment),i=t(),w=a("p"),w.innerHTML=Xr,Oo=t(),be=a("ul"),be.innerHTML=Wr,et=t(),_(Q.$$.fragment),ot=t(),_(Le.$$.fragment),tt=t(),k=a("div"),_(ve.$$.fragment),wt=t(),no=a("p"),no.innerHTML=Br,$t=t(),K=a("div"),_(we.$$.fragment),Mt=t(),so=a("p"),so.innerHTML=jr,yt=t(),O=a("div"),_($e.$$.fragment),Dt=t(),io=a("p"),io.innerHTML=Jr,Tt=t(),I=a("div"),_(Me.$$.fragment),St=t(),lo=a("p"),lo.innerHTML=zr,kt=t(),co=a("p"),co.innerHTML=qr,At=t(),fo=a("p"),fo.innerHTML=Vr,Ct=t(),po=a("p"),po.innerHTML=Zr,Rt=t(),_o=a("p"),_o.innerHTML=Gr,Pt=t(),B=a("div"),_(ye.$$.fragment),It=t(),mo=a("p"),mo.textContent=Fr,Ht=t(),_(ee.$$.fragment),Ut=t(),oe=a("div"),_(De.$$.fragment),Et=t(),uo=a("p"),uo.textContent=Yr,rt=t(),_(Te.$$.fragment),at=t(),A=a("div"),_(Se.$$.fragment),Nt=t(),ho=a("p"),ho.innerHTML=Qr,Xt=t(),te=a("div"),_(ke.$$.fragment),Wt=t(),go=a("p"),go.innerHTML=Kr,Bt=t(),re=a("div"),_(Ae.$$.fragment),jt=t(),xo=a("p"),xo.innerHTML=Or,Jt=t(),H=a("div"),_(Ce.$$.fragment),zt=t(),bo=a("p"),bo.innerHTML=ea,qt=t(),Lo=a("p"),Lo.innerHTML=oa,Vt=t(),vo=a("p"),vo.innerHTML=ta,Zt=t(),wo=a("p"),wo.innerHTML=ra,Gt=t(),$o=a("p"),$o.innerHTML=aa,Ft=t(),j=a("div"),_(Re.$$.fragment),Yt=t(),Mo=a("p"),Mo.textContent=na,Qt=t(),_(ae.$$.fragment),Kt=t(),ne=a("div"),_(Pe.$$.fragment),Ot=t(),yo=a("p"),yo.textContent=sa,nt=t(),_(Ie.$$.fragment),st=t(),T=a("div"),_(He.$$.fragment),er=t(),Do=a("p"),Do.innerHTML=ia,or=t(),To=a("p"),To.innerHTML=da,tr=t(),se=a("div"),_(Ue.$$.fragment),rr=t(),So=a("p"),So.innerHTML=la,ar=t(),ie=a("div"),_(Ee.$$.fragment),nr=t(),ko=a("p"),ko.innerHTML=ca,sr=t(),N=a("div"),_(Ne.$$.fragment),ir=t(),Ao=a("p"),Ao.innerHTML=fa,dr=t(),Co=a("p"),Co.innerHTML=pa,lr=t(),Ro=a("p"),Ro.innerHTML=_a,cr=t(),Po=a("p"),Po.innerHTML=ma,fr=t(),J=a("div"),_(Xe.$$.fragment),pr=t(),Io=a("p"),Io.textContent=ua,_r=t(),_(de.$$.fragment),mr=t(),le=a("div"),_(We.$$.fragment),ur=t(),Ho=a("p"),Ho.textContent=ha,it=t(),_(Be.$$.fragment),dt=t(),G=a("div"),_(je.$$.fragment),hr=t(),ce=a("div"),_(Je.$$.fragment),gr=t(),Uo=a("p"),Uo.innerHTML=ga,lt=t(),_(ze.$$.fragment),ct=t(),D=a("div"),_(qe.$$.fragment),xr=t(),Eo=a("p"),Eo.textContent=xa,br=t(),No=a("div"),_(Ve.$$.fragment),Lr=t(),X=a("div"),_(Ze.$$.fragment),vr=t(),Xo=a("p"),Xo.textContent=ba,wr=t(),_(fe.$$.fragment),$r=t(),_(pe.$$.fragment),Mr=t(),z=a("div"),_(Ge.$$.fragment),yr=t(),Wo=a("p"),Wo.textContent=La,Dr=t(),_(_e.$$.fragment),Tr=t(),me=a("div"),_(Fe.$$.fragment),Sr=t(),Bo=a("p"),Bo.textContent=va,kr=t(),ue=a("div"),_(Ye.$$.fragment),Ar=t(),jo=a("p"),jo.innerHTML=wa,Cr=t(),q=a("div"),_(Qe.$$.fragment),Rr=t(),Jo=a("p"),Jo.innerHTML=$a,Pr=t(),_(he.$$.fragment),Ir=t(),V=a("div"),_(Ke.$$.fragment),Hr=t(),zo=a("p"),zo.textContent=Ma,Ur=t(),_(ge.$$.fragment),ft=t(),_(Oe.$$.fragment),pt=t(),Ko=a("p"),this.h()},l(e){const c=Aa("svelte-u9bgzb",document.head);s=n(c,"META",{name:!0,content:!0}),c.forEach(d),L=r(e),f=n(e,"P",{}),$(f).forEach(d),l=r(e),m(v.$$.fragment,e),i=r(e),w=n(e,"P",{"data-svelte-h":!0}),p(w)!=="svelte-ql658d"&&(w.innerHTML=Xr),Oo=r(e),be=n(e,"UL",{"data-svelte-h":!0}),p(be)!=="svelte-1nsszd8"&&(be.innerHTML=Wr),et=r(e),m(Q.$$.fragment,e),ot=r(e),m(Le.$$.fragment,e),tt=r(e),k=n(e,"DIV",{class:!0});var R=$(k);m(ve.$$.fragment,R),wt=r(R),no=n(R,"P",{"data-svelte-h":!0}),p(no)!=="svelte-1k0htjf"&&(no.innerHTML=Br),$t=r(R),K=n(R,"DIV",{class:!0});var eo=$(K);m(we.$$.fragment,eo),Mt=r(eo),so=n(eo,"P",{"data-svelte-h":!0}),p(so)!=="svelte-1062ci4"&&(so.innerHTML=jr),eo.forEach(d),yt=r(R),O=n(R,"DIV",{class:!0});var oo=$(O);m($e.$$.fragment,oo),Dt=r(oo),io=n(oo,"P",{"data-svelte-h":!0}),p(io)!=="svelte-u3q4so"&&(io.innerHTML=Jr),oo.forEach(d),Tt=r(R),I=n(R,"DIV",{class:!0});var E=$(I);m(Me.$$.fragment,E),St=r(E),lo=n(E,"P",{"data-svelte-h":!0}),p(lo)!=="svelte-vs7s0z"&&(lo.innerHTML=zr),kt=r(E),co=n(E,"P",{"data-svelte-h":!0}),p(co)!=="svelte-15b960v"&&(co.innerHTML=qr),At=r(E),fo=n(E,"P",{"data-svelte-h":!0}),p(fo)!=="svelte-1yb4zvo"&&(fo.innerHTML=Vr),Ct=r(E),po=n(E,"P",{"data-svelte-h":!0}),p(po)!=="svelte-1v5x0l3"&&(po.innerHTML=Zr),Rt=r(E),_o=n(E,"P",{"data-svelte-h":!0}),p(_o)!=="svelte-jq3xax"&&(_o.innerHTML=Gr),E.forEach(d),Pt=r(R),B=n(R,"DIV",{class:!0});var F=$(B);m(ye.$$.fragment,F),It=r(F),mo=n(F,"P",{"data-svelte-h":!0}),p(mo)!=="svelte-flusvq"&&(mo.textContent=Fr),Ht=r(F),m(ee.$$.fragment,F),F.forEach(d),Ut=r(R),oe=n(R,"DIV",{class:!0});var to=$(oe);m(De.$$.fragment,to),Et=r(to),uo=n(to,"P",{"data-svelte-h":!0}),p(uo)!=="svelte-1ufq5ot"&&(uo.textContent=Yr),to.forEach(d),R.forEach(d),rt=r(e),m(Te.$$.fragment,e),at=r(e),A=n(e,"DIV",{class:!0});var P=$(A);m(Se.$$.fragment,P),Nt=r(P),ho=n(P,"P",{"data-svelte-h":!0}),p(ho)!=="svelte-1kup6cg"&&(ho.innerHTML=Qr),Xt=r(P),te=n(P,"DIV",{class:!0});var ro=$(te);m(ke.$$.fragment,ro),Wt=r(ro),go=n(ro,"P",{"data-svelte-h":!0}),p(go)!=="svelte-1062ci4"&&(go.innerHTML=Kr),ro.forEach(d),Bt=r(P),re=n(P,"DIV",{class:!0});var ao=$(re);m(Ae.$$.fragment,ao),jt=r(ao),xo=n(ao,"P",{"data-svelte-h":!0}),p(xo)!=="svelte-u3q4so"&&(xo.innerHTML=Or),ao.forEach(d),Jt=r(P),H=n(P,"DIV",{class:!0});var W=$(H);m(Ce.$$.fragment,W),zt=r(W),bo=n(W,"P",{"data-svelte-h":!0}),p(bo)!=="svelte-vs7s0z"&&(bo.innerHTML=ea),qt=r(W),Lo=n(W,"P",{"data-svelte-h":!0}),p(Lo)!=="svelte-15b960v"&&(Lo.innerHTML=oa),Vt=r(W),vo=n(W,"P",{"data-svelte-h":!0}),p(vo)!=="svelte-1yb4zvo"&&(vo.innerHTML=ta),Zt=r(W),wo=n(W,"P",{"data-svelte-h":!0}),p(wo)!=="svelte-1v5x0l3"&&(wo.innerHTML=ra),Gt=r(W),$o=n(W,"P",{"data-svelte-h":!0}),p($o)!=="svelte-jq3xax"&&($o.innerHTML=aa),W.forEach(d),Ft=r(P),j=n(P,"DIV",{class:!0});var qo=$(j);m(Re.$$.fragment,qo),Yt=r(qo),Mo=n(qo,"P",{"data-svelte-h":!0}),p(Mo)!=="svelte-flusvq"&&(Mo.textContent=na),Qt=r(qo),m(ae.$$.fragment,qo),qo.forEach(d),Kt=r(P),ne=n(P,"DIV",{class:!0});var mt=$(ne);m(Pe.$$.fragment,mt),Ot=r(mt),yo=n(mt,"P",{"data-svelte-h":!0}),p(yo)!=="svelte-1ufq5ot"&&(yo.textContent=sa),mt.forEach(d),P.forEach(d),nt=r(e),m(Ie.$$.fragment,e),st=r(e),T=n(e,"DIV",{class:!0});var U=$(T);m(He.$$.fragment,U),er=r(U),Do=n(U,"P",{"data-svelte-h":!0}),p(Do)!=="svelte-1l0w5w9"&&(Do.innerHTML=ia),or=r(U),To=n(U,"P",{"data-svelte-h":!0}),p(To)!=="svelte-jxirh3"&&(To.innerHTML=da),tr=r(U),se=n(U,"DIV",{class:!0});var ut=$(se);m(Ue.$$.fragment,ut),rr=r(ut),So=n(ut,"P",{"data-svelte-h":!0}),p(So)!=="svelte-1062ci4"&&(So.innerHTML=la),ut.forEach(d),ar=r(U),ie=n(U,"DIV",{class:!0});var ht=$(ie);m(Ee.$$.fragment,ht),nr=r(ht),ko=n(ht,"P",{"data-svelte-h":!0}),p(ko)!=="svelte-1lgbsz7"&&(ko.innerHTML=ca),ht.forEach(d),sr=r(U),N=n(U,"DIV",{class:!0});var Z=$(N);m(Ne.$$.fragment,Z),ir=r(Z),Ao=n(Z,"P",{"data-svelte-h":!0}),p(Ao)!=="svelte-vs7s0z"&&(Ao.innerHTML=fa),dr=r(Z),Co=n(Z,"P",{"data-svelte-h":!0}),p(Co)!=="svelte-15b960v"&&(Co.innerHTML=pa),lr=r(Z),Ro=n(Z,"P",{"data-svelte-h":!0}),p(Ro)!=="svelte-1yb4zvo"&&(Ro.innerHTML=_a),cr=r(Z),Po=n(Z,"P",{"data-svelte-h":!0}),p(Po)!=="svelte-1ukghd4"&&(Po.innerHTML=ma),Z.forEach(d),fr=r(U),J=n(U,"DIV",{class:!0});var Vo=$(J);m(Xe.$$.fragment,Vo),pr=r(Vo),Io=n(Vo,"P",{"data-svelte-h":!0}),p(Io)!=="svelte-flusvq"&&(Io.textContent=ua),_r=r(Vo),m(de.$$.fragment,Vo),Vo.forEach(d),mr=r(U),le=n(U,"DIV",{class:!0});var gt=$(le);m(We.$$.fragment,gt),ur=r(gt),Ho=n(gt,"P",{"data-svelte-h":!0}),p(Ho)!=="svelte-1ufq5ot"&&(Ho.textContent=ha),gt.forEach(d),U.forEach(d),it=r(e),m(Be.$$.fragment,e),dt=r(e),G=n(e,"DIV",{class:!0});var xt=$(G);m(je.$$.fragment,xt),hr=r(xt),ce=n(xt,"DIV",{class:!0});var bt=$(ce);m(Je.$$.fragment,bt),gr=r(bt),Uo=n(bt,"P",{"data-svelte-h":!0}),p(Uo)!=="svelte-1lgbsz7"&&(Uo.innerHTML=ga),bt.forEach(d),xt.forEach(d),lt=r(e),m(ze.$$.fragment,e),ct=r(e),D=n(e,"DIV",{class:!0});var C=$(D);m(qe.$$.fragment,C),xr=r(C),Eo=n(C,"P",{"data-svelte-h":!0}),p(Eo)!=="svelte-1q4bbx"&&(Eo.textContent=xa),br=r(C),No=n(C,"DIV",{class:!0});var ya=$(No);m(Ve.$$.fragment,ya),ya.forEach(d),Lr=r(C),X=n(C,"DIV",{class:!0});var xe=$(X);m(Ze.$$.fragment,xe),vr=r(xe),Xo=n(xe,"P",{"data-svelte-h":!0}),p(Xo)!=="svelte-1nr2dy0"&&(Xo.textContent=ba),wr=r(xe),m(fe.$$.fragment,xe),$r=r(xe),m(pe.$$.fragment,xe),xe.forEach(d),Mr=r(C),z=n(C,"DIV",{class:!0});var Zo=$(z);m(Ge.$$.fragment,Zo),yr=r(Zo),Wo=n(Zo,"P",{"data-svelte-h":!0}),p(Wo)!=="svelte-h0os0v"&&(Wo.textContent=La),Dr=r(Zo),m(_e.$$.fragment,Zo),Zo.forEach(d),Tr=r(C),me=n(C,"DIV",{class:!0});var Lt=$(me);m(Fe.$$.fragment,Lt),Sr=r(Lt),Bo=n(Lt,"P",{"data-svelte-h":!0}),p(Bo)!=="svelte-1825k9e"&&(Bo.textContent=va),Lt.forEach(d),kr=r(C),ue=n(C,"DIV",{class:!0});var vt=$(ue);m(Ye.$$.fragment,vt),Ar=r(vt),jo=n(vt,"P",{"data-svelte-h":!0}),p(jo)!=="svelte-rvubqa"&&(jo.innerHTML=wa),vt.forEach(d),Cr=r(C),q=n(C,"DIV",{class:!0});var Go=$(q);m(Qe.$$.fragment,Go),Rr=r(Go),Jo=n(Go,"P",{"data-svelte-h":!0}),p(Jo)!=="svelte-ioswce"&&(Jo.innerHTML=$a),Pr=r(Go),m(he.$$.fragment,Go),Go.forEach(d),Ir=r(C),V=n(C,"DIV",{class:!0});var Fo=$(V);m(Ke.$$.fragment,Fo),Hr=r(Fo),zo=n(Fo,"P",{"data-svelte-h":!0}),p(zo)!=="svelte-119cgd9"&&(zo.textContent=Ma),Ur=r(Fo),m(ge.$$.fragment,Fo),Fo.forEach(d),C.forEach(d),ft=r(e),m(Oe.$$.fragment,e),pt=r(e),Ko=n(e,"P",{}),$(Ko).forEach(d),this.h()},h(){M(s,"name","hf:doc:metadata"),M(s,"content",ja),M(K,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(O,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(I,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(B,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(oe,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(k,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(te,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(re,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(H,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(j,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(ne,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(A,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(se,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(ie,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(N,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(J,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(le,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(T,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(ce,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(G,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(No,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(X,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(z,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(me,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(ue,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(q,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(V,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),M(D,"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,c){o(document.head,s),b(e,L,c),b(e,f,c),b(e,l,c),u(v,e,c),b(e,i,c),b(e,w,c),b(e,Oo,c),b(e,be,c),b(e,et,c),u(Q,e,c),b(e,ot,c),u(Le,e,c),b(e,tt,c),b(e,k,c),u(ve,k,null),o(k,wt),o(k,no),o(k,$t),o(k,K),u(we,K,null),o(K,Mt),o(K,so),o(k,yt),o(k,O),u($e,O,null),o(O,Dt),o(O,io),o(k,Tt),o(k,I),u(Me,I,null),o(I,St),o(I,lo),o(I,kt),o(I,co),o(I,At),o(I,fo),o(I,Ct),o(I,po),o(I,Rt),o(I,_o),o(k,Pt),o(k,B),u(ye,B,null),o(B,It),o(B,mo),o(B,Ht),u(ee,B,null),o(k,Ut),o(k,oe),u(De,oe,null),o(oe,Et),o(oe,uo),b(e,rt,c),u(Te,e,c),b(e,at,c),b(e,A,c),u(Se,A,null),o(A,Nt),o(A,ho),o(A,Xt),o(A,te),u(ke,te,null),o(te,Wt),o(te,go),o(A,Bt),o(A,re),u(Ae,re,null),o(re,jt),o(re,xo),o(A,Jt),o(A,H),u(Ce,H,null),o(H,zt),o(H,bo),o(H,qt),o(H,Lo),o(H,Vt),o(H,vo),o(H,Zt),o(H,wo),o(H,Gt),o(H,$o),o(A,Ft),o(A,j),u(Re,j,null),o(j,Yt),o(j,Mo),o(j,Qt),u(ae,j,null),o(A,Kt),o(A,ne),u(Pe,ne,null),o(ne,Ot),o(ne,yo),b(e,nt,c),u(Ie,e,c),b(e,st,c),b(e,T,c),u(He,T,null),o(T,er),o(T,Do),o(T,or),o(T,To),o(T,tr),o(T,se),u(Ue,se,null),o(se,rr),o(se,So),o(T,ar),o(T,ie),u(Ee,ie,null),o(ie,nr),o(ie,ko),o(T,sr),o(T,N),u(Ne,N,null),o(N,ir),o(N,Ao),o(N,dr),o(N,Co),o(N,lr),o(N,Ro),o(N,cr),o(N,Po),o(T,fr),o(T,J),u(Xe,J,null),o(J,pr),o(J,Io),o(J,_r),u(de,J,null),o(T,mr),o(T,le),u(We,le,null),o(le,ur),o(le,Ho),b(e,it,c),u(Be,e,c),b(e,dt,c),b(e,G,c),u(je,G,null),o(G,hr),o(G,ce),u(Je,ce,null),o(ce,gr),o(ce,Uo),b(e,lt,c),u(ze,e,c),b(e,ct,c),b(e,D,c),u(qe,D,null),o(D,xr),o(D,Eo),o(D,br),o(D,No),u(Ve,No,null),o(D,Lr),o(D,X),u(Ze,X,null),o(X,vr),o(X,Xo),o(X,wr),u(fe,X,null),o(X,$r),u(pe,X,null),o(D,Mr),o(D,z),u(Ge,z,null),o(z,yr),o(z,Wo),o(z,Dr),u(_e,z,null),o(D,Tr),o(D,me),u(Fe,me,null),o(me,Sr),o(me,Bo),o(D,kr),o(D,ue),u(Ye,ue,null),o(ue,Ar),o(ue,jo),o(D,Cr),o(D,q),u(Qe,q,null),o(q,Rr),o(q,Jo),o(q,Pr),u(he,q,null),o(D,Ir),o(D,V),u(Ke,V,null),o(V,Hr),o(V,zo),o(V,Ur),u(ge,V,null),b(e,ft,c),u(Oe,e,c),b(e,pt,c),b(e,Ko,c),_t=!0},p(e,[c]){const R={};c&2&&(R.$$scope={dirty:c,ctx:e}),Q.$set(R);const eo={};c&2&&(eo.$$scope={dirty:c,ctx:e}),ee.$set(eo);const oo={};c&2&&(oo.$$scope={dirty:c,ctx:e}),ae.$set(oo);const E={};c&2&&(E.$$scope={dirty:c,ctx:e}),de.$set(E);const F={};c&2&&(F.$$scope={dirty:c,ctx:e}),fe.$set(F);const to={};c&2&&(to.$$scope={dirty:c,ctx:e}),pe.$set(to);const P={};c&2&&(P.$$scope={dirty:c,ctx:e}),_e.$set(P);const ro={};c&2&&(ro.$$scope={dirty:c,ctx:e}),he.$set(ro);const ao={};c&2&&(ao.$$scope={dirty:c,ctx:e}),ge.$set(ao)},i(e){_t||(h(v.$$.fragment,e),h(Q.$$.fragment,e),h(Le.$$.fragment,e),h(ve.$$.fragment,e),h(we.$$.fragment,e),h($e.$$.fragment,e),h(Me.$$.fragment,e),h(ye.$$.fragment,e),h(ee.$$.fragment,e),h(De.$$.fragment,e),h(Te.$$.fragment,e),h(Se.$$.fragment,e),h(ke.$$.fragment,e),h(Ae.$$.fragment,e),h(Ce.$$.fragment,e),h(Re.$$.fragment,e),h(ae.$$.fragment,e),h(Pe.$$.fragment,e),h(Ie.$$.fragment,e),h(He.$$.fragment,e),h(Ue.$$.fragment,e),h(Ee.$$.fragment,e),h(Ne.$$.fragment,e),h(Xe.$$.fragment,e),h(de.$$.fragment,e),h(We.$$.fragment,e),h(Be.$$.fragment,e),h(je.$$.fragment,e),h(Je.$$.fragment,e),h(ze.$$.fragment,e),h(qe.$$.fragment,e),h(Ve.$$.fragment,e),h(Ze.$$.fragment,e),h(fe.$$.fragment,e),h(pe.$$.fragment,e),h(Ge.$$.fragment,e),h(_e.$$.fragment,e),h(Fe.$$.fragment,e),h(Ye.$$.fragment,e),h(Qe.$$.fragment,e),h(he.$$.fragment,e),h(Ke.$$.fragment,e),h(ge.$$.fragment,e),h(Oe.$$.fragment,e),_t=!0)},o(e){g(v.$$.fragment,e),g(Q.$$.fragment,e),g(Le.$$.fragment,e),g(ve.$$.fragment,e),g(we.$$.fragment,e),g($e.$$.fragment,e),g(Me.$$.fragment,e),g(ye.$$.fragment,e),g(ee.$$.fragment,e),g(De.$$.fragment,e),g(Te.$$.fragment,e),g(Se.$$.fragment,e),g(ke.$$.fragment,e),g(Ae.$$.fragment,e),g(Ce.$$.fragment,e),g(Re.$$.fragment,e),g(ae.$$.fragment,e),g(Pe.$$.fragment,e),g(Ie.$$.fragment,e),g(He.$$.fragment,e),g(Ue.$$.fragment,e),g(Ee.$$.fragment,e),g(Ne.$$.fragment,e),g(Xe.$$.fragment,e),g(de.$$.fragment,e),g(We.$$.fragment,e),g(Be.$$.fragment,e),g(je.$$.fragment,e),g(Je.$$.fragment,e),g(ze.$$.fragment,e),g(qe.$$.fragment,e),g(Ve.$$.fragment,e),g(Ze.$$.fragment,e),g(fe.$$.fragment,e),g(pe.$$.fragment,e),g(Ge.$$.fragment,e),g(_e.$$.fragment,e),g(Fe.$$.fragment,e),g(Ye.$$.fragment,e),g(Qe.$$.fragment,e),g(he.$$.fragment,e),g(Ke.$$.fragment,e),g(ge.$$.fragment,e),g(Oe.$$.fragment,e),_t=!1},d(e){e&&(d(L),d(f),d(l),d(i),d(w),d(Oo),d(be),d(et),d(ot),d(tt),d(k),d(rt),d(at),d(A),d(nt),d(st),d(T),d(it),d(dt),d(G),d(lt),d(ct),d(D),d(ft),d(pt),d(Ko)),d(s),x(v,e),x(Q,e),x(Le,e),x(ve),x(we),x($e),x(Me),x(ye),x(ee),x(De),x(Te,e),x(Se),x(ke),x(Ae),x(Ce),x(Re),x(ae),x(Pe),x(Ie,e),x(He),x(Ue),x(Ee),x(Ne),x(Xe),x(de),x(We),x(Be,e),x(je),x(Je),x(ze,e),x(qe),x(Ve),x(Ze),x(fe),x(pe),x(Ge),x(_e),x(Fe),x(Ye),x(Qe),x(he),x(Ke),x(ge),x(Oe,e)}}}const ja='{"title":"LoRA","local":"lora","sections":[{"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":"AmusedLoraLoaderMixin","local":"diffusers.loaders.AmusedLoraLoaderMixin","sections":[],"depth":2},{"title":"LoraBaseMixin","local":"diffusers.loaders.lora_base.LoraBaseMixin","sections":[],"depth":2}],"depth":1}';function Ja(S){return Ta(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Qa extends Sa{constructor(s){super(),ka(this,s,Ja,Ba,Da,{})}}export{Qa as component};