diffusers/pr_10175/en/_app/immutable/nodes/115.ee77f5a3.js

import{s as Xe,o as Ae,n as Ne}from"../chunks/scheduler.8c3d61f6.js";import{S as Ee,i as Oe,g as s,s as n,r as _,A as He,h as a,f as i,c as r,j as B,u as h,x as u,k as F,y as t,a as c,v as b,d as v,t as x,w as D}from"../chunks/index.da70eac4.js";import{T as qe}from"../chunks/Tip.1d9b8c37.js";import{D as de}from"../chunks/Docstring.6b390b9a.js";import{H as Pe,E as Re}from"../chunks/EditOnGithub.1e64e623.js";function Ue(Y){let f,w="This is an experimental pipeline and is likely to change in the future.";return{c(){f=s("p"),f.textContent=w},l(g){f=a(g,"P",{"data-svelte-h":!0}),u(f)!=="svelte-5fv3pw"&&(f.textContent=w)},m(g,A){c(g,f,A)},p:Ne,d(g){g&&i(f)}}}function Ve(Y){let f,w,g,A,k,J,$,Le='<a href="https://github.com/crowsonkb/k-diffusion" rel="nofollow">k-diffusion</a> is a popular library created by <a href="https://github.com/crowsonkb/" rel="nofollow">Katherine Crowson</a>. We provide <code>StableDiffusionKDiffusionPipeline</code> and <code>StableDiffusionXLKDiffusionPipeline</code> that allow you to run Stable DIffusion with samplers from k-diffusion.',Q,C,Se='Note that most the samplers from k-diffusion are implemented in Diffusers and we recommend using existing schedulers. You can find a mapping between k-diffusion samplers and schedulers in Diffusers <a href="https://huggingface.co/docs/diffusers/api/schedulers/overview" rel="nofollow">here</a>',Z,T,ee,d,y,fe,N,we="Pipeline for text-to-image generation using Stable Diffusion.",le,E,ke=`This model inherits from <a href="/docs/diffusers/pr_10175/en/api/pipelines/overview#diffusers.DiffusionPipeline">DiffusionPipeline</a>. Check the superclass documentation for the generic methods the
library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)`,pe,O,$e="The pipeline also inherits the following loading methods:",ce,H,Ce='<li><a href="/docs/diffusers/pr_10175/en/api/loaders/textual_inversion#diffusers.loaders.TextualInversionLoaderMixin.load_textual_inversion">load_textual_inversion()</a> for loading textual inversion embeddings</li> <li><a href="/docs/diffusers/pr_10175/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.load_lora_weights">load_lora_weights()</a> for loading LoRA weights</li> <li><a href="/docs/diffusers/pr_10175/en/api/loaders/lora#diffusers.loaders.StableDiffusionLoraLoaderMixin.save_lora_weights">save_lora_weights()</a> for saving LoRA weights</li>',ue,P,me,L,K,ge,q,Te="Encodes the prompt into text encoder hidden states.",oe,M,te,l,I,_e,R,ye="Pipeline for text-to-image generation using Stable Diffusion XL and k-diffusion.",he,U,Ke=`This model inherits from <a href="/docs/diffusers/pr_10175/en/api/pipelines/overview#diffusers.DiffusionPipeline">DiffusionPipeline</a>. Check the superclass documentation for the generic methods the
library implements for all the pipelines (such as downloading or saving, running on a particular device, etc.)`,be,V,Me="The pipeline also inherits the following loading methods:",ve,W,Ie='<li><a href="/docs/diffusers/pr_10175/en/api/loaders/textual_inversion#diffusers.loaders.TextualInversionLoaderMixin.load_textual_inversion">load_textual_inversion()</a> for loading textual inversion embeddings</li> <li><a href="/docs/diffusers/pr_10175/en/api/loaders/single_file#diffusers.loaders.FromSingleFileMixin.from_single_file">from_single_file()</a> for loading <code>.ckpt</code> files</li> <li><a href="/docs/diffusers/pr_10175/en/api/loaders/lora#diffusers.loaders.StableDiffusionXLLoraLoaderMixin.load_lora_weights">load_lora_weights()</a> for loading LoRA weights</li> <li><a href="/docs/diffusers/pr_10175/en/api/loaders/lora#diffusers.loaders.StableDiffusionXLLoraLoaderMixin.save_lora_weights">save_lora_weights()</a> for saving LoRA weights</li> <li><a href="/docs/diffusers/pr_10175/en/api/loaders/ip_adapter#diffusers.loaders.IPAdapterMixin.load_ip_adapter">load_ip_adapter()</a> for loading IP Adapters</li>',xe,S,z,De,j,ze="Encodes the prompt into text encoder hidden states.",ie,X,ne,G,re;return k=new Pe({props:{title:"K-Diffusion",local:"k-diffusion",headingTag:"h1"}}),T=new Pe({props:{title:"StableDiffusionKDiffusionPipeline",local:"diffusers.StableDiffusionKDiffusionPipeline",headingTag:"h2"}}),y=new de({props:{name:"class diffusers.StableDiffusionKDiffusionPipeline",anchor:"diffusers.StableDiffusionKDiffusionPipeline",parameters:[{name:"vae",val:""},{name:"text_encoder",val:""},{name:"tokenizer",val:""},{name:"unet",val:""},{name:"scheduler",val:""},{name:"safety_checker",val:""},{name:"feature_extractor",val:""},{name:"requires_safety_checker",val:": bool = True"}],parametersDescription:[{anchor:"diffusers.StableDiffusionKDiffusionPipeline.vae",description:`<strong>vae</strong> (<a href="/docs/diffusers/pr_10175/en/api/models/autoencoderkl#diffusers.AutoencoderKL">AutoencoderKL</a>) &#x2014;
Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.`,name:"vae"},{anchor:"diffusers.StableDiffusionKDiffusionPipeline.text_encoder",description:`<strong>text_encoder</strong> (<code>CLIPTextModel</code>) &#x2014;
Frozen text-encoder. Stable Diffusion uses the text portion of
<a href="https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel" rel="nofollow">CLIP</a>, specifically
the <a href="https://huggingface.co/openai/clip-vit-large-patch14" rel="nofollow">clip-vit-large-patch14</a> variant.`,name:"text_encoder"},{anchor:"diffusers.StableDiffusionKDiffusionPipeline.tokenizer",description:`<strong>tokenizer</strong> (<code>CLIPTokenizer</code>) &#x2014;
Tokenizer of class
<a href="https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer" rel="nofollow">CLIPTokenizer</a>.`,name:"tokenizer"},{anchor:"diffusers.StableDiffusionKDiffusionPipeline.unet",description:'<strong>unet</strong> (<a href="/docs/diffusers/pr_10175/en/api/models/unet2d-cond#diffusers.UNet2DConditionModel">UNet2DConditionModel</a>) &#x2014; Conditional U-Net architecture to denoise the encoded image latents.',name:"unet"},{anchor:"diffusers.StableDiffusionKDiffusionPipeline.scheduler",description:`<strong>scheduler</strong> (<a href="/docs/diffusers/pr_10175/en/api/schedulers/overview#diffusers.SchedulerMixin">SchedulerMixin</a>) &#x2014;
A scheduler to be used in combination with <code>unet</code> to denoise the encoded image latents. Can be one of
<a href="/docs/diffusers/pr_10175/en/api/schedulers/ddim#diffusers.DDIMScheduler">DDIMScheduler</a>, <a href="/docs/diffusers/pr_10175/en/api/schedulers/lms_discrete#diffusers.LMSDiscreteScheduler">LMSDiscreteScheduler</a>, or <a href="/docs/diffusers/pr_10175/en/api/schedulers/pndm#diffusers.PNDMScheduler">PNDMScheduler</a>.`,name:"scheduler"},{anchor:"diffusers.StableDiffusionKDiffusionPipeline.safety_checker",description:`<strong>safety_checker</strong> (<code>StableDiffusionSafetyChecker</code>) &#x2014;
Classification module that estimates whether generated images could be considered offensive or harmful.
Please, refer to the <a href="https://huggingface.co/runwayml/stable-diffusion-v1-5" rel="nofollow">model card</a> for details.`,name:"safety_checker"},{anchor:"diffusers.StableDiffusionKDiffusionPipeline.feature_extractor",description:`<strong>feature_extractor</strong> (<code>CLIPImageProcessor</code>) &#x2014;
Model that extracts features from generated images to be used as inputs for the <code>safety_checker</code>.`,name:"feature_extractor"}],source:"https://github.com/huggingface/diffusers/blob/vr_10175/src/diffusers/pipelines/stable_diffusion_k_diffusion/pipeline_stable_diffusion_k_diffusion.py#L50"}}),P=new qe({props:{warning:!0,$$slots:{default:[Ue]},$$scope:{ctx:Y}}}),K=new de({props:{name:"encode_prompt",anchor:"diffusers.StableDiffusionKDiffusionPipeline.encode_prompt",parameters:[{name:"prompt",val:""},{name:"device",val:""},{name:"num_images_per_prompt",val:""},{name:"do_classifier_free_guidance",val:""},{name:"negative_prompt",val:" = None"},{name:"prompt_embeds",val:": typing.Optional[torch.Tensor] = None"},{name:"negative_prompt_embeds",val:": typing.Optional[torch.Tensor] = None"},{name:"lora_scale",val:": typing.Optional[float] = None"},{name:"clip_skip",val:": typing.Optional[int] = None"}],parametersDescription:[{anchor:"diffusers.StableDiffusionKDiffusionPipeline.encode_prompt.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
prompt to be encoded`,name:"prompt"},{anchor:"diffusers.StableDiffusionKDiffusionPipeline.encode_prompt.device",description:`<strong>device</strong> &#x2014; (<code>torch.device</code>):
torch device`,name:"device"},{anchor:"diffusers.StableDiffusionKDiffusionPipeline.encode_prompt.num_images_per_prompt",description:`<strong>num_images_per_prompt</strong> (<code>int</code>) &#x2014;
number of images that should be generated per prompt`,name:"num_images_per_prompt"},{anchor:"diffusers.StableDiffusionKDiffusionPipeline.encode_prompt.do_classifier_free_guidance",description:`<strong>do_classifier_free_guidance</strong> (<code>bool</code>) &#x2014;
whether to use classifier free guidance or not`,name:"do_classifier_free_guidance"},{anchor:"diffusers.StableDiffusionKDiffusionPipeline.encode_prompt.negative_prompt",description:`<strong>negative_prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
The prompt or prompts not to guide the image generation. If not defined, one has to pass
<code>negative_prompt_embeds</code> instead. Ignored when not using guidance (i.e., ignored if <code>guidance_scale</code> is
less than <code>1</code>).`,name:"negative_prompt"},{anchor:"diffusers.StableDiffusionKDiffusionPipeline.encode_prompt.prompt_embeds",description:`<strong>prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated text embeddings. Can be used to easily tweak text inputs, <em>e.g.</em> prompt weighting. If not
provided, text embeddings will be generated from <code>prompt</code> input argument.`,name:"prompt_embeds"},{anchor:"diffusers.StableDiffusionKDiffusionPipeline.encode_prompt.negative_prompt_embeds",description:`<strong>negative_prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, <em>e.g.</em> prompt
weighting. If not provided, negative_prompt_embeds will be generated from <code>negative_prompt</code> input
argument.`,name:"negative_prompt_embeds"},{anchor:"diffusers.StableDiffusionKDiffusionPipeline.encode_prompt.lora_scale",description:`<strong>lora_scale</strong> (<code>float</code>, <em>optional</em>) &#x2014;
A LoRA scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.`,name:"lora_scale"},{anchor:"diffusers.StableDiffusionKDiffusionPipeline.encode_prompt.clip_skip",description:`<strong>clip_skip</strong> (<code>int</code>, <em>optional</em>) &#x2014;
Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
the output of the pre-final layer will be used for computing the prompt embeddings.`,name:"clip_skip"}],source:"https://github.com/huggingface/diffusers/blob/vr_10175/src/diffusers/pipelines/stable_diffusion_k_diffusion/pipeline_stable_diffusion_k_diffusion.py#L183"}}),M=new Pe({props:{title:"StableDiffusionXLKDiffusionPipeline",local:"diffusers.StableDiffusionXLKDiffusionPipeline",headingTag:"h2"}}),I=new de({props:{name:"class diffusers.StableDiffusionXLKDiffusionPipeline",anchor:"diffusers.StableDiffusionXLKDiffusionPipeline",parameters:[{name:"vae",val:": AutoencoderKL"},{name:"text_encoder",val:": CLIPTextModel"},{name:"text_encoder_2",val:": CLIPTextModelWithProjection"},{name:"tokenizer",val:": CLIPTokenizer"},{name:"tokenizer_2",val:": CLIPTokenizer"},{name:"unet",val:": UNet2DConditionModel"},{name:"scheduler",val:": KarrasDiffusionSchedulers"},{name:"force_zeros_for_empty_prompt",val:": bool = True"}],parametersDescription:[{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.vae",description:`<strong>vae</strong> (<a href="/docs/diffusers/pr_10175/en/api/models/autoencoderkl#diffusers.AutoencoderKL">AutoencoderKL</a>) &#x2014;
Variational Auto-Encoder (VAE) Model to encode and decode images to and from latent representations.`,name:"vae"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.text_encoder",description:`<strong>text_encoder</strong> (<code>CLIPTextModel</code>) &#x2014;
Frozen text-encoder. Stable Diffusion XL uses the text portion of
<a href="https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModel" rel="nofollow">CLIP</a>, specifically
the <a href="https://huggingface.co/openai/clip-vit-large-patch14" rel="nofollow">clip-vit-large-patch14</a> variant.`,name:"text_encoder"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.text_encoder_2",description:`<strong>text_encoder_2</strong> (<code> CLIPTextModelWithProjection</code>) &#x2014;
Second frozen text-encoder. Stable Diffusion XL uses the text and pool portion of
<a href="https://huggingface.co/docs/transformers/model_doc/clip#transformers.CLIPTextModelWithProjection" rel="nofollow">CLIP</a>,
specifically the
<a href="https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k" rel="nofollow">laion/CLIP-ViT-bigG-14-laion2B-39B-b160k</a>
variant.`,name:"text_encoder_2"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.tokenizer",description:`<strong>tokenizer</strong> (<code>CLIPTokenizer</code>) &#x2014;
Tokenizer of class
<a href="https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer" rel="nofollow">CLIPTokenizer</a>.`,name:"tokenizer"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.tokenizer_2",description:`<strong>tokenizer_2</strong> (<code>CLIPTokenizer</code>) &#x2014;
Second Tokenizer of class
<a href="https://huggingface.co/docs/transformers/v4.21.0/en/model_doc/clip#transformers.CLIPTokenizer" rel="nofollow">CLIPTokenizer</a>.`,name:"tokenizer_2"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.unet",description:'<strong>unet</strong> (<a href="/docs/diffusers/pr_10175/en/api/models/unet2d-cond#diffusers.UNet2DConditionModel">UNet2DConditionModel</a>) &#x2014; Conditional U-Net architecture to denoise the encoded image latents.',name:"unet"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.scheduler",description:`<strong>scheduler</strong> (<a href="/docs/diffusers/pr_10175/en/api/schedulers/overview#diffusers.SchedulerMixin">SchedulerMixin</a>) &#x2014;
A scheduler to be used in combination with <code>unet</code> to denoise the encoded image latents. Can be one of
<a href="/docs/diffusers/pr_10175/en/api/schedulers/ddim#diffusers.DDIMScheduler">DDIMScheduler</a>, <a href="/docs/diffusers/pr_10175/en/api/schedulers/lms_discrete#diffusers.LMSDiscreteScheduler">LMSDiscreteScheduler</a>, or <a href="/docs/diffusers/pr_10175/en/api/schedulers/pndm#diffusers.PNDMScheduler">PNDMScheduler</a>.`,name:"scheduler"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.force_zeros_for_empty_prompt",description:`<strong>force_zeros_for_empty_prompt</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>&quot;True&quot;</code>) &#x2014;
Whether the negative prompt embeddings shall be forced to always be set to 0. Also see the config of
<code>stabilityai/stable-diffusion-xl-base-1-0</code>.`,name:"force_zeros_for_empty_prompt"}],source:"https://github.com/huggingface/diffusers/blob/vr_10175/src/diffusers/pipelines/stable_diffusion_k_diffusion/pipeline_stable_diffusion_xl_k_diffusion.py#L90"}}),z=new de({props:{name:"encode_prompt",anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.encode_prompt",parameters:[{name:"prompt",val:": str"},{name:"prompt_2",val:": typing.Optional[str] = None"},{name:"device",val:": typing.Optional[torch.device] = None"},{name:"num_images_per_prompt",val:": int = 1"},{name:"do_classifier_free_guidance",val:": bool = True"},{name:"negative_prompt",val:": typing.Optional[str] = None"},{name:"negative_prompt_2",val:": typing.Optional[str] = None"},{name:"prompt_embeds",val:": typing.Optional[torch.Tensor] = None"},{name:"negative_prompt_embeds",val:": typing.Optional[torch.Tensor] = None"},{name:"pooled_prompt_embeds",val:": typing.Optional[torch.Tensor] = None"},{name:"negative_pooled_prompt_embeds",val:": typing.Optional[torch.Tensor] = None"},{name:"lora_scale",val:": typing.Optional[float] = None"},{name:"clip_skip",val:": typing.Optional[int] = None"}],parametersDescription:[{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.encode_prompt.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
prompt to be encoded`,name:"prompt"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.encode_prompt.prompt_2",description:`<strong>prompt_2</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
The prompt or prompts to be sent to the <code>tokenizer_2</code> and <code>text_encoder_2</code>. If not defined, <code>prompt</code> is
used in both text-encoders`,name:"prompt_2"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.encode_prompt.device",description:`<strong>device</strong> &#x2014; (<code>torch.device</code>):
torch device`,name:"device"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.encode_prompt.num_images_per_prompt",description:`<strong>num_images_per_prompt</strong> (<code>int</code>) &#x2014;
number of images that should be generated per prompt`,name:"num_images_per_prompt"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.encode_prompt.do_classifier_free_guidance",description:`<strong>do_classifier_free_guidance</strong> (<code>bool</code>) &#x2014;
whether to use classifier free guidance or not`,name:"do_classifier_free_guidance"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.encode_prompt.negative_prompt",description:`<strong>negative_prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
The prompt or prompts not to guide the image generation. If not defined, one has to pass
<code>negative_prompt_embeds</code> instead. Ignored when not using guidance (i.e., ignored if <code>guidance_scale</code> is
less than <code>1</code>).`,name:"negative_prompt"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.encode_prompt.negative_prompt_2",description:`<strong>negative_prompt_2</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) &#x2014;
The prompt or prompts not to guide the image generation to be sent to <code>tokenizer_2</code> and
<code>text_encoder_2</code>. If not defined, <code>negative_prompt</code> is used in both text-encoders`,name:"negative_prompt_2"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.encode_prompt.prompt_embeds",description:`<strong>prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated text embeddings. Can be used to easily tweak text inputs, <em>e.g.</em> prompt weighting. If not
provided, text embeddings will be generated from <code>prompt</code> input argument.`,name:"prompt_embeds"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.encode_prompt.negative_prompt_embeds",description:`<strong>negative_prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated negative text embeddings. Can be used to easily tweak text inputs, <em>e.g.</em> prompt
weighting. If not provided, negative_prompt_embeds will be generated from <code>negative_prompt</code> input
argument.`,name:"negative_prompt_embeds"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.encode_prompt.pooled_prompt_embeds",description:`<strong>pooled_prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated pooled text embeddings. Can be used to easily tweak text inputs, <em>e.g.</em> prompt weighting.
If not provided, pooled text embeddings will be generated from <code>prompt</code> input argument.`,name:"pooled_prompt_embeds"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.encode_prompt.negative_pooled_prompt_embeds",description:`<strong>negative_pooled_prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) &#x2014;
Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, <em>e.g.</em> prompt
weighting. If not provided, pooled negative_prompt_embeds will be generated from <code>negative_prompt</code>
input argument.`,name:"negative_pooled_prompt_embeds"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.encode_prompt.lora_scale",description:`<strong>lora_scale</strong> (<code>float</code>, <em>optional</em>) &#x2014;
A lora scale that will be applied to all LoRA layers of the text encoder if LoRA layers are loaded.`,name:"lora_scale"},{anchor:"diffusers.StableDiffusionXLKDiffusionPipeline.encode_prompt.clip_skip",description:`<strong>clip_skip</strong> (<code>int</code>, <em>optional</em>) &#x2014;
Number of layers to be skipped from CLIP while computing the prompt embeddings. A value of 1 means that
the output of the pre-final layer will be used for computing the prompt embeddings.`,name:"clip_skip"}],source:"https://github.com/huggingface/diffusers/blob/vr_10175/src/diffusers/pipelines/stable_diffusion_k_diffusion/pipeline_stable_diffusion_xl_k_diffusion.py#L199"}}),X=new Re({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/pipelines/stable_diffusion/k_diffusion.md"}}),{c(){f=s("meta"),w=n(),g=s("p"),A=n(),_(k.$$.fragment),J=n(),$=s("p"),$.innerHTML=Le,Q=n(),C=s("p"),C.innerHTML=Se,Z=n(),_(T.$$.fragment),ee=n(),d=s("div"),_(y.$$.fragment),fe=n(),N=s("p"),N.textContent=we,le=n(),E=s("p"),E.innerHTML=ke,pe=n(),O=s("p"),O.textContent=$e,ce=n(),H=s("ul"),H.innerHTML=Ce,ue=n(),_(P.$$.fragment),me=n(),L=s("div"),_(K.$$.fragment),ge=n(),q=s("p"),q.textContent=Te,oe=n(),_(M.$$.fragment),te=n(),l=s("div"),_(I.$$.fragment),_e=n(),R=s("p"),R.textContent=ye,he=n(),U=s("p"),U.innerHTML=Ke,be=n(),V=s("p"),V.textContent=Me,ve=n(),W=s("ul"),W.innerHTML=Ie,xe=n(),S=s("div"),_(z.$$.fragment),De=n(),j=s("p"),j.textContent=ze,ie=n(),_(X.$$.fragment),ne=n(),G=s("p"),this.h()},l(e){const o=He("svelte-u9bgzb",document.head);f=a(o,"META",{name:!0,content:!0}),o.forEach(i),w=r(e),g=a(e,"P",{}),B(g).forEach(i),A=r(e),h(k.$$.fragment,e),J=r(e),$=a(e,"P",{"data-svelte-h":!0}),u($)!=="svelte-1u0qckb"&&($.innerHTML=Le),Q=r(e),C=a(e,"P",{"data-svelte-h":!0}),u(C)!=="svelte-kxbfc9"&&(C.innerHTML=Se),Z=r(e),h(T.$$.fragment,e),ee=r(e),d=a(e,"DIV",{class:!0});var p=B(d);h(y.$$.fragment,p),fe=r(p),N=a(p,"P",{"data-svelte-h":!0}),u(N)!=="svelte-35p306"&&(N.textContent=we),le=r(p),E=a(p,"P",{"data-svelte-h":!0}),u(E)!=="svelte-iqqbzt"&&(E.innerHTML=ke),pe=r(p),O=a(p,"P",{"data-svelte-h":!0}),u(O)!=="svelte-14s6m4u"&&(O.textContent=$e),ce=r(p),H=a(p,"UL",{"data-svelte-h":!0}),u(H)!=="svelte-1axywbm"&&(H.innerHTML=Ce),ue=r(p),h(P.$$.fragment,p),me=r(p),L=a(p,"DIV",{class:!0});var se=B(L);h(K.$$.fragment,se),ge=r(se),q=a(se,"P",{"data-svelte-h":!0}),u(q)!=="svelte-16q0ax1"&&(q.textContent=Te),se.forEach(i),p.forEach(i),oe=r(e),h(M.$$.fragment,e),te=r(e),l=a(e,"DIV",{class:!0});var m=B(l);h(I.$$.fragment,m),_e=r(m),R=a(m,"P",{"data-svelte-h":!0}),u(R)!=="svelte-3dg7oo"&&(R.textContent=ye),he=r(m),U=a(m,"P",{"data-svelte-h":!0}),u(U)!=="svelte-iqqbzt"&&(U.innerHTML=Ke),be=r(m),V=a(m,"P",{"data-svelte-h":!0}),u(V)!=="svelte-14s6m4u"&&(V.textContent=Me),ve=r(m),W=a(m,"UL",{"data-svelte-h":!0}),u(W)!=="svelte-1tzp7x5"&&(W.innerHTML=Ie),xe=r(m),S=a(m,"DIV",{class:!0});var ae=B(S);h(z.$$.fragment,ae),De=r(ae),j=a(ae,"P",{"data-svelte-h":!0}),u(j)!=="svelte-16q0ax1"&&(j.textContent=ze),ae.forEach(i),m.forEach(i),ie=r(e),h(X.$$.fragment,e),ne=r(e),G=a(e,"P",{}),B(G).forEach(i),this.h()},h(){F(f,"name","hf:doc:metadata"),F(f,"content",We),F(L,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),F(d,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),F(S,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),F(l,"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,o){t(document.head,f),c(e,w,o),c(e,g,o),c(e,A,o),b(k,e,o),c(e,J,o),c(e,$,o),c(e,Q,o),c(e,C,o),c(e,Z,o),b(T,e,o),c(e,ee,o),c(e,d,o),b(y,d,null),t(d,fe),t(d,N),t(d,le),t(d,E),t(d,pe),t(d,O),t(d,ce),t(d,H),t(d,ue),b(P,d,null),t(d,me),t(d,L),b(K,L,null),t(L,ge),t(L,q),c(e,oe,o),b(M,e,o),c(e,te,o),c(e,l,o),b(I,l,null),t(l,_e),t(l,R),t(l,he),t(l,U),t(l,be),t(l,V),t(l,ve),t(l,W),t(l,xe),t(l,S),b(z,S,null),t(S,De),t(S,j),c(e,ie,o),b(X,e,o),c(e,ne,o),c(e,G,o),re=!0},p(e,[o]){const p={};o&2&&(p.$$scope={dirty:o,ctx:e}),P.$set(p)},i(e){re||(v(k.$$.fragment,e),v(T.$$.fragment,e),v(y.$$.fragment,e),v(P.$$.fragment,e),v(K.$$.fragment,e),v(M.$$.fragment,e),v(I.$$.fragment,e),v(z.$$.fragment,e),v(X.$$.fragment,e),re=!0)},o(e){x(k.$$.fragment,e),x(T.$$.fragment,e),x(y.$$.fragment,e),x(P.$$.fragment,e),x(K.$$.fragment,e),x(M.$$.fragment,e),x(I.$$.fragment,e),x(z.$$.fragment,e),x(X.$$.fragment,e),re=!1},d(e){e&&(i(w),i(g),i(A),i(J),i($),i(Q),i(C),i(Z),i(ee),i(d),i(oe),i(te),i(l),i(ie),i(ne),i(G)),i(f),D(k,e),D(T,e),D(y),D(P),D(K),D(M,e),D(I),D(z),D(X,e)}}}const We='{"title":"K-Diffusion","local":"k-diffusion","sections":[{"title":"StableDiffusionKDiffusionPipeline","local":"diffusers.StableDiffusionKDiffusionPipeline","sections":[],"depth":2},{"title":"StableDiffusionXLKDiffusionPipeline","local":"diffusers.StableDiffusionXLKDiffusionPipeline","sections":[],"depth":2}],"depth":1}';function je(Y){return Ae(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Qe extends Ee{constructor(f){super(),Oe(this,f,je,Ve,Xe,{})}}export{Qe as component};