Buckets:

hf-doc-build
/

doc-dev

hf-doc-build/doc-dev / diffusers /pr_9715 /en /_app /immutable /nodes /101.52965cfb.js

rtrm's picture

3 months ago

78.9 kB

	import{s as Ta,o as va,n as $t}from"../chunks/scheduler.8c3d61f6.js";import{S as Ja,i as Ua,g as l,s as o,r as m,A as Pa,h as r,f as a,c as s,j as S,u,x as b,k as $,y as c,a as n,v as g,d as f,t as _,w as h}from"../chunks/index.da70eac4.js";import{T as xa}from"../chunks/Tip.1d9b8c37.js";import{D as V}from"../chunks/Docstring.6b390b9a.js";import{C as Xe}from"../chunks/CodeBlock.00a903b3.js";import{E as Ot}from"../chunks/ExampleCodeBlock.db12be95.js";import{H as U,E as ja}from"../chunks/EditOnGithub.1e64e623.js";function Sa(I){let d,v="There are some restrictions on data types that can be used with the Stable Cascade models. The official checkpoints for the <code>StableCascadePriorPipeline</code> do not support the <code>torch.float16</code> data type. Please use <code>torch.bfloat16</code> instead.",y,p,C="In order to use the <code>torch.bfloat16</code> data type with the <code>StableCascadeDecoderPipeline</code> you need to have PyTorch 2.2.0 or higher installed. This also means that using the <code>StableCascadeCombinedPipeline</code> with <code>torch.bfloat16</code> requires PyTorch 2.2.0 or higher, since it calls the <code>StableCascadeDecoderPipeline</code> internally.",i,w,Le="If it is not possible to install PyTorch 2.2.0 or higher in your environment, the <code>StableCascadeDecoderPipeline</code> can be used on its own with the <code>torch.float16</code> data type. You can download the full precision or <code>bf16</code> variant weights for the pipeline and cast the weights to <code>torch.float16</code>.";return{c(){d=l("p"),d.innerHTML=v,y=o(),p=l("p"),p.innerHTML=C,i=o(),w=l("p"),w.innerHTML=Le},l(M){d=r(M,"P",{"data-svelte-h":!0}),b(d)!=="svelte-1tw7sew"&&(d.innerHTML=v),y=s(M),p=r(M,"P",{"data-svelte-h":!0}),b(p)!=="svelte-szepwi"&&(p.innerHTML=C),i=s(M),w=r(M,"P",{"data-svelte-h":!0}),b(w)!=="svelte-jwlk0w"&&(w.innerHTML=Le)},m(M,P){n(M,d,P),n(M,y,P),n(M,p,P),n(M,i,P),n(M,w,P)},p:$t,d(M){M&&(a(d),a(y),a(p),a(i),a(w))}}}function $a(I){let d,v="Examples:",y,p,C;return p=new Xe({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> torch
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableCascadeCombinedPipeline

	<span class="hljs-meta">>>> </span>pipe = StableCascadeCombinedPipeline.from_pretrained(
	<span class="hljs-meta">... </span> <span class="hljs-string">"stabilityai/stable-cascade"</span>, variant=<span class="hljs-string">"bf16"</span>, torch_dtype=torch.bfloat16
	<span class="hljs-meta">... </span>)
	<span class="hljs-meta">>>> </span>pipe.enable_model_cpu_offload()
	<span class="hljs-meta">>>> </span>prompt = <span class="hljs-string">"an image of a shiba inu, donning a spacesuit and helmet"</span>
	<span class="hljs-meta">>>> </span>images = pipe(prompt=prompt)`,wrap:!1}}),{c(){d=l("p"),d.textContent=v,y=o(),m(p.$$.fragment)},l(i){d=r(i,"P",{"data-svelte-h":!0}),b(d)!=="svelte-kvfsh7"&&(d.textContent=v),y=s(i),u(p.$$.fragment,i)},m(i,w){n(i,d,w),n(i,y,w),g(p,i,w),C=!0},p:$t,i(i){C\|\|(f(p.$$.fragment,i),C=!0)},o(i){_(p.$$.fragment,i),C=!1},d(i){i&&(a(d),a(y)),h(p,i)}}}function Ia(I){let d,v="Examples:",y,p,C;return p=new Xe({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> torch
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableCascadePriorPipeline

	<span class="hljs-meta">>>> </span>prior_pipe = StableCascadePriorPipeline.from_pretrained(
	<span class="hljs-meta">... </span> <span class="hljs-string">"stabilityai/stable-cascade-prior"</span>, torch_dtype=torch.bfloat16
	<span class="hljs-meta">... </span>).to(<span class="hljs-string">"cuda"</span>)

	<span class="hljs-meta">>>> </span>prompt = <span class="hljs-string">"an image of a shiba inu, donning a spacesuit and helmet"</span>
	<span class="hljs-meta">>>> </span>prior_output = pipe(prompt)`,wrap:!1}}),{c(){d=l("p"),d.textContent=v,y=o(),m(p.$$.fragment)},l(i){d=r(i,"P",{"data-svelte-h":!0}),b(d)!=="svelte-kvfsh7"&&(d.textContent=v),y=s(i),u(p.$$.fragment,i)},m(i,w){n(i,d,w),n(i,y,w),g(p,i,w),C=!0},p:$t,i(i){C\|\|(f(p.$$.fragment,i),C=!0)},o(i){_(p.$$.fragment,i),C=!1},d(i){i&&(a(d),a(y)),h(p,i)}}}function Za(I){let d,v="Examples:",y,p,C;return p=new Xe({props:{code:"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",highlighted:`<span class="hljs-meta">>>> </span><span class="hljs-keyword">import</span> torch
	<span class="hljs-meta">>>> </span><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableCascadePriorPipeline, StableCascadeDecoderPipeline

	<span class="hljs-meta">>>> </span>prior_pipe = StableCascadePriorPipeline.from_pretrained(
	<span class="hljs-meta">... </span> <span class="hljs-string">"stabilityai/stable-cascade-prior"</span>, torch_dtype=torch.bfloat16
	<span class="hljs-meta">... </span>).to(<span class="hljs-string">"cuda"</span>)
	<span class="hljs-meta">>>> </span>gen_pipe = StableCascadeDecoderPipeline.from_pretrain(
	<span class="hljs-meta">... </span> <span class="hljs-string">"stabilityai/stable-cascade"</span>, torch_dtype=torch.float16
	<span class="hljs-meta">... </span>).to(<span class="hljs-string">"cuda"</span>)

	<span class="hljs-meta">>>> </span>prompt = <span class="hljs-string">"an image of a shiba inu, donning a spacesuit and helmet"</span>
	<span class="hljs-meta">>>> </span>prior_output = pipe(prompt)
	<span class="hljs-meta">>>> </span>images = gen_pipe(prior_output.image_embeddings, prompt=prompt)`,wrap:!1}}),{c(){d=l("p"),d.textContent=v,y=o(),m(p.$$.fragment)},l(i){d=r(i,"P",{"data-svelte-h":!0}),b(d)!=="svelte-kvfsh7"&&(d.textContent=v),y=s(i),u(p.$$.fragment,i)},m(i,w){n(i,d,w),n(i,y,w),g(p,i,w),C=!0},p:$t,i(i){C\|\|(f(p.$$.fragment,i),C=!0)},o(i){_(p.$$.fragment,i),C=!1},d(i){i&&(a(d),a(y)),h(p,i)}}}function ka(I){let d,v,y,p,C,i,w,Le=`This model is built upon the <a href="https://openreview.net/forum?id=gU58d5QeGv" rel="nofollow">Würstchen</a> architecture and its main
	difference to other models like Stable Diffusion is that it is working at a much smaller latent space. Why is this
	important? The smaller the latent space, the <strong>faster</strong> you can run inference and the <strong>cheaper</strong> the training becomes.
	How small is the latent space? Stable Diffusion uses a compression factor of 8, resulting in a 1024x1024 image being
	encoded to 128x128. Stable Cascade achieves a compression factor of 42, meaning that it is possible to encode a
	1024x1024 image to 24x24, while maintaining crisp reconstructions. The text-conditional model is then trained in the
	highly compressed latent space. Previous versions of this architecture, achieved a 16x cost reduction over Stable
	Diffusion 1.5.`,M,P,Kt=`Therefore, this kind of model is well suited for usages where efficiency is important. Furthermore, all known extensions
	like finetuning, LoRA, ControlNet, IP-Adapter, LCM etc. are possible with this method as well.`,ze,L,ea='The original codebase can be found at <a href="https://github.com/Stability-AI/StableCascade" rel="nofollow">Stability-AI/StableCascade</a>.',qe,F,Ae,z,ta=`Stable Cascade consists of three models: Stage A, Stage B and Stage C, representing a cascade to generate images,
	hence the name “Stable Cascade”.`,Oe,q,aa=`Stage A & B are used to compress images, similar to what the job of the VAE is in Stable Diffusion.
	However, with this setup, a much higher compression of images can be achieved. While the Stable Diffusion models use a
	spatial compression factor of 8, encoding an image with resolution of 1024 x 1024 to 128 x 128, Stable Cascade achieves
	a compression factor of 42. This encodes a 1024 x 1024 image to 24 x 24, while being able to accurately decode the
	image. This comes with the great benefit of cheaper training and inference. Furthermore, Stage C is responsible
	for generating the small 24 x 24 latents given a text prompt.`,Ke,A,na="The Stage C model operates on the small 24 x 24 latents and denoises the latents conditioned on text prompts. The model is also the largest component in the Cascade pipeline and is meant to be used with the <code>StableCascadePriorPipeline</code>",et,O,oa="The Stage B and Stage A models are used with the <code>StableCascadeDecoderPipeline</code> and are responsible for generating the final image given the small 24 x 24 latents.",tt,N,at,K,nt,ee,ot,te,st,ae,it,ne,lt,oe,sa="Loading the original format checkpoints is supported via <code>from_single_file</code> method in the StableCascadeUNet.",rt,se,dt,ie,ct,le,pt,re,ia="The model is intended for research purposes for now. Possible research areas and tasks include",mt,de,la="<li>Research on generative models.</li> <li>Safe deployment of models which have the potential to generate harmful content.</li> <li>Probing and understanding the limitations and biases of generative models.</li> <li>Generation of artworks and use in design and other artistic processes.</li> <li>Applications in educational or creative tools.</li>",ut,ce,ra="Excluded uses are described below.",gt,pe,ft,me,da=`The model was not trained to be factual or true representations of people or events,
	and therefore using the model to generate such content is out-of-scope for the abilities of this model.
	The model should not be used in any way that violates Stability AI’s <a href="https://stability.ai/use-policy" rel="nofollow">Acceptable Use Policy</a>.`,_t,ue,ht,ge,bt,fe,ca="<li>Faces and people in general may not be generated properly.</li> <li>The autoencoding part of the model is lossy.</li>",wt,_e,yt,T,he,It,Ie,pa="Combined Pipeline for text-to-image generation using Stable Cascade.",Zt,Ze,ma=`This model inherits from <a href="/docs/diffusers/pr_9715/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.)`,kt,Z,be,Wt,ke,ua="Function invoked when calling the pipeline for generation.",Gt,Y,Bt,R,we,Vt,We,ga=`Offloads all models to CPU using accelerate, reducing memory usage with a low impact on performance. Compared
	to <code>enable_sequential_cpu_offload</code>, this method moves one whole model at a time to the GPU when its <code>forward</code>
	method is called, and the model remains in GPU until the next model runs. Memory savings are lower than with
	<code>enable_sequential_cpu_offload</code>, but performance is much better due to the iterative execution of the <code>unet</code>.`,Nt,H,ye,Yt,Ge,fa=`Offloads all models (<code>unet</code>, <code>text_encoder</code>, <code>vae</code>, and <code>safety checker</code> state dicts) to CPU using 🤗
	Accelerate, significantly reducing memory usage. Models are moved to a <code>torch.device('meta')</code> and loaded on a
	GPU only when their specific submodule’s <code>forward</code> method is called. Offloading happens on a submodule basis.
	Memory savings are higher than using <code>enable_model_cpu_offload</code>, but performance is lower.`,Ct,Ce,Mt,x,Me,Rt,Be,_a="Pipeline for generating image prior for Stable Cascade.",Ht,Ve,ha=`This model inherits from <a href="/docs/diffusers/pr_9715/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.)`,Et,k,Te,Dt,Ne,ba="Function invoked when calling the pipeline for generation.",Qt,E,Tt,ve,vt,G,Je,Xt,Ye,wa="Output class for WuerstchenPriorPipeline.",Jt,Ue,Ut,j,Pe,Lt,Re,ya="Pipeline for generating images from the Stable Cascade model.",Ft,He,Ca=`This model inherits from <a href="/docs/diffusers/pr_9715/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.)`,zt,W,xe,qt,Ee,Ma="Function invoked when calling the pipeline for generation.",At,D,Pt,je,xt,Fe,jt;return C=new U({props:{title:"Stable Cascade",local:"stable-cascade",headingTag:"h1"}}),F=new U({props:{title:"Model Overview",local:"model-overview",headingTag:"h2"}}),N=new xa({props:{warning:!0,$$slots:{default:[Sa]},$$scope:{ctx:I}}}),K=new U({props:{title:"Usage example",local:"usage-example",headingTag:"h2"}}),ee=new Xe({props:{code:"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",highlighted:`<span class="hljs-keyword">import</span> torch
	<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableCascadeDecoderPipeline, StableCascadePriorPipeline

	prompt = <span class="hljs-string">"an image of a shiba inu, donning a spacesuit and helmet"</span>
	negative_prompt = <span class="hljs-string">""</span>

	prior = StableCascadePriorPipeline.from_pretrained(<span class="hljs-string">"stabilityai/stable-cascade-prior"</span>, variant=<span class="hljs-string">"bf16"</span>, torch_dtype=torch.bfloat16)
	decoder = StableCascadeDecoderPipeline.from_pretrained(<span class="hljs-string">"stabilityai/stable-cascade"</span>, variant=<span class="hljs-string">"bf16"</span>, torch_dtype=torch.float16)

	prior.enable_model_cpu_offload()
	prior_output = prior(
	prompt=prompt,
	height=<span class="hljs-number">1024</span>,
	width=<span class="hljs-number">1024</span>,
	negative_prompt=negative_prompt,
	guidance_scale=<span class="hljs-number">4.0</span>,
	num_images_per_prompt=<span class="hljs-number">1</span>,
	num_inference_steps=<span class="hljs-number">20</span>
	)

	decoder.enable_model_cpu_offload()
	decoder_output = decoder(
	image_embeddings=prior_output.image_embeddings.to(torch.float16),
	prompt=prompt,
	negative_prompt=negative_prompt,
	guidance_scale=<span class="hljs-number">0.0</span>,
	output_type=<span class="hljs-string">"pil"</span>,
	num_inference_steps=<span class="hljs-number">10</span>
	).images[<span class="hljs-number">0</span>]
	decoder_output.save(<span class="hljs-string">"cascade.png"</span>)`,wrap:!1}}),te=new U({props:{title:"Using the Lite Versions of the Stage B and Stage C models",local:"using-the-lite-versions-of-the-stage-b-and-stage-c-models",headingTag:"h2"}}),ae=new Xe({props:{code:"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",highlighted:`<span class="hljs-keyword">import</span> torch
	<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> (
	StableCascadeDecoderPipeline,
	StableCascadePriorPipeline,
	StableCascadeUNet,
	)

	prompt = <span class="hljs-string">"an image of a shiba inu, donning a spacesuit and helmet"</span>
	negative_prompt = <span class="hljs-string">""</span>

	prior_unet = StableCascadeUNet.from_pretrained(<span class="hljs-string">"stabilityai/stable-cascade-prior"</span>, subfolder=<span class="hljs-string">"prior_lite"</span>)
	decoder_unet = StableCascadeUNet.from_pretrained(<span class="hljs-string">"stabilityai/stable-cascade"</span>, subfolder=<span class="hljs-string">"decoder_lite"</span>)

	prior = StableCascadePriorPipeline.from_pretrained(<span class="hljs-string">"stabilityai/stable-cascade-prior"</span>, prior=prior_unet)
	decoder = StableCascadeDecoderPipeline.from_pretrained(<span class="hljs-string">"stabilityai/stable-cascade"</span>, decoder=decoder_unet)

	prior.enable_model_cpu_offload()
	prior_output = prior(
	prompt=prompt,
	height=<span class="hljs-number">1024</span>,
	width=<span class="hljs-number">1024</span>,
	negative_prompt=negative_prompt,
	guidance_scale=<span class="hljs-number">4.0</span>,
	num_images_per_prompt=<span class="hljs-number">1</span>,
	num_inference_steps=<span class="hljs-number">20</span>
	)

	decoder.enable_model_cpu_offload()
	decoder_output = decoder(
	image_embeddings=prior_output.image_embeddings,
	prompt=prompt,
	negative_prompt=negative_prompt,
	guidance_scale=<span class="hljs-number">0.0</span>,
	output_type=<span class="hljs-string">"pil"</span>,
	num_inference_steps=<span class="hljs-number">10</span>
	).images[<span class="hljs-number">0</span>]
	decoder_output.save(<span class="hljs-string">"cascade.png"</span>)`,wrap:!1}}),ne=new U({props:{title:"Loading original checkpoints with from_single_file",local:"loading-original-checkpoints-with-fromsinglefile",headingTag:"h2"}}),se=new Xe({props:{code:"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",highlighted:`<span class="hljs-keyword">import</span> torch
	<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> (
	StableCascadeDecoderPipeline,
	StableCascadePriorPipeline,
	StableCascadeUNet,
	)

	prompt = <span class="hljs-string">"an image of a shiba inu, donning a spacesuit and helmet"</span>
	negative_prompt = <span class="hljs-string">""</span>

	prior_unet = StableCascadeUNet.from_single_file(
	<span class="hljs-string">"https://huggingface.co/stabilityai/stable-cascade/resolve/main/stage_c_bf16.safetensors"</span>,
	torch_dtype=torch.bfloat16
	)
	decoder_unet = StableCascadeUNet.from_single_file(
	<span class="hljs-string">"https://huggingface.co/stabilityai/stable-cascade/blob/main/stage_b_bf16.safetensors"</span>,
	torch_dtype=torch.bfloat16
	)

	prior = StableCascadePriorPipeline.from_pretrained(<span class="hljs-string">"stabilityai/stable-cascade-prior"</span>, prior=prior_unet, torch_dtype=torch.bfloat16)
	decoder = StableCascadeDecoderPipeline.from_pretrained(<span class="hljs-string">"stabilityai/stable-cascade"</span>, decoder=decoder_unet, torch_dtype=torch.bfloat16)

	prior.enable_model_cpu_offload()
	prior_output = prior(
	prompt=prompt,
	height=<span class="hljs-number">1024</span>,
	width=<span class="hljs-number">1024</span>,
	negative_prompt=negative_prompt,
	guidance_scale=<span class="hljs-number">4.0</span>,
	num_images_per_prompt=<span class="hljs-number">1</span>,
	num_inference_steps=<span class="hljs-number">20</span>
	)

	decoder.enable_model_cpu_offload()
	decoder_output = decoder(
	image_embeddings=prior_output.image_embeddings,
	prompt=prompt,
	negative_prompt=negative_prompt,
	guidance_scale=<span class="hljs-number">0.0</span>,
	output_type=<span class="hljs-string">"pil"</span>,
	num_inference_steps=<span class="hljs-number">10</span>
	).images[<span class="hljs-number">0</span>]
	decoder_output.save(<span class="hljs-string">"cascade-single-file.png"</span>)`,wrap:!1}}),ie=new U({props:{title:"Uses",local:"uses",headingTag:"h2"}}),le=new U({props:{title:"Direct Use",local:"direct-use",headingTag:"h3"}}),pe=new U({props:{title:"Out-of-Scope Use",local:"out-of-scope-use",headingTag:"h3"}}),ue=new U({props:{title:"Limitations and Bias",local:"limitations-and-bias",headingTag:"h2"}}),ge=new U({props:{title:"Limitations",local:"limitations",headingTag:"h3"}}),_e=new U({props:{title:"StableCascadeCombinedPipeline",local:"diffusers.StableCascadeCombinedPipeline",headingTag:"h2"}}),he=new V({props:{name:"class diffusers.StableCascadeCombinedPipeline",anchor:"diffusers.StableCascadeCombinedPipeline",parameters:[{name:"tokenizer",val:": CLIPTokenizer"},{name:"text_encoder",val:": CLIPTextModel"},{name:"decoder",val:": StableCascadeUNet"},{name:"scheduler",val:": DDPMWuerstchenScheduler"},{name:"vqgan",val:": PaellaVQModel"},{name:"prior_prior",val:": StableCascadeUNet"},{name:"prior_text_encoder",val:": CLIPTextModel"},{name:"prior_tokenizer",val:": CLIPTokenizer"},{name:"prior_scheduler",val:": DDPMWuerstchenScheduler"},{name:"prior_feature_extractor",val:": Optional = None"},{name:"prior_image_encoder",val:": Optional = None"}],parametersDescription:[{anchor:"diffusers.StableCascadeCombinedPipeline.tokenizer",description:`<strong>tokenizer</strong> (<code>CLIPTokenizer</code>) —
	The decoder tokenizer to be used for text inputs.`,name:"tokenizer"},{anchor:"diffusers.StableCascadeCombinedPipeline.text_encoder",description:`<strong>text_encoder</strong> (<code>CLIPTextModel</code>) —
	The decoder text encoder to be used for text inputs.`,name:"text_encoder"},{anchor:"diffusers.StableCascadeCombinedPipeline.decoder",description:`<strong>decoder</strong> (<code>StableCascadeUNet</code>) —
	The decoder model to be used for decoder image generation pipeline.`,name:"decoder"},{anchor:"diffusers.StableCascadeCombinedPipeline.scheduler",description:`<strong>scheduler</strong> (<code>DDPMWuerstchenScheduler</code>) —
	The scheduler to be used for decoder image generation pipeline.`,name:"scheduler"},{anchor:"diffusers.StableCascadeCombinedPipeline.vqgan",description:`<strong>vqgan</strong> (<code>PaellaVQModel</code>) —
	The VQGAN model to be used for decoder image generation pipeline.`,name:"vqgan"},{anchor:"diffusers.StableCascadeCombinedPipeline.feature_extractor",description:`<strong>feature_extractor</strong> (<a href="https://huggingface.co/docs/transformers/main/en/model_doc/clip#transformers.CLIPImageProcessor" rel="nofollow">CLIPImageProcessor</a>) —
	Model that extracts features from generated images to be used as inputs for the <code>image_encoder</code>.`,name:"feature_extractor"},{anchor:"diffusers.StableCascadeCombinedPipeline.image_encoder",description:`<strong>image_encoder</strong> (<code>CLIPVisionModelWithProjection</code>) —
	Frozen CLIP image-encoder (<a href="https://huggingface.co/openai/clip-vit-large-patch14" rel="nofollow">clip-vit-large-patch14</a>).`,name:"image_encoder"},{anchor:"diffusers.StableCascadeCombinedPipeline.prior_prior",description:`<strong>prior_prior</strong> (<code>StableCascadeUNet</code>) —
	The prior model to be used for prior pipeline.`,name:"prior_prior"},{anchor:"diffusers.StableCascadeCombinedPipeline.prior_scheduler",description:`<strong>prior_scheduler</strong> (<code>DDPMWuerstchenScheduler</code>) —
	The scheduler to be used for prior pipeline.`,name:"prior_scheduler"}],source:"https://github.com/huggingface/diffusers/blob/vr_9715/src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade_combined.py#L45"}}),be=new V({props:{name:"__call__",anchor:"diffusers.StableCascadeCombinedPipeline.__call__",parameters:[{name:"prompt",val:": Union = None"},{name:"images",val:": Union = None"},{name:"height",val:": int = 512"},{name:"width",val:": int = 512"},{name:"prior_num_inference_steps",val:": int = 60"},{name:"prior_guidance_scale",val:": float = 4.0"},{name:"num_inference_steps",val:": int = 12"},{name:"decoder_guidance_scale",val:": float = 0.0"},{name:"negative_prompt",val:": Union = None"},{name:"prompt_embeds",val:": Optional = None"},{name:"prompt_embeds_pooled",val:": Optional = None"},{name:"negative_prompt_embeds",val:": Optional = None"},{name:"negative_prompt_embeds_pooled",val:": Optional = None"},{name:"num_images_per_prompt",val:": int = 1"},{name:"generator",val:": Union = None"},{name:"latents",val:": Optional = None"},{name:"output_type",val:": Optional = 'pil'"},{name:"return_dict",val:": bool = True"},{name:"prior_callback_on_step_end",val:": Optional = None"},{name:"prior_callback_on_step_end_tensor_inputs",val:": List = ['latents']"},{name:"callback_on_step_end",val:": Optional = None"},{name:"callback_on_step_end_tensor_inputs",val:": List = ['latents']"}],parametersDescription:[{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>List[str]</code>) —
	The prompt or prompts to guide the image generation for the prior and decoder.`,name:"prompt"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.images",description:`<strong>images</strong> (<code>torch.Tensor</code>, <code>PIL.Image.Image</code>, <code>List[torch.Tensor]</code>, <code>List[PIL.Image.Image]</code>, <em>optional</em>) —
	The images to guide the image generation for the prior.`,name:"images"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.negative_prompt",description:`<strong>negative_prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) —
	The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored
	if <code>guidance_scale</code> is less than <code>1</code>).`,name:"negative_prompt"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.prompt_embeds",description:`<strong>prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	Pre-generated text embeddings for the prior. 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.StableCascadeCombinedPipeline.__call__.prompt_embeds_pooled",description:`<strong>prompt_embeds_pooled</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	Pre-generated text embeddings for the prior. 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_pooled"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.negative_prompt_embeds",description:`<strong>negative_prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	Pre-generated negative text embeddings for the prior. 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.StableCascadeCombinedPipeline.__call__.negative_prompt_embeds_pooled",description:`<strong>negative_prompt_embeds_pooled</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	Pre-generated negative text embeddings for the prior. 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_pooled"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.num_images_per_prompt",description:`<strong>num_images_per_prompt</strong> (<code>int</code>, <em>optional</em>, defaults to 1) —
	The number of images to generate per prompt.`,name:"num_images_per_prompt"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.height",description:`<strong>height</strong> (<code>int</code>, <em>optional</em>, defaults to 512) —
	The height in pixels of the generated image.`,name:"height"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.width",description:`<strong>width</strong> (<code>int</code>, <em>optional</em>, defaults to 512) —
	The width in pixels of the generated image.`,name:"width"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.prior_guidance_scale",description:`<strong>prior_guidance_scale</strong> (<code>float</code>, <em>optional</em>, defaults to 4.0) —
	Guidance scale as defined in <a href="https://arxiv.org/abs/2207.12598" rel="nofollow">Classifier-Free Diffusion Guidance</a>.
	<code>prior_guidance_scale</code> is defined as <code>w</code> of equation 2. of <a href="https://arxiv.org/pdf/2205.11487.pdf" rel="nofollow">Imagen
	Paper</a>. Guidance scale is enabled by setting
	<code>prior_guidance_scale > 1</code>. Higher guidance scale encourages to generate images that are closely linked
	to the text <code>prompt</code>, usually at the expense of lower image quality.`,name:"prior_guidance_scale"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.prior_num_inference_steps",description:`<strong>prior_num_inference_steps</strong> (<code>Union[int, Dict[float, int]]</code>, <em>optional</em>, defaults to 60) —
	The number of prior denoising steps. More denoising steps usually lead to a higher quality image at the
	expense of slower inference. For more specific timestep spacing, you can pass customized
	<code>prior_timesteps</code>`,name:"prior_num_inference_steps"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.num_inference_steps",description:`<strong>num_inference_steps</strong> (<code>int</code>, <em>optional</em>, defaults to 12) —
	The number of decoder denoising steps. More denoising steps usually lead to a higher quality image at
	the expense of slower inference. For more specific timestep spacing, you can pass customized
	<code>timesteps</code>`,name:"num_inference_steps"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.decoder_guidance_scale",description:`<strong>decoder_guidance_scale</strong> (<code>float</code>, <em>optional</em>, defaults to 0.0) —
	Guidance scale as defined in <a href="https://arxiv.org/abs/2207.12598" rel="nofollow">Classifier-Free Diffusion Guidance</a>.
	<code>guidance_scale</code> is defined as <code>w</code> of equation 2. of <a href="https://arxiv.org/pdf/2205.11487.pdf" rel="nofollow">Imagen
	Paper</a>. Guidance scale is enabled by setting <code>guidance_scale > 1</code>. Higher guidance scale encourages to generate images that are closely linked to the text <code>prompt</code>,
	usually at the expense of lower image quality.`,name:"decoder_guidance_scale"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.generator",description:`<strong>generator</strong> (<code>torch.Generator</code> or <code>List[torch.Generator]</code>, <em>optional</em>) —
	One or a list of <a href="https://pytorch.org/docs/stable/generated/torch.Generator.html" rel="nofollow">torch generator(s)</a>
	to make generation deterministic.`,name:"generator"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.latents",description:`<strong>latents</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
	generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
	tensor will ge generated by sampling using the supplied random <code>generator</code>.`,name:"latents"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.output_type",description:`<strong>output_type</strong> (<code>str</code>, <em>optional</em>, defaults to <code>"pil"</code>) —
	The output format of the generate image. Choose between: <code>"pil"</code> (<code>PIL.Image.Image</code>), <code>"np"</code>
	(<code>np.array</code>) or <code>"pt"</code> (<code>torch.Tensor</code>).`,name:"output_type"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.return_dict",description:`<strong>return_dict</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) —
	Whether or not to return a <a href="/docs/diffusers/pr_9715/en/api/pipelines/latent_diffusion#diffusers.ImagePipelineOutput">ImagePipelineOutput</a> instead of a plain tuple.`,name:"return_dict"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.prior_callback_on_step_end",description:`<strong>prior_callback_on_step_end</strong> (<code>Callable</code>, <em>optional</em>) —
	A function that calls at the end of each denoising steps during the inference. The function is called
	with the following arguments: <code>prior_callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict)</code>.`,name:"prior_callback_on_step_end"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.prior_callback_on_step_end_tensor_inputs",description:`<strong>prior_callback_on_step_end_tensor_inputs</strong> (<code>List</code>, <em>optional</em>) —
	The list of tensor inputs for the <code>prior_callback_on_step_end</code> function. The tensors specified in the
	list will be passed as <code>callback_kwargs</code> argument. You will only be able to include variables listed in
	the <code>._callback_tensor_inputs</code> attribute of your pipeline class.`,name:"prior_callback_on_step_end_tensor_inputs"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.callback_on_step_end",description:`<strong>callback_on_step_end</strong> (<code>Callable</code>, <em>optional</em>) —
	A function that calls at the end of each denoising steps during the inference. The function is called
	with the following arguments: <code>callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict)</code>. <code>callback_kwargs</code> will include a list of all tensors as specified by
	<code>callback_on_step_end_tensor_inputs</code>.`,name:"callback_on_step_end"},{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.callback_on_step_end_tensor_inputs",description:`<strong>callback_on_step_end_tensor_inputs</strong> (<code>List</code>, <em>optional</em>) —
	The list of tensor inputs for the <code>callback_on_step_end</code> function. The tensors specified in the list
	will be passed as <code>callback_kwargs</code> argument. You will only be able to include variables listed in the
	<code>._callback_tensor_inputs</code> attribute of your pipeline class.`,name:"callback_on_step_end_tensor_inputs"}],source:"https://github.com/huggingface/diffusers/blob/vr_9715/src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade_combined.py#L152",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


	<p><a
	href="/docs/diffusers/pr_9715/en/api/pipelines/latent_diffusion#diffusers.ImagePipelineOutput"
	>ImagePipelineOutput</a> or <code>tuple</code> <a
	href="/docs/diffusers/pr_9715/en/api/pipelines/latent_diffusion#diffusers.ImagePipelineOutput"
	>ImagePipelineOutput</a> if <code>return_dict</code> is True,
	otherwise a <code>tuple</code>. When returning a tuple, the first element is a list with the generated images.</p>
	`}}),Y=new Ot({props:{anchor:"diffusers.StableCascadeCombinedPipeline.__call__.example",$$slots:{default:[$a]},$$scope:{ctx:I}}}),we=new V({props:{name:"enable_model_cpu_offload",anchor:"diffusers.StableCascadeCombinedPipeline.enable_model_cpu_offload",parameters:[{name:"gpu_id",val:": Optional = None"},{name:"device",val:": Union = 'cuda'"}],source:"https://github.com/huggingface/diffusers/blob/vr_9715/src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade_combined.py#L124"}}),ye=new V({props:{name:"enable_sequential_cpu_offload",anchor:"diffusers.StableCascadeCombinedPipeline.enable_sequential_cpu_offload",parameters:[{name:"gpu_id",val:": Optional = None"},{name:"device",val:": Union = 'cuda'"}],source:"https://github.com/huggingface/diffusers/blob/vr_9715/src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade_combined.py#L134"}}),Ce=new U({props:{title:"StableCascadePriorPipeline",local:"diffusers.StableCascadePriorPipeline",headingTag:"h2"}}),Me=new V({props:{name:"class diffusers.StableCascadePriorPipeline",anchor:"diffusers.StableCascadePriorPipeline",parameters:[{name:"tokenizer",val:": CLIPTokenizer"},{name:"text_encoder",val:": CLIPTextModelWithProjection"},{name:"prior",val:": StableCascadeUNet"},{name:"scheduler",val:": DDPMWuerstchenScheduler"},{name:"resolution_multiple",val:": float = 42.67"},{name:"feature_extractor",val:": Optional = None"},{name:"image_encoder",val:": Optional = None"}],parametersDescription:[{anchor:"diffusers.StableCascadePriorPipeline.prior",description:`<strong>prior</strong> (<code>StableCascadeUNet</code>) —
	The Stable Cascade prior to approximate the image embedding from the text and/or image embedding.`,name:"prior"},{anchor:"diffusers.StableCascadePriorPipeline.text_encoder",description:`<strong>text_encoder</strong> (<code>CLIPTextModelWithProjection</code>) —
	Frozen text-encoder
	(<a href="https://huggingface.co/laion/CLIP-ViT-bigG-14-laion2B-39B-b160k" rel="nofollow">laion/CLIP-ViT-bigG-14-laion2B-39B-b160k</a>).`,name:"text_encoder"},{anchor:"diffusers.StableCascadePriorPipeline.feature_extractor",description:`<strong>feature_extractor</strong> (<a href="https://huggingface.co/docs/transformers/main/en/model_doc/clip#transformers.CLIPImageProcessor" rel="nofollow">CLIPImageProcessor</a>) —
	Model that extracts features from generated images to be used as inputs for the <code>image_encoder</code>.`,name:"feature_extractor"},{anchor:"diffusers.StableCascadePriorPipeline.image_encoder",description:`<strong>image_encoder</strong> (<code>CLIPVisionModelWithProjection</code>) —
	Frozen CLIP image-encoder (<a href="https://huggingface.co/openai/clip-vit-large-patch14" rel="nofollow">clip-vit-large-patch14</a>).`,name:"image_encoder"},{anchor:"diffusers.StableCascadePriorPipeline.tokenizer",description:`<strong>tokenizer</strong> (<code>CLIPTokenizer</code>) —
	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.StableCascadePriorPipeline.scheduler",description:`<strong>scheduler</strong> (<code>DDPMWuerstchenScheduler</code>) —
	A scheduler to be used in combination with <code>prior</code> to generate image embedding.`,name:"scheduler"},{anchor:"diffusers.StableCascadePriorPipeline.resolution_multiple",description:`<strong>resolution_multiple</strong> (‘float’, <em>optional</em>, defaults to 42.67) —
	Default resolution for multiple images generated.`,name:"resolution_multiple"}],source:"https://github.com/huggingface/diffusers/blob/vr_9715/src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade_prior.py#L72"}}),Te=new V({props:{name:"__call__",anchor:"diffusers.StableCascadePriorPipeline.__call__",parameters:[{name:"prompt",val:": Union = None"},{name:"images",val:": Union = None"},{name:"height",val:": int = 1024"},{name:"width",val:": int = 1024"},{name:"num_inference_steps",val:": int = 20"},{name:"timesteps",val:": List = None"},{name:"guidance_scale",val:": float = 4.0"},{name:"negative_prompt",val:": Union = None"},{name:"prompt_embeds",val:": Optional = None"},{name:"prompt_embeds_pooled",val:": Optional = None"},{name:"negative_prompt_embeds",val:": Optional = None"},{name:"negative_prompt_embeds_pooled",val:": Optional = None"},{name:"image_embeds",val:": Optional = None"},{name:"num_images_per_prompt",val:": Optional = 1"},{name:"generator",val:": Union = None"},{name:"latents",val:": Optional = None"},{name:"output_type",val:": Optional = 'pt'"},{name:"return_dict",val:": bool = True"},{name:"callback_on_step_end",val:": Optional = None"},{name:"callback_on_step_end_tensor_inputs",val:": List = ['latents']"}],parametersDescription:[{anchor:"diffusers.StableCascadePriorPipeline.__call__.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>List[str]</code>) —
	The prompt or prompts to guide the image generation.`,name:"prompt"},{anchor:"diffusers.StableCascadePriorPipeline.__call__.height",description:`<strong>height</strong> (<code>int</code>, <em>optional</em>, defaults to 1024) —
	The height in pixels of the generated image.`,name:"height"},{anchor:"diffusers.StableCascadePriorPipeline.__call__.width",description:`<strong>width</strong> (<code>int</code>, <em>optional</em>, defaults to 1024) —
	The width in pixels of the generated image.`,name:"width"},{anchor:"diffusers.StableCascadePriorPipeline.__call__.num_inference_steps",description:`<strong>num_inference_steps</strong> (<code>int</code>, <em>optional</em>, defaults to 60) —
	The number of denoising steps. More denoising steps usually lead to a higher quality image at the
	expense of slower inference.`,name:"num_inference_steps"},{anchor:"diffusers.StableCascadePriorPipeline.__call__.guidance_scale",description:`<strong>guidance_scale</strong> (<code>float</code>, <em>optional</em>, defaults to 8.0) —
	Guidance scale as defined in <a href="https://arxiv.org/abs/2207.12598" rel="nofollow">Classifier-Free Diffusion Guidance</a>.
	<code>decoder_guidance_scale</code> is defined as <code>w</code> of equation 2. of <a href="https://arxiv.org/pdf/2205.11487.pdf" rel="nofollow">Imagen
	Paper</a>. Guidance scale is enabled by setting
	<code>decoder_guidance_scale > 1</code>. Higher guidance scale encourages to generate images that are closely
	linked to the text <code>prompt</code>, usually at the expense of lower image quality.`,name:"guidance_scale"},{anchor:"diffusers.StableCascadePriorPipeline.__call__.negative_prompt",description:`<strong>negative_prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) —
	The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored
	if <code>decoder_guidance_scale</code> is less than <code>1</code>).`,name:"negative_prompt"},{anchor:"diffusers.StableCascadePriorPipeline.__call__.prompt_embeds",description:`<strong>prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	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.StableCascadePriorPipeline.__call__.prompt_embeds_pooled",description:`<strong>prompt_embeds_pooled</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	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:"prompt_embeds_pooled"},{anchor:"diffusers.StableCascadePriorPipeline.__call__.negative_prompt_embeds",description:`<strong>negative_prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	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.StableCascadePriorPipeline.__call__.negative_prompt_embeds_pooled",description:`<strong>negative_prompt_embeds_pooled</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, <em>e.g.</em> prompt
	weighting. If not provided, negative_prompt_embeds_pooled will be generated from <code>negative_prompt</code>
	input argument.`,name:"negative_prompt_embeds_pooled"},{anchor:"diffusers.StableCascadePriorPipeline.__call__.image_embeds",description:`<strong>image_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	Pre-generated image embeddings. Can be used to easily tweak image inputs, <em>e.g.</em> prompt weighting. If
	not provided, image embeddings will be generated from <code>image</code> input argument if existing.`,name:"image_embeds"},{anchor:"diffusers.StableCascadePriorPipeline.__call__.num_images_per_prompt",description:`<strong>num_images_per_prompt</strong> (<code>int</code>, <em>optional</em>, defaults to 1) —
	The number of images to generate per prompt.`,name:"num_images_per_prompt"},{anchor:"diffusers.StableCascadePriorPipeline.__call__.generator",description:`<strong>generator</strong> (<code>torch.Generator</code> or <code>List[torch.Generator]</code>, <em>optional</em>) —
	One or a list of <a href="https://pytorch.org/docs/stable/generated/torch.Generator.html" rel="nofollow">torch generator(s)</a>
	to make generation deterministic.`,name:"generator"},{anchor:"diffusers.StableCascadePriorPipeline.__call__.latents",description:`<strong>latents</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
	generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
	tensor will ge generated by sampling using the supplied random <code>generator</code>.`,name:"latents"},{anchor:"diffusers.StableCascadePriorPipeline.__call__.output_type",description:`<strong>output_type</strong> (<code>str</code>, <em>optional</em>, defaults to <code>"pil"</code>) —
	The output format of the generate image. Choose between: <code>"pil"</code> (<code>PIL.Image.Image</code>), <code>"np"</code>
	(<code>np.array</code>) or <code>"pt"</code> (<code>torch.Tensor</code>).`,name:"output_type"},{anchor:"diffusers.StableCascadePriorPipeline.__call__.return_dict",description:`<strong>return_dict</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) —
	Whether or not to return a <a href="/docs/diffusers/pr_9715/en/api/pipelines/latent_diffusion#diffusers.ImagePipelineOutput">ImagePipelineOutput</a> instead of a plain tuple.`,name:"return_dict"},{anchor:"diffusers.StableCascadePriorPipeline.__call__.callback_on_step_end",description:`<strong>callback_on_step_end</strong> (<code>Callable</code>, <em>optional</em>) —
	A function that calls at the end of each denoising steps during the inference. The function is called
	with the following arguments: <code>callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict)</code>. <code>callback_kwargs</code> will include a list of all tensors as specified by
	<code>callback_on_step_end_tensor_inputs</code>.`,name:"callback_on_step_end"},{anchor:"diffusers.StableCascadePriorPipeline.__call__.callback_on_step_end_tensor_inputs",description:`<strong>callback_on_step_end_tensor_inputs</strong> (<code>List</code>, <em>optional</em>) —
	The list of tensor inputs for the <code>callback_on_step_end</code> function. The tensors specified in the list
	will be passed as <code>callback_kwargs</code> argument. You will only be able to include variables listed in the
	<code>._callback_tensor_inputs</code> attribute of your pipeline class.`,name:"callback_on_step_end_tensor_inputs"}],source:"https://github.com/huggingface/diffusers/blob/vr_9715/src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade_prior.py#L365",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


	<p><code>StableCascadePriorPipelineOutput</code> or <code>tuple</code> <code>StableCascadePriorPipelineOutput</code> if <code>return_dict</code> is
	True, otherwise a <code>tuple</code>. When returning a tuple, the first element is a list with the generated image
	embeddings.</p>
	`}}),E=new Ot({props:{anchor:"diffusers.StableCascadePriorPipeline.__call__.example",$$slots:{default:[Ia]},$$scope:{ctx:I}}}),ve=new U({props:{title:"StableCascadePriorPipelineOutput",local:"diffusers.pipelines.stable_cascade.pipeline_stable_cascade_prior.StableCascadePriorPipelineOutput",headingTag:"h2"}}),Je=new V({props:{name:"class diffusers.pipelines.stable_cascade.pipeline_stable_cascade_prior.StableCascadePriorPipelineOutput",anchor:"diffusers.pipelines.stable_cascade.pipeline_stable_cascade_prior.StableCascadePriorPipelineOutput",parameters:[{name:"image_embeddings",val:": Union"},{name:"prompt_embeds",val:": Union"},{name:"prompt_embeds_pooled",val:": Union"},{name:"negative_prompt_embeds",val:": Union"},{name:"negative_prompt_embeds_pooled",val:": Union"}],parametersDescription:[{anchor:"diffusers.pipelines.stable_cascade.pipeline_stable_cascade_prior.StableCascadePriorPipelineOutput.image_embeddings",description:`<strong>image_embeddings</strong> (<code>torch.Tensor</code> or <code>np.ndarray</code>) —
	Prior image embeddings for text prompt`,name:"image_embeddings"},{anchor:"diffusers.pipelines.stable_cascade.pipeline_stable_cascade_prior.StableCascadePriorPipelineOutput.prompt_embeds",description:`<strong>prompt_embeds</strong> (<code>torch.Tensor</code>) —
	Text embeddings for the prompt.`,name:"prompt_embeds"},{anchor:"diffusers.pipelines.stable_cascade.pipeline_stable_cascade_prior.StableCascadePriorPipelineOutput.negative_prompt_embeds",description:`<strong>negative_prompt_embeds</strong> (<code>torch.Tensor</code>) —
	Text embeddings for the negative prompt.`,name:"negative_prompt_embeds"}],source:"https://github.com/huggingface/diffusers/blob/vr_9715/src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade_prior.py#L51"}}),Ue=new U({props:{title:"StableCascadeDecoderPipeline",local:"diffusers.StableCascadeDecoderPipeline",headingTag:"h2"}}),Pe=new V({props:{name:"class diffusers.StableCascadeDecoderPipeline",anchor:"diffusers.StableCascadeDecoderPipeline",parameters:[{name:"decoder",val:": StableCascadeUNet"},{name:"tokenizer",val:": CLIPTokenizer"},{name:"text_encoder",val:": CLIPTextModel"},{name:"scheduler",val:": DDPMWuerstchenScheduler"},{name:"vqgan",val:": PaellaVQModel"},{name:"latent_dim_scale",val:": float = 10.67"}],parametersDescription:[{anchor:"diffusers.StableCascadeDecoderPipeline.tokenizer",description:`<strong>tokenizer</strong> (<code>CLIPTokenizer</code>) —
	The CLIP tokenizer.`,name:"tokenizer"},{anchor:"diffusers.StableCascadeDecoderPipeline.text_encoder",description:`<strong>text_encoder</strong> (<code>CLIPTextModel</code>) —
	The CLIP text encoder.`,name:"text_encoder"},{anchor:"diffusers.StableCascadeDecoderPipeline.decoder",description:`<strong>decoder</strong> (<code>StableCascadeUNet</code>) —
	The Stable Cascade decoder unet.`,name:"decoder"},{anchor:"diffusers.StableCascadeDecoderPipeline.vqgan",description:`<strong>vqgan</strong> (<code>PaellaVQModel</code>) —
	The VQGAN model.`,name:"vqgan"},{anchor:"diffusers.StableCascadeDecoderPipeline.scheduler",description:`<strong>scheduler</strong> (<code>DDPMWuerstchenScheduler</code>) —
	A scheduler to be used in combination with <code>prior</code> to generate image embedding.`,name:"scheduler"},{anchor:"diffusers.StableCascadeDecoderPipeline.latent_dim_scale",description:`<strong>latent_dim_scale</strong> (float, <code>optional</code>, defaults to 10.67) —
	Multiplier to determine the VQ latent space size from the image embeddings. If the image embeddings are
	height=24 and width=24, the VQ latent shape needs to be height=int(24<em>10.67)=256 and
	width=int(24</em>10.67)=256 in order to match the training conditions.`,name:"latent_dim_scale"}],source:"https://github.com/huggingface/diffusers/blob/vr_9715/src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade.py#L50"}}),xe=new V({props:{name:"__call__",anchor:"diffusers.StableCascadeDecoderPipeline.__call__",parameters:[{name:"image_embeddings",val:": Union"},{name:"prompt",val:": Union = None"},{name:"num_inference_steps",val:": int = 10"},{name:"guidance_scale",val:": float = 0.0"},{name:"negative_prompt",val:": Union = None"},{name:"prompt_embeds",val:": Optional = None"},{name:"prompt_embeds_pooled",val:": Optional = None"},{name:"negative_prompt_embeds",val:": Optional = None"},{name:"negative_prompt_embeds_pooled",val:": Optional = None"},{name:"num_images_per_prompt",val:": int = 1"},{name:"generator",val:": Union = None"},{name:"latents",val:": Optional = None"},{name:"output_type",val:": Optional = 'pil'"},{name:"return_dict",val:": bool = True"},{name:"callback_on_step_end",val:": Optional = None"},{name:"callback_on_step_end_tensor_inputs",val:": List = ['latents']"}],parametersDescription:[{anchor:"diffusers.StableCascadeDecoderPipeline.__call__.image_embedding",description:`<strong>image_embedding</strong> (<code>torch.Tensor</code> or <code>List[torch.Tensor]</code>) —
	Image Embeddings either extracted from an image or generated by a Prior Model.`,name:"image_embedding"},{anchor:"diffusers.StableCascadeDecoderPipeline.__call__.prompt",description:`<strong>prompt</strong> (<code>str</code> or <code>List[str]</code>) —
	The prompt or prompts to guide the image generation.`,name:"prompt"},{anchor:"diffusers.StableCascadeDecoderPipeline.__call__.num_inference_steps",description:`<strong>num_inference_steps</strong> (<code>int</code>, <em>optional</em>, defaults to 12) —
	The number of denoising steps. More denoising steps usually lead to a higher quality image at the
	expense of slower inference.`,name:"num_inference_steps"},{anchor:"diffusers.StableCascadeDecoderPipeline.__call__.guidance_scale",description:`<strong>guidance_scale</strong> (<code>float</code>, <em>optional</em>, defaults to 0.0) —
	Guidance scale as defined in <a href="https://arxiv.org/abs/2207.12598" rel="nofollow">Classifier-Free Diffusion Guidance</a>.
	<code>decoder_guidance_scale</code> is defined as <code>w</code> of equation 2. of <a href="https://arxiv.org/pdf/2205.11487.pdf" rel="nofollow">Imagen
	Paper</a>. Guidance scale is enabled by setting
	<code>decoder_guidance_scale > 1</code>. Higher guidance scale encourages to generate images that are closely
	linked to the text <code>prompt</code>, usually at the expense of lower image quality.`,name:"guidance_scale"},{anchor:"diffusers.StableCascadeDecoderPipeline.__call__.negative_prompt",description:`<strong>negative_prompt</strong> (<code>str</code> or <code>List[str]</code>, <em>optional</em>) —
	The prompt or prompts not to guide the image generation. Ignored when not using guidance (i.e., ignored
	if <code>decoder_guidance_scale</code> is less than <code>1</code>).`,name:"negative_prompt"},{anchor:"diffusers.StableCascadeDecoderPipeline.__call__.prompt_embeds",description:`<strong>prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	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.StableCascadeDecoderPipeline.__call__.prompt_embeds_pooled",description:`<strong>prompt_embeds_pooled</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	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:"prompt_embeds_pooled"},{anchor:"diffusers.StableCascadeDecoderPipeline.__call__.negative_prompt_embeds",description:`<strong>negative_prompt_embeds</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	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.StableCascadeDecoderPipeline.__call__.negative_prompt_embeds_pooled",description:`<strong>negative_prompt_embeds_pooled</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	Pre-generated negative pooled text embeddings. Can be used to easily tweak text inputs, <em>e.g.</em> prompt
	weighting. If not provided, negative_prompt_embeds_pooled will be generated from <code>negative_prompt</code>
	input argument.`,name:"negative_prompt_embeds_pooled"},{anchor:"diffusers.StableCascadeDecoderPipeline.__call__.num_images_per_prompt",description:`<strong>num_images_per_prompt</strong> (<code>int</code>, <em>optional</em>, defaults to 1) —
	The number of images to generate per prompt.`,name:"num_images_per_prompt"},{anchor:"diffusers.StableCascadeDecoderPipeline.__call__.generator",description:`<strong>generator</strong> (<code>torch.Generator</code> or <code>List[torch.Generator]</code>, <em>optional</em>) —
	One or a list of <a href="https://pytorch.org/docs/stable/generated/torch.Generator.html" rel="nofollow">torch generator(s)</a>
	to make generation deterministic.`,name:"generator"},{anchor:"diffusers.StableCascadeDecoderPipeline.__call__.latents",description:`<strong>latents</strong> (<code>torch.Tensor</code>, <em>optional</em>) —
	Pre-generated noisy latents, sampled from a Gaussian distribution, to be used as inputs for image
	generation. Can be used to tweak the same generation with different prompts. If not provided, a latents
	tensor will ge generated by sampling using the supplied random <code>generator</code>.`,name:"latents"},{anchor:"diffusers.StableCascadeDecoderPipeline.__call__.output_type",description:`<strong>output_type</strong> (<code>str</code>, <em>optional</em>, defaults to <code>"pil"</code>) —
	The output format of the generate image. Choose between: <code>"pil"</code> (<code>PIL.Image.Image</code>), <code>"np"</code>
	(<code>np.array</code>) or <code>"pt"</code> (<code>torch.Tensor</code>).`,name:"output_type"},{anchor:"diffusers.StableCascadeDecoderPipeline.__call__.return_dict",description:`<strong>return_dict</strong> (<code>bool</code>, <em>optional</em>, defaults to <code>True</code>) —
	Whether or not to return a <a href="/docs/diffusers/pr_9715/en/api/pipelines/latent_diffusion#diffusers.ImagePipelineOutput">ImagePipelineOutput</a> instead of a plain tuple.`,name:"return_dict"},{anchor:"diffusers.StableCascadeDecoderPipeline.__call__.callback_on_step_end",description:`<strong>callback_on_step_end</strong> (<code>Callable</code>, <em>optional</em>) —
	A function that calls at the end of each denoising steps during the inference. The function is called
	with the following arguments: <code>callback_on_step_end(self: DiffusionPipeline, step: int, timestep: int, callback_kwargs: Dict)</code>. <code>callback_kwargs</code> will include a list of all tensors as specified by
	<code>callback_on_step_end_tensor_inputs</code>.`,name:"callback_on_step_end"},{anchor:"diffusers.StableCascadeDecoderPipeline.__call__.callback_on_step_end_tensor_inputs",description:`<strong>callback_on_step_end_tensor_inputs</strong> (<code>List</code>, <em>optional</em>) —
	The list of tensor inputs for the <code>callback_on_step_end</code> function. The tensors specified in the list
	will be passed as <code>callback_kwargs</code> argument. You will only be able to include variables listed in the
	<code>._callback_tensor_inputs</code> attribute of your pipeline class.`,name:"callback_on_step_end_tensor_inputs"}],source:"https://github.com/huggingface/diffusers/blob/vr_9715/src/diffusers/pipelines/stable_cascade/pipeline_stable_cascade.py#L294",returnDescription:`<script context="module">export const metadata = 'undefined';<\/script>


	<p><a
	href="/docs/diffusers/pr_9715/en/api/pipelines/latent_diffusion#diffusers.ImagePipelineOutput"
	>ImagePipelineOutput</a> or <code>tuple</code> <a
	href="/docs/diffusers/pr_9715/en/api/pipelines/latent_diffusion#diffusers.ImagePipelineOutput"
	>ImagePipelineOutput</a> if <code>return_dict</code> is True,
	otherwise a <code>tuple</code>. When returning a tuple, the first element is a list with the generated image
	embeddings.</p>
	`}}),D=new Ot({props:{anchor:"diffusers.StableCascadeDecoderPipeline.__call__.example",$$slots:{default:[Za]},$$scope:{ctx:I}}}),je=new ja({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/pipelines/stable_cascade.md"}}),{c(){d=l("meta"),v=o(),y=l("p"),p=o(),m(C.$$.fragment),i=o(),w=l("p"),w.innerHTML=Le,M=o(),P=l("p"),P.textContent=Kt,ze=o(),L=l("p"),L.innerHTML=ea,qe=o(),m(F.$$.fragment),Ae=o(),z=l("p"),z.textContent=ta,Oe=o(),q=l("p"),q.textContent=aa,Ke=o(),A=l("p"),A.innerHTML=na,et=o(),O=l("p"),O.innerHTML=oa,tt=o(),m(N.$$.fragment),at=o(),m(K.$$.fragment),nt=o(),m(ee.$$.fragment),ot=o(),m(te.$$.fragment),st=o(),m(ae.$$.fragment),it=o(),m(ne.$$.fragment),lt=o(),oe=l("p"),oe.innerHTML=sa,rt=o(),m(se.$$.fragment),dt=o(),m(ie.$$.fragment),ct=o(),m(le.$$.fragment),pt=o(),re=l("p"),re.textContent=ia,mt=o(),de=l("ul"),de.innerHTML=la,ut=o(),ce=l("p"),ce.textContent=ra,gt=o(),m(pe.$$.fragment),ft=o(),me=l("p"),me.innerHTML=da,_t=o(),m(ue.$$.fragment),ht=o(),m(ge.$$.fragment),bt=o(),fe=l("ul"),fe.innerHTML=ca,wt=o(),m(_e.$$.fragment),yt=o(),T=l("div"),m(he.$$.fragment),It=o(),Ie=l("p"),Ie.textContent=pa,Zt=o(),Ze=l("p"),Ze.innerHTML=ma,kt=o(),Z=l("div"),m(be.$$.fragment),Wt=o(),ke=l("p"),ke.textContent=ua,Gt=o(),m(Y.$$.fragment),Bt=o(),R=l("div"),m(we.$$.fragment),Vt=o(),We=l("p"),We.innerHTML=ga,Nt=o(),H=l("div"),m(ye.$$.fragment),Yt=o(),Ge=l("p"),Ge.innerHTML=fa,Ct=o(),m(Ce.$$.fragment),Mt=o(),x=l("div"),m(Me.$$.fragment),Rt=o(),Be=l("p"),Be.textContent=_a,Ht=o(),Ve=l("p"),Ve.innerHTML=ha,Et=o(),k=l("div"),m(Te.$$.fragment),Dt=o(),Ne=l("p"),Ne.textContent=ba,Qt=o(),m(E.$$.fragment),Tt=o(),m(ve.$$.fragment),vt=o(),G=l("div"),m(Je.$$.fragment),Xt=o(),Ye=l("p"),Ye.textContent=wa,Jt=o(),m(Ue.$$.fragment),Ut=o(),j=l("div"),m(Pe.$$.fragment),Lt=o(),Re=l("p"),Re.textContent=ya,Ft=o(),He=l("p"),He.innerHTML=Ca,zt=o(),W=l("div"),m(xe.$$.fragment),qt=o(),Ee=l("p"),Ee.textContent=Ma,At=o(),m(D.$$.fragment),Pt=o(),m(je.$$.fragment),xt=o(),Fe=l("p"),this.h()},l(e){const t=Pa("svelte-u9bgzb",document.head);d=r(t,"META",{name:!0,content:!0}),t.forEach(a),v=s(e),y=r(e,"P",{}),S(y).forEach(a),p=s(e),u(C.$$.fragment,e),i=s(e),w=r(e,"P",{"data-svelte-h":!0}),b(w)!=="svelte-58yed7"&&(w.innerHTML=Le),M=s(e),P=r(e,"P",{"data-svelte-h":!0}),b(P)!=="svelte-pdgmnb"&&(P.textContent=Kt),ze=s(e),L=r(e,"P",{"data-svelte-h":!0}),b(L)!=="svelte-1rol617"&&(L.innerHTML=ea),qe=s(e),u(F.$$.fragment,e),Ae=s(e),z=r(e,"P",{"data-svelte-h":!0}),b(z)!=="svelte-13mtumf"&&(z.textContent=ta),Oe=s(e),q=r(e,"P",{"data-svelte-h":!0}),b(q)!=="svelte-1lpwfdo"&&(q.textContent=aa),Ke=s(e),A=r(e,"P",{"data-svelte-h":!0}),b(A)!=="svelte-nx9r15"&&(A.innerHTML=na),et=s(e),O=r(e,"P",{"data-svelte-h":!0}),b(O)!=="svelte-1r2fmf1"&&(O.innerHTML=oa),tt=s(e),u(N.$$.fragment,e),at=s(e),u(K.$$.fragment,e),nt=s(e),u(ee.$$.fragment,e),ot=s(e),u(te.$$.fragment,e),st=s(e),u(ae.$$.fragment,e),it=s(e),u(ne.$$.fragment,e),lt=s(e),oe=r(e,"P",{"data-svelte-h":!0}),b(oe)!=="svelte-vq9k87"&&(oe.innerHTML=sa),rt=s(e),u(se.$$.fragment,e),dt=s(e),u(ie.$$.fragment,e),ct=s(e),u(le.$$.fragment,e),pt=s(e),re=r(e,"P",{"data-svelte-h":!0}),b(re)!=="svelte-marzm0"&&(re.textContent=ia),mt=s(e),de=r(e,"UL",{"data-svelte-h":!0}),b(de)!=="svelte-1io3utn"&&(de.innerHTML=la),ut=s(e),ce=r(e,"P",{"data-svelte-h":!0}),b(ce)!=="svelte-usmk6k"&&(ce.textContent=ra),gt=s(e),u(pe.$$.fragment,e),ft=s(e),me=r(e,"P",{"data-svelte-h":!0}),b(me)!=="svelte-md3bci"&&(me.innerHTML=da),_t=s(e),u(ue.$$.fragment,e),ht=s(e),u(ge.$$.fragment,e),bt=s(e),fe=r(e,"UL",{"data-svelte-h":!0}),b(fe)!=="svelte-1lgsa2f"&&(fe.innerHTML=ca),wt=s(e),u(_e.$$.fragment,e),yt=s(e),T=r(e,"DIV",{class:!0});var J=S(T);u(he.$$.fragment,J),It=s(J),Ie=r(J,"P",{"data-svelte-h":!0}),b(Ie)!=="svelte-zuq8la"&&(Ie.textContent=pa),Zt=s(J),Ze=r(J,"P",{"data-svelte-h":!0}),b(Ze)!=="svelte-wbg2it"&&(Ze.innerHTML=ma),kt=s(J),Z=r(J,"DIV",{class:!0});var B=S(Z);u(be.$$.fragment,B),Wt=s(B),ke=r(B,"P",{"data-svelte-h":!0}),b(ke)!=="svelte-v78lg8"&&(ke.textContent=ua),Gt=s(B),u(Y.$$.fragment,B),B.forEach(a),Bt=s(J),R=r(J,"DIV",{class:!0});var Se=S(R);u(we.$$.fragment,Se),Vt=s(Se),We=r(Se,"P",{"data-svelte-h":!0}),b(We)!=="svelte-d7vywi"&&(We.innerHTML=ga),Se.forEach(a),Nt=s(J),H=r(J,"DIV",{class:!0});var $e=S(H);u(ye.$$.fragment,$e),Yt=s($e),Ge=r($e,"P",{"data-svelte-h":!0}),b(Ge)!=="svelte-a2a0wt"&&(Ge.innerHTML=fa),$e.forEach(a),J.forEach(a),Ct=s(e),u(Ce.$$.fragment,e),Mt=s(e),x=r(e,"DIV",{class:!0});var Q=S(x);u(Me.$$.fragment,Q),Rt=s(Q),Be=r(Q,"P",{"data-svelte-h":!0}),b(Be)!=="svelte-1k7c4ws"&&(Be.textContent=_a),Ht=s(Q),Ve=r(Q,"P",{"data-svelte-h":!0}),b(Ve)!=="svelte-wbg2it"&&(Ve.innerHTML=ha),Et=s(Q),k=r(Q,"DIV",{class:!0});var De=S(k);u(Te.$$.fragment,De),Dt=s(De),Ne=r(De,"P",{"data-svelte-h":!0}),b(Ne)!=="svelte-v78lg8"&&(Ne.textContent=ba),Qt=s(De),u(E.$$.fragment,De),De.forEach(a),Q.forEach(a),Tt=s(e),u(ve.$$.fragment,e),vt=s(e),G=r(e,"DIV",{class:!0});var St=S(G);u(Je.$$.fragment,St),Xt=s(St),Ye=r(St,"P",{"data-svelte-h":!0}),b(Ye)!=="svelte-cw9h8a"&&(Ye.textContent=wa),St.forEach(a),Jt=s(e),u(Ue.$$.fragment,e),Ut=s(e),j=r(e,"DIV",{class:!0});var X=S(j);u(Pe.$$.fragment,X),Lt=s(X),Re=r(X,"P",{"data-svelte-h":!0}),b(Re)!=="svelte-1bqijj8"&&(Re.textContent=ya),Ft=s(X),He=r(X,"P",{"data-svelte-h":!0}),b(He)!=="svelte-wbg2it"&&(He.innerHTML=Ca),zt=s(X),W=r(X,"DIV",{class:!0});var Qe=S(W);u(xe.$$.fragment,Qe),qt=s(Qe),Ee=r(Qe,"P",{"data-svelte-h":!0}),b(Ee)!=="svelte-v78lg8"&&(Ee.textContent=Ma),At=s(Qe),u(D.$$.fragment,Qe),Qe.forEach(a),X.forEach(a),Pt=s(e),u(je.$$.fragment,e),xt=s(e),Fe=r(e,"P",{}),S(Fe).forEach(a),this.h()},h(){$(d,"name","hf:doc:metadata"),$(d,"content",Wa),$(Z,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(R,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(H,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(T,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(k,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(x,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(G,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(W,"class","docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"),$(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(e,t){c(document.head,d),n(e,v,t),n(e,y,t),n(e,p,t),g(C,e,t),n(e,i,t),n(e,w,t),n(e,M,t),n(e,P,t),n(e,ze,t),n(e,L,t),n(e,qe,t),g(F,e,t),n(e,Ae,t),n(e,z,t),n(e,Oe,t),n(e,q,t),n(e,Ke,t),n(e,A,t),n(e,et,t),n(e,O,t),n(e,tt,t),g(N,e,t),n(e,at,t),g(K,e,t),n(e,nt,t),g(ee,e,t),n(e,ot,t),g(te,e,t),n(e,st,t),g(ae,e,t),n(e,it,t),g(ne,e,t),n(e,lt,t),n(e,oe,t),n(e,rt,t),g(se,e,t),n(e,dt,t),g(ie,e,t),n(e,ct,t),g(le,e,t),n(e,pt,t),n(e,re,t),n(e,mt,t),n(e,de,t),n(e,ut,t),n(e,ce,t),n(e,gt,t),g(pe,e,t),n(e,ft,t),n(e,me,t),n(e,_t,t),g(ue,e,t),n(e,ht,t),g(ge,e,t),n(e,bt,t),n(e,fe,t),n(e,wt,t),g(_e,e,t),n(e,yt,t),n(e,T,t),g(he,T,null),c(T,It),c(T,Ie),c(T,Zt),c(T,Ze),c(T,kt),c(T,Z),g(be,Z,null),c(Z,Wt),c(Z,ke),c(Z,Gt),g(Y,Z,null),c(T,Bt),c(T,R),g(we,R,null),c(R,Vt),c(R,We),c(T,Nt),c(T,H),g(ye,H,null),c(H,Yt),c(H,Ge),n(e,Ct,t),g(Ce,e,t),n(e,Mt,t),n(e,x,t),g(Me,x,null),c(x,Rt),c(x,Be),c(x,Ht),c(x,Ve),c(x,Et),c(x,k),g(Te,k,null),c(k,Dt),c(k,Ne),c(k,Qt),g(E,k,null),n(e,Tt,t),g(ve,e,t),n(e,vt,t),n(e,G,t),g(Je,G,null),c(G,Xt),c(G,Ye),n(e,Jt,t),g(Ue,e,t),n(e,Ut,t),n(e,j,t),g(Pe,j,null),c(j,Lt),c(j,Re),c(j,Ft),c(j,He),c(j,zt),c(j,W),g(xe,W,null),c(W,qt),c(W,Ee),c(W,At),g(D,W,null),n(e,Pt,t),g(je,e,t),n(e,xt,t),n(e,Fe,t),jt=!0},p(e,[t]){const J={};t&2&&(J.$$scope={dirty:t,ctx:e}),N.$set(J);const B={};t&2&&(B.$$scope={dirty:t,ctx:e}),Y.$set(B);const Se={};t&2&&(Se.$$scope={dirty:t,ctx:e}),E.$set(Se);const $e={};t&2&&($e.$$scope={dirty:t,ctx:e}),D.$set($e)},i(e){jt\|\|(f(C.$$.fragment,e),f(F.$$.fragment,e),f(N.$$.fragment,e),f(K.$$.fragment,e),f(ee.$$.fragment,e),f(te.$$.fragment,e),f(ae.$$.fragment,e),f(ne.$$.fragment,e),f(se.$$.fragment,e),f(ie.$$.fragment,e),f(le.$$.fragment,e),f(pe.$$.fragment,e),f(ue.$$.fragment,e),f(ge.$$.fragment,e),f(_e.$$.fragment,e),f(he.$$.fragment,e),f(be.$$.fragment,e),f(Y.$$.fragment,e),f(we.$$.fragment,e),f(ye.$$.fragment,e),f(Ce.$$.fragment,e),f(Me.$$.fragment,e),f(Te.$$.fragment,e),f(E.$$.fragment,e),f(ve.$$.fragment,e),f(Je.$$.fragment,e),f(Ue.$$.fragment,e),f(Pe.$$.fragment,e),f(xe.$$.fragment,e),f(D.$$.fragment,e),f(je.$$.fragment,e),jt=!0)},o(e){_(C.$$.fragment,e),_(F.$$.fragment,e),_(N.$$.fragment,e),_(K.$$.fragment,e),_(ee.$$.fragment,e),_(te.$$.fragment,e),_(ae.$$.fragment,e),_(ne.$$.fragment,e),_(se.$$.fragment,e),_(ie.$$.fragment,e),_(le.$$.fragment,e),_(pe.$$.fragment,e),_(ue.$$.fragment,e),_(ge.$$.fragment,e),_(_e.$$.fragment,e),_(he.$$.fragment,e),_(be.$$.fragment,e),_(Y.$$.fragment,e),_(we.$$.fragment,e),_(ye.$$.fragment,e),_(Ce.$$.fragment,e),_(Me.$$.fragment,e),_(Te.$$.fragment,e),_(E.$$.fragment,e),_(ve.$$.fragment,e),_(Je.$$.fragment,e),_(Ue.$$.fragment,e),_(Pe.$$.fragment,e),_(xe.$$.fragment,e),_(D.$$.fragment,e),_(je.$$.fragment,e),jt=!1},d(e){e&&(a(v),a(y),a(p),a(i),a(w),a(M),a(P),a(ze),a(L),a(qe),a(Ae),a(z),a(Oe),a(q),a(Ke),a(A),a(et),a(O),a(tt),a(at),a(nt),a(ot),a(st),a(it),a(lt),a(oe),a(rt),a(dt),a(ct),a(pt),a(re),a(mt),a(de),a(ut),a(ce),a(gt),a(ft),a(me),a(_t),a(ht),a(bt),a(fe),a(wt),a(yt),a(T),a(Ct),a(Mt),a(x),a(Tt),a(vt),a(G),a(Jt),a(Ut),a(j),a(Pt),a(xt),a(Fe)),a(d),h(C,e),h(F,e),h(N,e),h(K,e),h(ee,e),h(te,e),h(ae,e),h(ne,e),h(se,e),h(ie,e),h(le,e),h(pe,e),h(ue,e),h(ge,e),h(_e,e),h(he),h(be),h(Y),h(we),h(ye),h(Ce,e),h(Me),h(Te),h(E),h(ve,e),h(Je),h(Ue,e),h(Pe),h(xe),h(D),h(je,e)}}}const Wa='{"title":"Stable Cascade","local":"stable-cascade","sections":[{"title":"Model Overview","local":"model-overview","sections":[],"depth":2},{"title":"Usage example","local":"usage-example","sections":[],"depth":2},{"title":"Using the Lite Versions of the Stage B and Stage C models","local":"using-the-lite-versions-of-the-stage-b-and-stage-c-models","sections":[],"depth":2},{"title":"Loading original checkpoints with from_single_file","local":"loading-original-checkpoints-with-fromsinglefile","sections":[],"depth":2},{"title":"Uses","local":"uses","sections":[{"title":"Direct Use","local":"direct-use","sections":[],"depth":3},{"title":"Out-of-Scope Use","local":"out-of-scope-use","sections":[],"depth":3}],"depth":2},{"title":"Limitations and Bias","local":"limitations-and-bias","sections":[{"title":"Limitations","local":"limitations","sections":[],"depth":3}],"depth":2},{"title":"StableCascadeCombinedPipeline","local":"diffusers.StableCascadeCombinedPipeline","sections":[],"depth":2},{"title":"StableCascadePriorPipeline","local":"diffusers.StableCascadePriorPipeline","sections":[],"depth":2},{"title":"StableCascadePriorPipelineOutput","local":"diffusers.pipelines.stable_cascade.pipeline_stable_cascade_prior.StableCascadePriorPipelineOutput","sections":[],"depth":2},{"title":"StableCascadeDecoderPipeline","local":"diffusers.StableCascadeDecoderPipeline","sections":[],"depth":2}],"depth":1}';function Ga(I){return va(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Da extends Ja{constructor(d){super(),Ua(this,d,Ga,ka,Ta,{})}}export{Da as component};

Xet Storage Details

Size:: 78.9 kB
Xet hash:: c14194b091aa089c8d6ccccf0c0a98e1185e6d52564acc0f7bf61fbf39b7b359

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.