diffusers/main/en/_app/immutable/nodes/111.8238c031.js

import{s as Me,o as be,n as ye}from"../chunks/scheduler.8c3d61f6.js";import{S as we,i as ge,g as m,s as a,r as u,A as Je,h as r,f as l,c as i,j as de,u as c,x as g,k as he,y as Ze,a as s,v as d,d as h,t as M,w as b}from"../chunks/index.da70eac4.js";import{T as Ue}from"../chunks/Tip.1d9b8c37.js";import{C as ie}from"../chunks/CodeBlock.00a903b3.js";import{H as S,E as Te}from"../chunks/EditOnGithub.1e64e623.js";function We(F){let n,Z='Make sure to check out the Stable Diffusion <a href="overview#tips">Tips</a> section to learn how to explore the tradeoff between scheduler speed and quality, and how to reuse pipeline components efficiently!',y,o,w='If you’re interested in using one of the official checkpoints for a task, explore the <a href="https://huggingface.co/CompVis" rel="nofollow">CompVis</a>, <a href="https://huggingface.co/runwayml" rel="nofollow">Runway</a>, and <a href="https://huggingface.co/stabilityai" rel="nofollow">Stability AI</a> Hub organizations!';return{c(){n=m("p"),n.innerHTML=Z,y=a(),o=m("p"),o.innerHTML=w},l(p){n=r(p,"P",{"data-svelte-h":!0}),g(n)!=="svelte-1j961ct"&&(n.innerHTML=Z),y=i(p),o=r(p,"P",{"data-svelte-h":!0}),g(o)!=="svelte-z4pn9c"&&(o.innerHTML=w)},m(p,f){s(p,n,f),s(p,y,f),s(p,o,f)},p:ye,d(p){p&&(l(n),l(y),l(o))}}}function je(F){let n,Z,y,o,w,p,f,ne='Stable Diffusion 2 is a text-to-image <em>latent diffusion</em> model built upon the work of the original <a href="https://stability.ai/blog/stable-diffusion-public-release" rel="nofollow">Stable Diffusion</a>, and it was led by Robin Rombach and Katherine Crowson from <a href="https://stability.ai/" rel="nofollow">Stability AI</a> and <a href="https://laion.ai/" rel="nofollow">LAION</a>.',Q,U,pe=`<em>The Stable Diffusion 2.0 release includes robust text-to-image models trained using a brand new text encoder (OpenCLIP), developed by LAION with support from Stability AI, which greatly improves the quality of the generated images compared to earlier V1 releases. The text-to-image models in this release can generate images with default resolutions of both 512x512 pixels and 768x768 pixels.
These models are trained on an aesthetic subset of the <a href="https://laion.ai/blog/laion-5b/" rel="nofollow">LAION-5B dataset</a> created by the DeepFloyd team at Stability AI, which is then further filtered to remove adult content using <a href="https://openreview.net/forum?id=M3Y74vmsMcY" rel="nofollow">LAION’s NSFW filter</a>.</em>`,x,T,oe='For more details about how Stable Diffusion 2 works and how it differs from the original Stable Diffusion, please refer to the official <a href="https://stability.ai/blog/stable-diffusion-v2-release" rel="nofollow">announcement post</a>.',z,W,me='The architecture of Stable Diffusion 2 is more or less identical to the original <a href="./text2img">Stable Diffusion model</a> so check out it’s API documentation for how to use Stable Diffusion 2. We recommend using the <a href="/docs/diffusers/main/en/api/schedulers/multistep_dpm_solver#diffusers.DPMSolverMultistepScheduler">DPMSolverMultistepScheduler</a> as it gives a reasonable speed/quality trade-off and can be run with as little as 20 steps.',Y,j,re="Stable Diffusion 2 is available for tasks like text-to-image, inpainting, super-resolution, and depth-to-image:",E,G,fe='<thead><tr><th>Task</th> <th>Repository</th></tr></thead> <tbody><tr><td>text-to-image (512x512)</td> <td><a href="https://huggingface.co/stabilityai/stable-diffusion-2-base" rel="nofollow">stabilityai/stable-diffusion-2-base</a></td></tr> <tr><td>text-to-image (768x768)</td> <td><a href="https://huggingface.co/stabilityai/stable-diffusion-2" rel="nofollow">stabilityai/stable-diffusion-2</a></td></tr> <tr><td>inpainting</td> <td><a href="https://huggingface.co/stabilityai/stable-diffusion-2-inpainting" rel="nofollow">stabilityai/stable-diffusion-2-inpainting</a></td></tr> <tr><td>super-resolution</td> <td><a href="https://huggingface.co/stabilityai/stable-diffusion-x4-upscaler" rel="nofollow">stable-diffusion-x4-upscaler</a></td></tr> <tr><td>depth-to-image</td> <td><a href="https://huggingface.co/stabilityai/stable-diffusion-2-depth" rel="nofollow">stabilityai/stable-diffusion-2-depth</a></td></tr></tbody>',H,B,ue="Here are some examples for how to use Stable Diffusion 2 for each task:",D,J,L,X,q,k,A,I,P,_,K,R,O,V,ee,$,te,v,le,C,se,N,ae;return w=new S({props:{title:"Stable Diffusion 2",local:"stable-diffusion-2",headingTag:"h1"}}),J=new Ue({props:{$$slots:{default:[We]},$$scope:{ctx:F}}}),X=new S({props:{title:"Text-to-image",local:"text-to-image",headingTag:"h2"}}),k=new ie({props:{code:"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",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline, DPMSolverMultistepScheduler
<span class="hljs-keyword">import</span> torch

repo_id = <span class="hljs-string">&quot;stabilityai/stable-diffusion-2-base&quot;</span>
pipe = DiffusionPipeline.from_pretrained(repo_id, torch_dtype=torch.float16, variant=<span class="hljs-string">&quot;fp16&quot;</span>)

pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)

prompt = <span class="hljs-string">&quot;High quality photo of an astronaut riding a horse in space&quot;</span>
image = pipe(prompt, num_inference_steps=<span class="hljs-number">25</span>).images[<span class="hljs-number">0</span>]
image`,wrap:!1}}),I=new S({props:{title:"Inpainting",local:"inpainting",headingTag:"h2"}}),_=new ie({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> DiffusionPipeline, DPMSolverMultistepScheduler
<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image, make_image_grid

img_url = <span class="hljs-string">&quot;https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo.png&quot;</span>
mask_url = <span class="hljs-string">&quot;https://raw.githubusercontent.com/CompVis/latent-diffusion/main/data/inpainting_examples/overture-creations-5sI6fQgYIuo_mask.png&quot;</span>

init_image = load_image(img_url).resize((<span class="hljs-number">512</span>, <span class="hljs-number">512</span>))
mask_image = load_image(mask_url).resize((<span class="hljs-number">512</span>, <span class="hljs-number">512</span>))

repo_id = <span class="hljs-string">&quot;stabilityai/stable-diffusion-2-inpainting&quot;</span>
pipe = DiffusionPipeline.from_pretrained(repo_id, torch_dtype=torch.float16, variant=<span class="hljs-string">&quot;fp16&quot;</span>)

pipe.scheduler = DPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
pipe = pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)

prompt = <span class="hljs-string">&quot;Face of a yellow cat, high resolution, sitting on a park bench&quot;</span>
image = pipe(prompt=prompt, image=init_image, mask_image=mask_image, num_inference_steps=<span class="hljs-number">25</span>).images[<span class="hljs-number">0</span>]
make_image_grid([init_image, mask_image, image], rows=<span class="hljs-number">1</span>, cols=<span class="hljs-number">3</span>)`,wrap:!1}}),R=new S({props:{title:"Super-resolution",local:"super-resolution",headingTag:"h2"}}),V=new ie({props:{code:"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",highlighted:`<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> StableDiffusionUpscalePipeline
<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image, make_image_grid
<span class="hljs-keyword">import</span> torch

<span class="hljs-comment"># load model and scheduler</span>
model_id = <span class="hljs-string">&quot;stabilityai/stable-diffusion-x4-upscaler&quot;</span>
pipeline = StableDiffusionUpscalePipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipeline = pipeline.to(<span class="hljs-string">&quot;cuda&quot;</span>)

<span class="hljs-comment"># let&#x27;s download an  image</span>
url = <span class="hljs-string">&quot;https://huggingface.co/datasets/hf-internal-testing/diffusers-images/resolve/main/sd2-upscale/low_res_cat.png&quot;</span>
low_res_img = load_image(url)
low_res_img = low_res_img.resize((<span class="hljs-number">128</span>, <span class="hljs-number">128</span>))
prompt = <span class="hljs-string">&quot;a white cat&quot;</span>
upscaled_image = pipeline(prompt=prompt, image=low_res_img).images[<span class="hljs-number">0</span>]
make_image_grid([low_res_img.resize((<span class="hljs-number">512</span>, <span class="hljs-number">512</span>)), upscaled_image.resize((<span class="hljs-number">512</span>, <span class="hljs-number">512</span>))], rows=<span class="hljs-number">1</span>, cols=<span class="hljs-number">2</span>)`,wrap:!1}}),$=new S({props:{title:"Depth-to-image",local:"depth-to-image",headingTag:"h2"}}),v=new ie({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> StableDiffusionDepth2ImgPipeline
<span class="hljs-keyword">from</span> diffusers.utils <span class="hljs-keyword">import</span> load_image, make_image_grid

pipe = StableDiffusionDepth2ImgPipeline.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-2-depth&quot;</span>,
    torch_dtype=torch.float16,
).to(<span class="hljs-string">&quot;cuda&quot;</span>)


url = <span class="hljs-string">&quot;http://images.cocodataset.org/val2017/000000039769.jpg&quot;</span>
init_image = load_image(url)
prompt = <span class="hljs-string">&quot;two tigers&quot;</span>
negative_prompt = <span class="hljs-string">&quot;bad, deformed, ugly, bad anotomy&quot;</span>
image = pipe(prompt=prompt, image=init_image, negative_prompt=negative_prompt, strength=<span class="hljs-number">0.7</span>).images[<span class="hljs-number">0</span>]
make_image_grid([init_image, image], rows=<span class="hljs-number">1</span>, cols=<span class="hljs-number">2</span>)`,wrap:!1}}),C=new Te({props:{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/api/pipelines/stable_diffusion/stable_diffusion_2.md"}}),{c(){n=m("meta"),Z=a(),y=m("p"),o=a(),u(w.$$.fragment),p=a(),f=m("p"),f.innerHTML=ne,Q=a(),U=m("p"),U.innerHTML=pe,x=a(),T=m("p"),T.innerHTML=oe,z=a(),W=m("p"),W.innerHTML=me,Y=a(),j=m("p"),j.textContent=re,E=a(),G=m("table"),G.innerHTML=fe,H=a(),B=m("p"),B.textContent=ue,D=a(),u(J.$$.fragment),L=a(),u(X.$$.fragment),q=a(),u(k.$$.fragment),A=a(),u(I.$$.fragment),P=a(),u(_.$$.fragment),K=a(),u(R.$$.fragment),O=a(),u(V.$$.fragment),ee=a(),u($.$$.fragment),te=a(),u(v.$$.fragment),le=a(),u(C.$$.fragment),se=a(),N=m("p"),this.h()},l(e){const t=Je("svelte-u9bgzb",document.head);n=r(t,"META",{name:!0,content:!0}),t.forEach(l),Z=i(e),y=r(e,"P",{}),de(y).forEach(l),o=i(e),c(w.$$.fragment,e),p=i(e),f=r(e,"P",{"data-svelte-h":!0}),g(f)!=="svelte-b1fked"&&(f.innerHTML=ne),Q=i(e),U=r(e,"P",{"data-svelte-h":!0}),g(U)!=="svelte-14ofdwv"&&(U.innerHTML=pe),x=i(e),T=r(e,"P",{"data-svelte-h":!0}),g(T)!=="svelte-m1ataf"&&(T.innerHTML=oe),z=i(e),W=r(e,"P",{"data-svelte-h":!0}),g(W)!=="svelte-1fyxemw"&&(W.innerHTML=me),Y=i(e),j=r(e,"P",{"data-svelte-h":!0}),g(j)!=="svelte-lmvyuh"&&(j.textContent=re),E=i(e),G=r(e,"TABLE",{"data-svelte-h":!0}),g(G)!=="svelte-14nbvv4"&&(G.innerHTML=fe),H=i(e),B=r(e,"P",{"data-svelte-h":!0}),g(B)!=="svelte-1y4j0tz"&&(B.textContent=ue),D=i(e),c(J.$$.fragment,e),L=i(e),c(X.$$.fragment,e),q=i(e),c(k.$$.fragment,e),A=i(e),c(I.$$.fragment,e),P=i(e),c(_.$$.fragment,e),K=i(e),c(R.$$.fragment,e),O=i(e),c(V.$$.fragment,e),ee=i(e),c($.$$.fragment,e),te=i(e),c(v.$$.fragment,e),le=i(e),c(C.$$.fragment,e),se=i(e),N=r(e,"P",{}),de(N).forEach(l),this.h()},h(){he(n,"name","hf:doc:metadata"),he(n,"content",Ge)},m(e,t){Ze(document.head,n),s(e,Z,t),s(e,y,t),s(e,o,t),d(w,e,t),s(e,p,t),s(e,f,t),s(e,Q,t),s(e,U,t),s(e,x,t),s(e,T,t),s(e,z,t),s(e,W,t),s(e,Y,t),s(e,j,t),s(e,E,t),s(e,G,t),s(e,H,t),s(e,B,t),s(e,D,t),d(J,e,t),s(e,L,t),d(X,e,t),s(e,q,t),d(k,e,t),s(e,A,t),d(I,e,t),s(e,P,t),d(_,e,t),s(e,K,t),d(R,e,t),s(e,O,t),d(V,e,t),s(e,ee,t),d($,e,t),s(e,te,t),d(v,e,t),s(e,le,t),d(C,e,t),s(e,se,t),s(e,N,t),ae=!0},p(e,[t]){const ce={};t&2&&(ce.$$scope={dirty:t,ctx:e}),J.$set(ce)},i(e){ae||(h(w.$$.fragment,e),h(J.$$.fragment,e),h(X.$$.fragment,e),h(k.$$.fragment,e),h(I.$$.fragment,e),h(_.$$.fragment,e),h(R.$$.fragment,e),h(V.$$.fragment,e),h($.$$.fragment,e),h(v.$$.fragment,e),h(C.$$.fragment,e),ae=!0)},o(e){M(w.$$.fragment,e),M(J.$$.fragment,e),M(X.$$.fragment,e),M(k.$$.fragment,e),M(I.$$.fragment,e),M(_.$$.fragment,e),M(R.$$.fragment,e),M(V.$$.fragment,e),M($.$$.fragment,e),M(v.$$.fragment,e),M(C.$$.fragment,e),ae=!1},d(e){e&&(l(Z),l(y),l(o),l(p),l(f),l(Q),l(U),l(x),l(T),l(z),l(W),l(Y),l(j),l(E),l(G),l(H),l(B),l(D),l(L),l(q),l(A),l(P),l(K),l(O),l(ee),l(te),l(le),l(se),l(N)),l(n),b(w,e),b(J,e),b(X,e),b(k,e),b(I,e),b(_,e),b(R,e),b(V,e),b($,e),b(v,e),b(C,e)}}}const Ge='{"title":"Stable Diffusion 2","local":"stable-diffusion-2","sections":[{"title":"Text-to-image","local":"text-to-image","sections":[],"depth":2},{"title":"Inpainting","local":"inpainting","sections":[],"depth":2},{"title":"Super-resolution","local":"super-resolution","sections":[],"depth":2},{"title":"Depth-to-image","local":"depth-to-image","sections":[],"depth":2}],"depth":1}';function Be(F){return be(()=>{new URLSearchParams(window.location.search).get("fw")}),[]}class Ve extends we{constructor(n){super(),ge(this,n,Be,je,Me,{})}}export{Ve as component};