diffusers/pr_14407/en/_app/immutable/nodes/348.c3wId5VD.js

import"../chunks/DsnmJJEf.js";import{i as b,h as T,C as j,H as h,a as s,E as G,s as B}from"../chunks/CmJXCtRL.js";import{p as u,o as Z,s as l,f as I,a as r,b as g,d,n as f}from"../chunks/DK803DsY.js";const W='{"title":"Batch inference","local":"batch-inference","sections":[{"title":"Deterministic generation","local":"deterministic-generation","sections":[],"depth":2}],"depth":1}';var X=d('<meta name="hf:doc:metadata"/>'),C=d('<p></p> <!> <!> <p>Batch inference processes multiple prompts at a time to increase throughput. It is more efficient because processing multiple prompts at once maximizes GPU usage versus processing a single prompt and underutilizing the GPU.</p> <p>The downside is increased latency because you must wait for the entire batch to complete, and more GPU memory is required for large batches.</p> <p>For text-to-image, pass a list of prompts to the pipeline and for image-to-image, pass a list of images and prompts to the pipeline. The example below demonstrates batched text-to-image inference.</p> <!> <div class="flex justify-center"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/batch-inference.png"/></div> <p>To generate multiple variations of one prompt, use the <code>num_images_per_prompt</code> argument.</p> <!> <div class="flex justify-center"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/batch-inference-2.png"/></div> <p>Combine both approaches to generate different variations of different prompts.</p> <!> <div class="flex justify-center"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/batch-inference-3.png"/></div> <!> <p>Enable reproducible batch generation by passing a list of <a href="https://pytorch.org/docs/stable/generated/torch.Generator.html" rel="nofollow">Generator’s</a> to the pipeline and tie each <code>Generator</code> to a seed to reuse it.</p> <blockquote class="tip"><p>Refer to the <a href="./reusing_seeds">Reproducibility</a> docs to learn more about deterministic algorithms and the <code>Generator</code> object.</p></blockquote> <p>Use a list comprehension to iterate over the batch size specified in <code>range()</code> to create a unique <code>Generator</code> object for each image in the batch. Don’t multiply the <code>Generator</code> by the batch size because that only creates one <code>Generator</code> object that is used sequentially for each image in the batch.</p> <!> <p>Pass the <code>generator</code> to the pipeline.</p> <!> <p>You can use this to select an image associated with a seed and iteratively improve on it by crafting a more detailed prompt.</p> <!> <p></p>',1);function v(m,w){u(w,!1),Z(()=>{new URLSearchParams(window.location.search).get("fw")}),b();var a=C();T("1sdmsnt",y=>{var J=X();B(J,"content",W),r(y,J)});var e=l(I(a),2);j(e,{containerStyle:"float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"});var t=l(e,2);h(t,{title:"Batch inference",local:"batch-inference",headingTag:"h1"});var n=l(t,8);s(n,{code:"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",highlighted:`<span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">import</span> matplotlib.pyplot <span class="hljs-keyword">as</span> plt
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>,
    dtype=torch.float16,
    device_map=<span class="hljs-string">&quot;cuda&quot;</span>
)

prompts = [
    <span class="hljs-string">&quot;Cinematic shot of a cozy coffee shop interior, warm pastel light streaming through a window where a cat rests. Shallow depth of field, glowing cups in soft focus, dreamy lofi-inspired mood, nostalgic tones, framed like a quiet film scene.&quot;</span>,
    <span class="hljs-string">&quot;Polaroid-style photograph of a cozy coffee shop interior, bathed in warm pastel light. A cat sits on the windowsill near steaming mugs. Soft, slightly faded tones and dreamy blur evoke nostalgia, a lofi mood, and the intimate, imperfect charm of instant film.&quot;</span>,
    <span class="hljs-string">&quot;Soft watercolor illustration of a cozy coffee shop interior, pastel washes of color filling the space. A cat rests peacefully on the windowsill as warm light glows through. Gentle brushstrokes create a dreamy, lofi-inspired atmosphere with whimsical textures and nostalgic calm.&quot;</span>,
    <span class="hljs-string">&quot;Isometric pixel-art illustration of a cozy coffee shop interior in detailed 8-bit style. Warm pastel light fills the space as a cat rests on the windowsill. Blocky furniture and tiny mugs add charm, low-res retro graphics enhance the nostalgic, lofi-inspired game aesthetic.&quot;</span>
]

images = pipeline(
    prompt=prompts,
).images

fig, axes = plt.subplots(<span class="hljs-number">2</span>, <span class="hljs-number">2</span>, figsize=(<span class="hljs-number">12</span>, <span class="hljs-number">12</span>))
axes = axes.flatten()

<span class="hljs-keyword">for</span> i, image <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(images):
    axes[i].imshow(image)
    axes[i].set_title(<span class="hljs-string">f&quot;Image <span class="hljs-subst">{i+<span class="hljs-number">1</span>}</span>&quot;</span>)
    axes[i].axis(<span class="hljs-string">&#x27;off&#x27;</span>)

plt.tight_layout()
plt.show()`,lang:"py",wrap:!1});var i=l(n,6);s(i,{code:"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",highlighted:`<span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">import</span> matplotlib.pyplot <span class="hljs-keyword">as</span> plt
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline

pipeline = DiffusionPipeline.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>,
    dtype=torch.float16,
    device_map=<span class="hljs-string">&quot;cuda&quot;</span>
)

prompt=<span class="hljs-string">&quot;&quot;&quot;
Isometric pixel-art illustration of a cozy coffee shop interior in detailed 8-bit style. Warm pastel light fills the
space as a cat rests on the windowsill. Blocky furniture and tiny mugs add charm, low-res retro graphics enhance the
nostalgic, lofi-inspired game aesthetic.
&quot;&quot;&quot;</span>

images = pipeline(
    prompt=prompt,
    num_images_per_prompt=<span class="hljs-number">4</span>
).images

fig, axes = plt.subplots(<span class="hljs-number">2</span>, <span class="hljs-number">2</span>, figsize=(<span class="hljs-number">12</span>, <span class="hljs-number">12</span>))
axes = axes.flatten()

<span class="hljs-keyword">for</span> i, image <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(images):
    axes[i].imshow(image)
    axes[i].set_title(<span class="hljs-string">f&quot;Image <span class="hljs-subst">{i+<span class="hljs-number">1</span>}</span>&quot;</span>)
    axes[i].axis(<span class="hljs-string">&#x27;off&#x27;</span>)

plt.tight_layout()
plt.show()`,lang:"py",wrap:!1});var M=l(i,6);s(M,{code:"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",highlighted:`images = pipeline(
    prompt=prompts,
    num_images_per_prompt=<span class="hljs-number">2</span>,
).images

fig, axes = plt.subplots(<span class="hljs-number">2</span>, <span class="hljs-number">4</span>, figsize=(<span class="hljs-number">12</span>, <span class="hljs-number">12</span>))
axes = axes.flatten()

<span class="hljs-keyword">for</span> i, image <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(images):
    axes[i].imshow(image)
    axes[i].set_title(<span class="hljs-string">f&quot;Image <span class="hljs-subst">{i+<span class="hljs-number">1</span>}</span>&quot;</span>)
    axes[i].axis(<span class="hljs-string">&#x27;off&#x27;</span>)

plt.tight_layout()
plt.show()`,lang:"py",wrap:!1});var o=l(M,4);h(o,{title:"Deterministic generation",local:"deterministic-generation",headingTag:"h2"});var p=l(o,8);s(p,{code:"Z2VuZXJhdG9yJTIwJTNEJTIwJTVCdG9yY2guR2VuZXJhdG9yKGRldmljZSUzRCUyMmN1ZGElMjIpLm1hbnVhbF9zZWVkKDApJTVEJTIwKiUyMDM=",highlighted:'generator = [torch.Generator(device=<span class="hljs-string">&quot;cuda&quot;</span>).manual_seed(<span class="hljs-number">0</span>)] * <span class="hljs-number">3</span>',lang:"py",wrap:!1});var c=l(p,4);s(c,{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

pipeline = DiffusionPipeline.from_pretrained(
    <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>,
    dtype=torch.float16,
    device_map=<span class="hljs-string">&quot;cuda&quot;</span>
)

generator = [torch.Generator(device=<span class="hljs-string">&quot;cuda&quot;</span>).manual_seed(i) <span class="hljs-keyword">for</span> i <span class="hljs-keyword">in</span> <span class="hljs-built_in">range</span>(<span class="hljs-number">3</span>)]
prompts = [
    <span class="hljs-string">&quot;Cinematic shot of a cozy coffee shop interior, warm pastel light streaming through a window where a cat rests. Shallow depth of field, glowing cups in soft focus, dreamy lofi-inspired mood, nostalgic tones, framed like a quiet film scene.&quot;</span>,
    <span class="hljs-string">&quot;Polaroid-style photograph of a cozy coffee shop interior, bathed in warm pastel light. A cat sits on the windowsill near steaming mugs. Soft, slightly faded tones and dreamy blur evoke nostalgia, a lofi mood, and the intimate, imperfect charm of instant film.&quot;</span>,
    <span class="hljs-string">&quot;Soft watercolor illustration of a cozy coffee shop interior, pastel washes of color filling the space. A cat rests peacefully on the windowsill as warm light glows through. Gentle brushstrokes create a dreamy, lofi-inspired atmosphere with whimsical textures and nostalgic calm.&quot;</span>,
    <span class="hljs-string">&quot;Isometric pixel-art illustration of a cozy coffee shop interior in detailed 8-bit style. Warm pastel light fills the space as a cat rests on the windowsill. Blocky furniture and tiny mugs add charm, low-res retro graphics enhance the nostalgic, lofi-inspired game aesthetic.&quot;</span>
]

images = pipeline(
    prompt=prompts,
    generator=generator
).images

fig, axes = plt.subplots(<span class="hljs-number">2</span>, <span class="hljs-number">2</span>, figsize=(<span class="hljs-number">12</span>, <span class="hljs-number">12</span>))
axes = axes.flatten()

<span class="hljs-keyword">for</span> i, image <span class="hljs-keyword">in</span> <span class="hljs-built_in">enumerate</span>(images):
    axes[i].imshow(image)
    axes[i].set_title(<span class="hljs-string">f&quot;Image <span class="hljs-subst">{i+<span class="hljs-number">1</span>}</span>&quot;</span>)
    axes[i].axis(<span class="hljs-string">&#x27;off&#x27;</span>)

plt.tight_layout()
plt.show()`,lang:"py",wrap:!1});var U=l(c,4);G(U,{source:"https://github.com/huggingface/diffusers/blob/main/docs/source/en/using-diffusers/batched_inference.md"}),f(2),r(m,a),g()}export{v as component};