Buckets:

hf-doc-build
/

doc

Files
xet
hf-doc-build/doc / diffusers /main /ko /using-diffusers /callback.html
mishig
about 20 hours ago
download
raw
35.2 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Pipeline 콜백&quot;,&quot;local&quot;:&quot;pipeline-callbacks&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;조기 종료&quot;,&quot;local&quot;:&quot;early-stopping&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;중간 이미지 표시&quot;,&quot;local&quot;:&quot;display-intermediate-images&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;모듈형 파이프라인&quot;,&quot;local&quot;:&quot;modular-pipelines&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
		<link href="/docs/diffusers/main/en/_app/immutable/entry/start.vZc-dOUR.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/Bafuik5c.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/Bupkjr9f.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/entry/app.B6c3Ml05.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/CyvZ3FS5.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/l0QnnOED.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/DnVIJfC5.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/nodes/0.BQlx092V.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/CoSrdQax.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/nodes/379.D4s93XTH.js" rel="modulepreload">
		<link href="/docs/diffusers/main/en/_app/immutable/chunks/B4AMoTAu.js" rel="modulepreload">
		<!--apt59n--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Pipeline callbacks&quot;,&quot;local&quot;:&quot;pipeline-callbacks&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Early stopping&quot;,&quot;local&quot;:&quot;early-stopping&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Display intermediate images&quot;,&quot;local&quot;:&quot;display-intermediate-images&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Modular pipelines&quot;,&quot;local&quot;:&quot;modular-pipelines&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/><!---->
		<link href="/docs/diffusers/main/en/_app/immutable/assets/0.tn0RQdqM.css" rel="modulepreload"> <!--[--><!--[0--><!--[--><!--[0--><!--[--><p></p> <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: inline-end; margin-inline-start: 10px; display: inline-flex; position: relative; z-index: 10;"><div dir="ltr" class="inline-flex rounded-md max-sm:rounded-sm"><button class="inline-flex items-center gap-1 h-7 max-sm:h-7 px-2 max-sm:px-1.5 text-sm font-medium text-gray-800 border border-r-0 rounded-l-md max-sm:rounded-l-sm border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-live="polite"><span class="inline-flex items-center justify-center rounded-md p-0.5 max-sm:p-0 hover:text-gray-800 dark:hover:text-gray-200"><svg class="sm:size-3.5 size-3" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----></span> <span dir="auto">Copy page</span></button> <button class="inline-flex items-center justify-center w-6 max-sm:w-5 h-7 max-sm:h-7 disabled:pointer-events-none text-sm text-gray-500 hover:text-gray-700 dark:hover:text-white rounded-r-md max-sm:rounded-r-sm border border-l transition border-gray-200 bg-white hover:shadow-inner dark:border-gray-850 dark:bg-gray-950 dark:text-gray-200 dark:hover:bg-gray-800" aria-haspopup="menu" aria-expanded="false" aria-label="Open copy menu"><svg class="transition-transform text-gray-400 overflow-visible sm:size-3.5 size-3 rotate-0" width="1em" height="1em" viewBox="0 0 12 7" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M1 1L6 6L11 1" stroke="currentColor"></path></svg><!----></button></div> <!--[-1--><!--]--></div><!----> <!--[0--><h1 class="relative group"><a id="pipeline-callbacks" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#pipeline-callbacks"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span><!---->Pipeline 콜백<!----></span></h1><!--]--><!----> <p>Callback은 denoising 단계의 끝에서 실행되며, 이후 단계를 위해 pipeline 상태나 텐서를 변경할 수 있습니다. pipeline을 다시 작성하지 않고 새로운 동작을 위해 속성이나 텐서 변수를 조정하는 데 사용하세요.</p> <p>이 콜백은 기본적으로 클래식 <a href="/docs/diffusers/main/ko/api/pipelines/overview#diffusers.DiffusionPipeline">DiffusionPipeline</a> 루프와 함께 작동합니다. 디노이징 루프에 이를 실행하는 블록이 삽입되면 <a href="../modular_diffusers/overview">Modular Diffusers</a> 파이프라인에서도 작동하며, <a href="#modular-pipelines">Modular pipelines</a>를 참고하세요.</p> <p>Diffusers는 파이프라인 <a href="../api/pipelines/overview#diffusers.callbacks.PipelineCallback">개요</a>에서 여러 콜백을 제공합니다.</p> <p>콜백을 활성화하려면, … 중 하나의 인수를 사용하여 특정 수의 디노이징 단계 이후에 콜백이 실행되는 시점을 구성합니다.</p> <ul><li><code>cutoff_step_ratio</code>는 전체 디노이징 스텝의 백분율로 콜백이 활성화되는 시점을 지정합니다. 컷오프가 <code>num_inference_steps</code>에 따라 비례적으로 조정되어야 하는 경우(예: 실행의 40% 이후에 CFG 제거)에 사용합니다.</li> <li><code>cutoff_step_index</code>는 콜백이 활성화되는 정확한 스텝 번호를 지정합니다. 절대 스텝(예: 고정된 25스텝 스케줄의 <code>10</code>번째 스텝)에 관심이 있을 때 사용합니다.</li></ul> <p>아래 예시는 <code>cutoff_step_ratio=0.4</code>를 사용하여, 디노이징이 전체 추론 단계의 40%에 도달하면 콜백이 활성화됩니다. <a href="/docs/diffusers/main/ko/api/pipelines/overview#diffusers.callbacks.SDXLCFGCutoffCallback">SDXLCFGCutoffCallback</a>은 특정 단계 이후에 classifier-free guidance(CFG)를 비활성화하여, 성능에 큰 영향을 주지 않으면서도 계산 비용을 절감하는 데 도움이 될 수 있습니다.</p> <p><code>cutoff</code> 인자 중 하나를 사용하여 콜백을 정의하고, 파이프라인의 <code>callback_on_step_end</code> 매개변수에 전달합니다.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> 복사됨</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DPMSolverMultistepScheduler, StableDiffusionXLPipeline
<span class="hljs-keyword">from</span> diffusers.callbacks <span class="hljs-keyword">import</span> SDXLCFGCutoffCallback

callback = SDXLCFGCutoffCallback(cutoff_step_ratio=<span class="hljs-number">0.4</span>)
<span class="hljs-comment"># if using cutoff_step_index</span>
<span class="hljs-comment"># callback = SDXLCFGCutoffCallback(cutoff_step_ratio=None, cutoff_step_index=10)</span>

pipeline = StableDiffusionXLPipeline.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>  <span class="hljs-comment"># or &quot;mps&quot;, &quot;xpu&quot;, &quot;cpu&quot;</span>
)
pipeline.scheduler = DPMSolverMultistepScheduler.from_config(pipeline.scheduler.config, use_karras_sigmas=<span class="hljs-literal">True</span>)

prompt = <span class="hljs-string">&quot;a sports car on the road, best quality, high quality, high detail, 8k resolution&quot;</span>
output = pipeline(
    prompt=prompt,
    negative_prompt=<span class="hljs-string">&quot;&quot;</span>,
    guidance_scale=<span class="hljs-number">6.5</span>,
    num_inference_steps=<span class="hljs-number">25</span>,
    callback_on_step_end=callback,
)<!----></pre></div><!----> <p>공식 콜백은 자체적으로 텐서 입력을 설정합니다. 사용자 정의 함수의 경우, <a href="#display-intermediate-images">중간 이미지 표시</a>에서와 같이 <code>callback_on_step_end_tensor_inputs</code>를 전달합니다.</p> <p>새로운 공식 callback을 추가하려면 <a href="https://github.com/huggingface/diffusers/issues/new/choose" rel="nofollow">기능 요청</a>을 열거나 <a href="https://huggingface.co/docs/diffusers/main/en/conceptual/contribution#how-to-open-a-pr" rel="nofollow">PR을 제출</a>할 수 있습니다. 그렇지 않으면 아래에 나와 있는 대로 직접 callback을 만들 수도 있습니다.</p> <!--[1--><h2 class="relative group"><a id="early-stopping" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#early-stopping"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span><!---->조기 종료<!----></span></h2><!--]--><!----> <p>Early stopping은 생성 과정 중 중간 결과에 만족하지 못할 때 유용합니다. 이 콜백은 <code>_interrupt</code> 속성을 <code>True</code>로 설정하여 하드코딩된 중단 지점을 설정하며, 이를 통해 denoising 루프가 나머지 스텝을 건너뛰게 됩니다.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> 복사됨</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> DiffusionPipeline

<span class="hljs-keyword">def</span> <span class="hljs-title function_">interrupt_callback</span>(<span class="hljs-params">pipeline, i, t, callback_kwargs</span>):
    stop_idx = <span class="hljs-number">10</span>
    <span class="hljs-keyword">if</span> i == stop_idx:
        pipeline._interrupt = <span class="hljs-literal">True</span>
    <span class="hljs-keyword">return</span> callback_kwargs

pipeline = DiffusionPipeline.from_pretrained(
    <span class="hljs-string">&quot;Qwen/Qwen-Image&quot;</span>,
    dtype=torch.bfloat16,
    device_map=<span class="hljs-string">&quot;cuda&quot;</span>,  <span class="hljs-comment"># or &quot;mps&quot;, &quot;xpu&quot;, &quot;cpu&quot;</span>
)
pipeline(
    prompt=<span class="hljs-string">&quot;A photo of a cat&quot;</span>,
    num_inference_steps=<span class="hljs-number">50</span>,
    callback_on_step_end=interrupt_callback,
)<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="display-intermediate-images" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#display-intermediate-images"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span><!---->중간 이미지 표시<!----></span></h2><!--]--><!----> <p>중간 이미지를 시각화하는 것은 진행 상황 모니터링에 유용합니다. 아래 미리보기는 SDXL 전용입니다. 디노이징(denoising) 중에 빠르게 확인하기 위해 SDXL의 latents를 선형 변환(linear transform)으로 RGB로 매핑합니다. 해당 가중치는 다른 모델에 적용되지 않습니다. Qwen-Image 및 유사한 체크포인트의 경우, 이 헬퍼 대신 모델의 VAE로 디코딩하세요.</p> <p><a href="https://huggingface.co/blog/TimothyAlexisVass/explaining-the-sdxl-latent-space" rel="nofollow">변환</a> Stable Diffusion XL latents(4채널)를 RGB 텐서(3채널)로 변환합니다.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> 복사됨</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> PIL <span class="hljs-keyword">import</span> Image
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> AutoPipelineForText2Image

<span class="hljs-keyword">def</span> <span class="hljs-title function_">latents_to_rgb</span>(<span class="hljs-params">latents</span>):
    weights = (
        (<span class="hljs-number">60</span>, -<span class="hljs-number">60</span>, <span class="hljs-number">25</span>, -<span class="hljs-number">70</span>),
        (<span class="hljs-number">60</span>,  -<span class="hljs-number">5</span>, <span class="hljs-number">15</span>, -<span class="hljs-number">50</span>),
        (<span class="hljs-number">60</span>,  <span class="hljs-number">10</span>, -<span class="hljs-number">5</span>, -<span class="hljs-number">35</span>),
    )

    weights_tensor = torch.t(torch.tensor(weights, dtype=latents.dtype).to(latents.device))
    biases_tensor = torch.tensor((<span class="hljs-number">150</span>, <span class="hljs-number">140</span>, <span class="hljs-number">130</span>), dtype=latents.dtype).to(latents.device)
    rgb_tensor = torch.einsum(<span class="hljs-string">&quot;...lxy,lr -&gt; ...rxy&quot;</span>, latents, weights_tensor) + biases_tensor.unsqueeze(-<span class="hljs-number">1</span>).unsqueeze(-<span class="hljs-number">1</span>)
    image_array = rgb_tensor.clamp(<span class="hljs-number">0</span>, <span class="hljs-number">255</span>).byte().cpu().numpy().transpose(<span class="hljs-number">1</span>, <span class="hljs-number">2</span>, <span class="hljs-number">0</span>)

    <span class="hljs-keyword">return</span> Image.fromarray(image_array)<!----></pre></div><!----> <p>latents를 추출하고 배치의 첫 번째 이미지를 RGB로 변환합니다. 이미지를 단계 번호를 포함하여 PNG 파일로 저장합니다.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> 복사됨</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">def</span> <span class="hljs-title function_">decode_tensors</span>(<span class="hljs-params">pipe, step, timestep, callback_kwargs</span>):
    latents = callback_kwargs[<span class="hljs-string">&quot;latents&quot;</span>]

    image = latents_to_rgb(latents[<span class="hljs-number">0</span>])
    image.save(<span class="hljs-string">f&quot;<span class="hljs-subst">{step}</span>.png&quot;</span>)

    <span class="hljs-keyword">return</span> callback_kwargs<!----></pre></div><!----> <p><code>callback_on_step_end_tensor_inputs</code>를 사용하여 콜백이 수신할 텐서를 선택합니다. 이 경우 해당 텐서는 latents입니다.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> 복사됨</div><!----></button><!----></div> <pre class="language-py "><!---->pipeline = AutoPipelineForText2Image.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>  <span class="hljs-comment"># or &quot;mps&quot;, &quot;xpu&quot;, &quot;cpu&quot;</span>
)

image = pipeline(
    prompt=<span class="hljs-string">&quot;A croissant shaped like a cute bear.&quot;</span>,
    negative_prompt=<span class="hljs-string">&quot;Deformed, ugly, bad anatomy&quot;</span>,
    callback_on_step_end=decode_tensors,
    callback_on_step_end_tensor_inputs=[<span class="hljs-string">&quot;latents&quot;</span>],
).images[<span class="hljs-number">0</span>]<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="modular-pipelines" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#modular-pipelines"><span><svg xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg><!----></span></a> <span><!---->모듈형 파이프라인<!----></span></h2><!--]--><!----> <p>모듈형 파이프라인은 <code>callback_on_step_end</code> 및 <code>interrupt</code> 메커니즘을 지원하지 않습니다. 대신 일급 스트리밍 지원이 제공됩니다. 아직 병합되지 않은 <a href="https://github.com/huggingface/diffusers/pull/14159" rel="nofollow">huggingface/diffusers#14159</a>는 <code>pipe.stream()</code>을 추가하며, 이는 디노이징 단계마다 파이프라인 상태를 반환하고 반복을 중단하면 실행을 종료합니다. 현재는 기존 콜백 함수를 재사용하려면 디노이징 루프에 블록을 삽입해야 합니다. 이 블록은 단계 인덱스와 타임스텝을 포함한 루프의 <code>BlockState</code>를 수신하며, <code>latents</code>를 읽거나 수정할 수 있습니다.</p> <blockquote class="tip"><p><code>pipe.blocks</code>는 복사본을 반환하므로, 파이프라인이 생성된 이후에 수정해도 효과가 없습니다. 따라서 <a href="/docs/diffusers/main/ko/api/modular_diffusers/pipeline_blocks#diffusers.ModularPipelineBlocks.init_pipeline">init_pipeline()</a> <em>이전</em>에 블록을 수정해야 합니다.</p></blockquote> <p>아래 블록은 콜백을 파이프라인 입력으로 받아 위에서 설명한 것과 동일한 시그니처(파이프라인, 단계 인덱스, 타임스텝, 텐서 딕셔너리)로 호출합니다. 반환된 값은 다시 해당 딕셔너리에 기록됩니다. <code>walk_denoise_loops</code>는 해당 블록이 어떤 워크플로에 속해 있든 모든 디노이징 루프를 찾아내므로, 동일한 스니펫이 모든 모듈형 파이프라인에서 작동합니다.</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> 복사됨</div><!----></button><!----></div> <pre class="language-py "><!----><span class="hljs-keyword">from</span> typing <span class="hljs-keyword">import</span> <span class="hljs-type">Callable</span>

<span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> ModularPipeline
<span class="hljs-keyword">from</span> diffusers.modular_pipelines <span class="hljs-keyword">import</span> InputParam, LoopSequentialPipelineBlocks, ModularPipelineBlocks


<span class="hljs-keyword">class</span> <span class="hljs-title class_">CallbackOnStepEnd</span>(<span class="hljs-title class_ inherited__">ModularPipelineBlocks</span>):
<span class="hljs-meta">    @property</span>
    <span class="hljs-keyword">def</span> <span class="hljs-title function_">inputs</span>(<span class="hljs-params">self</span>):
        <span class="hljs-keyword">return</span> [
            InputParam(
                <span class="hljs-string">&quot;callback_on_step_end&quot;</span>,
                type_hint=<span class="hljs-type">Callable</span>,
                description=<span class="hljs-string">&quot;Called after each scheduler step as `callback(pipe, i, t, {&#x27;latents&#x27;: ...})`; the dict it returns is written back.&quot;</span>,
            ),
            InputParam(<span class="hljs-string">&quot;latents&quot;</span>, required=<span class="hljs-literal">True</span>),
        ]

    <span class="hljs-keyword">def</span> <span class="hljs-title function_">__call__</span>(<span class="hljs-params">self, components, block_state, i, t</span>):
        <span class="hljs-keyword">if</span> block_state.callback_on_step_end <span class="hljs-keyword">is</span> <span class="hljs-keyword">not</span> <span class="hljs-literal">None</span>:
            outputs = block_state.callback_on_step_end(components, i, t, {<span class="hljs-string">&quot;latents&quot;</span>: block_state.latents})
            block_state.latents = outputs.get(<span class="hljs-string">&quot;latents&quot;</span>, block_state.latents)
        <span class="hljs-keyword">return</span> components, block_state


<span class="hljs-keyword">def</span> <span class="hljs-title function_">walk_denoise_loops</span>(<span class="hljs-params">block</span>):
    <span class="hljs-string">&quot;&quot;&quot;Every denoising loop in the blocks, whichever workflow it belongs to.&quot;&quot;&quot;</span>
    <span class="hljs-keyword">if</span> <span class="hljs-built_in">isinstance</span>(block, LoopSequentialPipelineBlocks) <span class="hljs-keyword">and</span> <span class="hljs-string">&quot;denoiser&quot;</span> <span class="hljs-keyword">in</span> block.sub_blocks:
        <span class="hljs-keyword">yield</span> block
    <span class="hljs-keyword">for</span> sub <span class="hljs-keyword">in</span> <span class="hljs-built_in">getattr</span>(block, <span class="hljs-string">&quot;sub_blocks&quot;</span>, {}).values():
        <span class="hljs-keyword">yield</span> <span class="hljs-keyword">from</span> walk_denoise_loops(sub)


repo_id = <span class="hljs-string">&quot;stabilityai/stable-diffusion-xl-base-1.0&quot;</span>
blocks = ModularPipeline.from_pretrained(repo_id).blocks
<span class="hljs-keyword">for</span> loop <span class="hljs-keyword">in</span> walk_denoise_loops(blocks):
    loop.sub_blocks[<span class="hljs-string">&quot;callback&quot;</span>] = CallbackOnStepEnd()  <span class="hljs-comment"># appended after the last step of the loop</span>
pipe = blocks.init_pipeline(repo_id)
pipe.load_components(dtype=torch.float16)
pipe.to(<span class="hljs-string">&quot;cuda&quot;</span>)<!----></pre></div><!----> <p><code>callback_on_step_end</code>는 이제 파이프라인의 입력이며, <code>DiffusionPipeline</code>용으로 작성된 <code>decode_tensors</code>와 같은 콜백은 그대로 작동합니다:</p> <div class="code-block relative "><div class="absolute top-2.5 right-4"><button class="inline-flex items-center relative text-sm focus:text-green-500 cursor-pointer focus:outline-none transition duration-200 ease-in-out opacity-0 mx-0.5   text-gray-600  " title="code excerpt" type="button"><svg xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M28,10V28H10V10H28m0-2H10a2,2,0,0,0-2,2V28a2,2,0,0,0,2,2H28a2,2,0,0,0,2-2V10a2,2,0,0,0-2-2Z" transform="translate(0)"></path><path d="M4,18H2V4A2,2,0,0,1,4,2H18V4H4Z" transform="translate(0)"></path><rect fill="none" width="32" height="32"></rect></svg><!----> <div class=" absolute pointer-events-none transition-opacity bg-black text-white py-1 px-2 leading-tight rounded font-normal shadow left-1/2 top-full transform -translate-x-1/2 translate-y-2 opacity-0 "><div class="absolute bottom-full left-1/2 transform -translate-x-1/2 w-0 h-0 border-black border-4 border-t-0" style="border-left-color: transparent; border-right-color: transparent;"></div> 복사됨</div><!----></button><!----></div> <pre class="language-py "><!---->image = pipe(prompt=<span class="hljs-string">&quot;A croissant shaped like a cute bear.&quot;</span>, callback_on_step_end=decode_tensors, output=<span class="hljs-string">&quot;images&quot;</span>)[<span class="hljs-number">0</span>]<!----></pre></div><!----> <p><a href="#early-stopping">Early stopping</a>은 동작 방식이 다릅니다. 블록은 실행 중인 루프를 건너뛸 수 없으므로 <code>_interrupt</code>를 설정해도 효과가 없습니다. 대신 콜백에서 예외를 발생시키세요. 예외는 <code>pipe(...)</code>에서 전파되어 나옵니다(이미지가 디코딩되지 않음) 그리고 파이프라인은 이후에도 계속 사용할 수 있습니다.</p> <p>이 방법은 Helios와 Wan-Animate-2와 같은 자기회귀 비디오 모델처럼 외부 루프의 블록 내부에서 각 청크를 디노이즈하는 중첩 루프의 내부 루프를 제외한 모든 모듈형 파이프라인에 적용됩니다. 해당 경우, 블록을 외부 루프에 삽입하십시오. 이 경우 블록은 청크마다 한 번씩 실행되며, <code>i</code>와 <code>t</code> 대신 청크 인덱스 <code>k</code>를 수신합니다.</p> <a class="!text-gray-400 !no-underline text-sm flex items-center not-prose mt-4" href="https://github.com/huggingface/diffusers/blob/main/docs/source/en/using-diffusers/callback.md" target="_blank"><svg class="mr-1" xmlns="http://www.w3.org/2000/svg" aria-hidden="true" fill="currentColor" focusable="false" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 32 32"><path d="M31,16l-7,7l-1.41-1.41L28.17,16l-5.58-5.59L24,9l7,7z"></path><path d="M1,16l7-7l1.41,1.41L3.83,16l5.58,5.59L8,23l-7-7z"></path><path d="M12.419,25.484L17.639,6.552l1.932,0.518L14.351,26.002z"></path></svg><!----> <span><span class="underline">Update</span> on GitHub</span></a><!----> <p></p><!--]--><!----><!--]--><!--]--><!--]--> <!--[-1--><!--]--><!--]-->
			
			<script>
				{
					__sveltekit_1rjuniz = {
						base: "/docs/diffusers/main/en",
						assets: "/docs/diffusers/main/en"
					};
					const element = document.currentScript.parentElement;
					Promise.all([
						import("/docs/diffusers/main/en/_app/immutable/entry/start.vZc-dOUR.js"),
						import("/docs/diffusers/main/en/_app/immutable/entry/app.B6c3Ml05.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 379],
							data: [null,null],
							form: null,
							error: null
						});
					});
				}
			</script>
		
Xet Storage Details

Size:: 35.2 kB
Xet hash:: 470b82bb3ac7788341e1a2888e3b67989ef91db6020767b312f7149809f59c4b
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.