Hugging Face's logo

Buckets:
hf-doc-build
/
doc

Files
xet
hf-doc-build/doc / diffusers /main /ko /using-diffusers /weighted_prompts.html
mishig's picture
mishig
download
raw
23.7 kB
<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;프롬프팅&quot;,&quot;local&quot;:&quot;prompting&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;좋은 프롬프트 작성&quot;,&quot;local&quot;:&quot;writing-good-prompts&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;가이던스와 네거티브&quot;,&quot;local&quot;:&quot;guidance-and-negatives&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;프롬프트 가중치&quot;,&quot;local&quot;:&quot;prompt-weighting&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"/>
<link href="/docs/diffusers/main/en/_app/immutable/entry/start.0S0_iEoG.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/I9eooN77.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.CPdOxCbw.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.DteTvmQZ.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/409.446BYVDO.js" rel="modulepreload">
<link href="/docs/diffusers/main/en/_app/immutable/chunks/DSPDl1gz.js" rel="modulepreload">
<!--12846ih--><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;Prompting&quot;,&quot;local&quot;:&quot;prompting&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Writing good prompts&quot;,&quot;local&quot;:&quot;writing-good-prompts&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Guidance and negatives&quot;,&quot;local&quot;:&quot;guidance-and-negatives&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;Prompt weighting&quot;,&quot;local&quot;:&quot;prompt-weighting&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="prompting" 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="#prompting"><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><!---->프롬프팅<!----></span></h1><!--]--><!----> <p>Prompts는 모델이 생성해야 할 내용을 설명합니다. 좋은 Prompts는 상세하고 구체적이며 구조화되어 있어 더 나은 이미지와 비디오를 생성합니다.</p> <p>이 가이드는 효과적인 프롬프트 작성 방법을 보여주고, 프롬프트를 더 강력하게 만드는 기법을 소개합니다.</p> <!--[1--><h2 class="relative group"><a id="writing-good-prompts" 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="#writing-good-prompts"><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><!---->좋은 프롬프트 작성<!----></span></h2><!--]--><!----> <p>효과적인 프롬프트에는 세 가지 핵심 요소가 필요합니다.</p> <ol><li>Subject - 생성하려는 대상. 프롬프트를 여기서 시작하세요.</li> <li>스타일 - 매체 또는 미학. 어떻게 보여야 하는가?</li> <li>Context - 행동, 설정, 무드에 대한 세부 정보.</li></ol> <p>이 요소들을 키워드 목록이 아닌 구조화된 서술로 활용하세요. 최신 모델은 키워드 매칭보다 자연어 이해 능력이 더 뛰어납니다. 먼저 간단하게 시작하고, 점차 세부 사항을 추가해 나가세요.</p> <p>더 나은 프롬프트를 만드는 데에는 컨텍스트가 특히 중요합니다. 조명, 예술적 디테일, 무드를 추가해 보세요.</p> <div class="flex gap-4"><div class="flex-1 text-center"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/ok-prompt.png" class="w-full h-auto object-cover rounded-lg"/> <figcaption>평화로운 여름 오후, 풀장 속 잎사귀에 누워 있는 귀여운 고양이, 로파이 아트 스타일, 일러스트.</figcaption></div> <div class="flex-1 text-center"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/better-prompt.png" class="w-full h-auto object-cover rounded-lg"/> <figcaption>평화로운 여름 오후, 반짝이는 연못 위 떠 있는 잎사귀에 귀여운 고양이가 늘어져 있습니다. 맑은 물결이 물 표면을 따라 일렁이고, 햇살이 부드럽고 매끄러운 하이라이트를 드리웁니다. 이 일러스트는 세련된 선과 조화로운 색감으로 섬세하고 정교하게 표현되어 있으며, 애니메이션에서 영감을 받은 시각적으로 편안한 무드와 함께 이완되고 고요하며 환상적인 로파이(Lo-fi) 분위기를 자아냅니다.</figcaption></div></div> <p>구체적으로 작성하고 컨텍스트를 추가하세요. 렌즈 유형, 초점 거리, 카메라 앵글, 심도(Depth of Field)와 같은 사진 용어를 사용하세요.</p> <blockquote class="tip"><p>프롬프트 구조를 개선하는 데 도움이 되는 <a href="https://huggingface.co/models?sort=downloads&amp;search=prompt+enhancer" rel="nofollow">prompt enhancer</a>를 사용해 보세요.</p></blockquote> <!--[1--><h2 class="relative group"><a id="guidance-and-negatives" 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="#guidance-and-negatives"><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><!---->가이던스와 네거티브<!----></span></h2><!--]--><!----> <p>대부분의 Diffusers 파이프라인은 여전히 classifier-free guidance와 선택적 <code>negative_prompt</code>를 사용하여 샘플링을 제어합니다.</p> <p>Stable Diffusion 계열 파이프라인에서는 <code>guidance_scale</code>과 <code>negative_prompt</code>를 전달합니다. <code>guidance_scale</code> 값이 높을수록 프롬프트를 더 밀접하게 따릅니다. 값이 너무 높으면 결과가 부자연스럽거나 과포화되어 보일 수 있습니다.</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
pipeline = DiffusionPipeline.from_pretrained(
<span class="hljs-string">&quot;stable-diffusion-v1-5/stable-diffusion-v1-5&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 cozy reading nook with afternoon light&quot;</span>,
negative_prompt=<span class="hljs-string">&quot;blurry, low quality, distorted&quot;</span>,
guidance_scale=<span class="hljs-number">7.5</span>,
).images[<span class="hljs-number">0</span>]<!----></pre></div><!----> <p>Qwen-Image, Flux와 같은 새로운 체크포인트에서는 일반적으로 <code>true_cfg_scale</code>과 <code>negative_prompt</code>를 함께 사용하여 클래식 CFG를 적용합니다. true CFG가 활성화된 경우(<code>true_cfg_scale > 1</code>이고 <code>negative_prompt</code>가 있는 경우)에도 negative는 여전히 적용됩니다. <code>guidance_scale</code> 인수는 transformer가 이를 지원하는 경우 distilled 또는 embedded guidance를 의미하며, 이는 true CFG와 동일하지 않습니다. 로드하는 모델의 pipeline API를 확인하세요.</p> <p>Modular Diffusers는 guidance 알고리즘을 guider로 대체할 수 있습니다. <a href="./guiders">Guiders</a>를 참조하세요.</p> <!--[1--><h2 class="relative group"><a id="prompt-weighting" 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="#prompt-weighting"><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><!---->프롬프트 가중치<!----></span></h2><!--]--><!----> <p>Prompt weighting은 일부 단어의 강도를 높이고 다른 단어의 강도를 낮춥니다. attention score를 스케일링하여 각 개념이 미치는 영향의 정도를 제어할 수 있습니다.</p> <p>Diffusers는 <code>prompt_embeds</code>와 <code>pooled_prompt_embeds</code> 인수를 통해 이를 처리하며, 이 인수는 스케일링된 텍스트 임베딩 벡터를 받습니다. 이러한 임베딩을 생성하려면 <a href="https://github.com/xhinker/sd_embed" rel="nofollow">sd_embed</a> 라이브러리를 사용하세요. 또한 더 긴 프롬프트도 지원합니다. 더 간단한 구문으로 Stable Diffusion 계열의 가중치를 적용하려면 <a href="https://github.com/damian0815/compel" rel="nofollow">Compel</a>을 사용할 수도 있습니다.</p> <blockquote class="note"><p>sd_embed 라이브러리는 Stable Diffusion, Stable Diffusion XL, Stable Diffusion 3, Stable Cascade, Flux만 지원합니다. 프롬프트 가중치는 이미 프롬프트를 충실히 따르는 Flux 계열 모델에서는 항상 도움이 되지 않습니다.</p></blockquote> <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-shell "><!---->uv pip install git+https://github.com/xhinker/sd_embed.git@main<!----></pre></div><!----> <p>수치 배율 또는 괄호를 사용하여 가중 텍스트를 포맷합니다. 괄호가 많을수록 가중치가 강해집니다.</p> <table><thead><tr><th>형식</th><th>multiplier</th></tr></thead><tbody><tr><td><code>(cat)</code></td><td>1.1배 증가</td></tr><tr><td><code>((cat))</code></td><td>1.21배 증가</td></tr><tr><td><code>(cat:1.5)</code></td><td>1.5배 증가</td></tr><tr><td><code>(cat:0.5)</code></td><td>weight를 0.5×로 설정</td></tr></tbody></table> <p>가중 프롬프트를 생성하여 <a href="https://github.com/xhinker/sd_embed/blob/4a47f71150a22942fa606fb741a1c971d95ba56f/src/sd_embed/embedding_funcs.py#L405" rel="nofollow">get_weighted_text_embeddings_sdxl</a>에 전달하고 임베딩을 생성합니다.</p> <blockquote class="tip"><p><code>negative_prompt_embeds</code>와 <code>negative_pooled_prompt_embeds</code>에 negative prompt를 전달할 수도 있습니다.</p></blockquote> <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">from</span> sd_embed.embedding_funcs <span class="hljs-keyword">import</span> get_weighted_text_embeddings_sdxl
pipeline = DiffusionPipeline.from_pretrained(
<span class="hljs-string">&quot;Lykon/dreamshaper-xl-1-0&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>
)
prompt = <span class="hljs-string">&quot;&quot;&quot;
A (cute cat:1.4) lounges on a (floating leaf:1.2) in a (sparkling pool:1.1) during a peaceful summer afternoon.
Gentle ripples reflect pastel skies, while (sunlight:1.1) casts soft highlights. The illustration is smooth and polished
with elegant, sketchy lines and subtle gradients, evoking a ((whimsical, nostalgic, dreamy lofi atmosphere:2.0)),
(anime-inspired:1.6), calming, comforting, and visually serene.
&quot;&quot;&quot;</span>
prompt_embeds, _, pooled_prompt_embeds, *_ = get_weighted_text_embeddings_sdxl(pipeline, prompt=prompt)<!----></pre></div><!----> <p><code>prompt_embeds</code>와 <code>pooled_prompt_embeds</code>에 임베딩을 전달하여 이미지를 생성하세요.</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 = pipeline(prompt_embeds=prompt_embeds, pooled_prompt_embeds=pooled_prompt_embeds).images[<span class="hljs-number">0</span>]<!----></pre></div><!----> <div class="flex justify-center"><img src="https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/prompt-embed-sdxl.png"/></div> <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/weighted_prompts.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_1qsdbwf = {
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.0S0_iEoG.js"),
import("/docs/diffusers/main/en/_app/immutable/entry/app.CPdOxCbw.js")
]).then(([kit, app]) => {
kit.start(app, element, {
node_ids: [0, 409],
data: [null,null],
form: null,
error: null
});
});
}
</script>

Xet Storage Details

Size:
23.7 kB
·
Xet hash:
065c29aaabc404dde1fc61cc8acfb1c2d7e777c2dc854d9eb2606a2cd08b4704

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