diffusers/pr_13813/en/api/pipelines/longcat_image.html

<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;LongCat-Image&quot;,&quot;local&quot;:&quot;longcat-image&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Key Features&quot;,&quot;local&quot;:&quot;key-features&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Usage Example&quot;,&quot;local&quot;:&quot;usage-example&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;LongCatImagePipeline&quot;,&quot;local&quot;:&quot;diffusers.LongCatImagePipeline&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;LongCatImagePipelineOutput&quot;,&quot;local&quot;:&quot;diffusers.pipelines.longcat_image.LongCatImagePipelineOutput&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}">
		<link href="/docs/diffusers/pr_13813/en/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
		<link rel="modulepreload" href="/docs/diffusers/pr_13813/en/_app/immutable/entry/start.514fc400.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_13813/en/_app/immutable/chunks/scheduler.53228c21.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_13813/en/_app/immutable/chunks/singletons.79500073.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_13813/en/_app/immutable/chunks/index.e93d0901.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_13813/en/_app/immutable/chunks/paths.45f7df20.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_13813/en/_app/immutable/entry/app.931786ad.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_13813/en/_app/immutable/chunks/preload-helper.f7246978.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_13813/en/_app/immutable/chunks/index.cac5d66a.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_13813/en/_app/immutable/nodes/0.ff1b9b87.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_13813/en/_app/immutable/chunks/each.e59479a4.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_13813/en/_app/immutable/nodes/172.838cd6a1.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_13813/en/_app/immutable/chunks/CopyLLMTxtMenu.5ac9ab94.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_13813/en/_app/immutable/chunks/globals.7f7f1b26.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_13813/en/_app/immutable/chunks/IconCopy.56f02e4d.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_13813/en/_app/immutable/chunks/MermaidChart.svelte_svelte_type_style_lang.92b2cd9d.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_13813/en/_app/immutable/chunks/Docstring.8a316450.js">
		<link rel="modulepreload" href="/docs/diffusers/pr_13813/en/_app/immutable/chunks/CodeBlock.606cbaf4.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{&quot;title&quot;:&quot;LongCat-Image&quot;,&quot;local&quot;:&quot;longcat-image&quot;,&quot;sections&quot;:[{&quot;title&quot;:&quot;Key Features&quot;,&quot;local&quot;:&quot;key-features&quot;,&quot;sections&quot;:[],&quot;depth&quot;:3},{&quot;title&quot;:&quot;Usage Example&quot;,&quot;local&quot;:&quot;usage-example&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;LongCatImagePipeline&quot;,&quot;local&quot;:&quot;diffusers.LongCatImagePipeline&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2},{&quot;title&quot;:&quot;LongCatImagePipelineOutput&quot;,&quot;local&quot;:&quot;diffusers.pipelines.longcat_image.LongCatImagePipelineOutput&quot;,&quot;sections&quot;:[],&quot;depth&quot;:2}],&quot;depth&quot;:1}"><!-- HEAD_svelte-u9bgzb_END -->      <p></p>   <div class="items-center shrink-0 min-w-[100px] max-sm:min-w-[50px] justify-end ml-auto flex" style="float: right; margin-left: 10px; display: inline-flex; position: relative; z-index: 10;"><div 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>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> </div>  <h1 class="relative group"><a id="longcat-image" 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="#longcat-image"><span><svg class="" 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>LongCat-Image</span></h1> <div class="flex flex-wrap space-x-1" data-svelte-h="svelte-si9ct8"><img alt="LoRA" src="https://img.shields.io/badge/LoRA-d8b4fe?style=flat"></div> <p data-svelte-h="svelte-1j3b5cc">We introduce LongCat-Image, a pioneering open-source and bilingual (Chinese-English) foundation model for image generation, designed to address core challenges in multilingual text rendering, photorealism, deployment efficiency, and developer accessibility prevalent in current leading models.</p>  <h3 class="relative group"><a id="key-features" 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="#key-features"><span><svg class="" 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>Key Features</span></h3> <ul data-svelte-h="svelte-1663eao"><li>🌟 <strong>Exceptional Efficiency and Performance</strong>: With only <strong>6B parameters</strong>, LongCat-Image surpasses numerous open-source models that are several times larger across multiple benchmarks, demonstrating the immense potential of efficient model design.</li> <li>🌟 <strong>Superior Editing Performance</strong>: LongCat-Image-Edit model achieves state-of-the-art performance among open-source models, delivering leading instruction-following and image quality with superior visual consistency.</li> <li>🌟 <strong>Powerful Chinese Text Rendering</strong>: LongCat-Image demonstrates superior accuracy and stability in rendering common Chinese characters compared to existing SOTA open-source models and achieves industry-leading coverage of the Chinese dictionary.</li> <li>🌟 <strong>Remarkable Photorealism</strong>: Through an innovative data strategy and training framework, LongCat-Image achieves remarkable photorealism in generated images.</li> <li>🌟 <strong>Comprehensive Open-Source Ecosystem</strong>: We provide a complete toolchain, from intermediate checkpoints to full training code, significantly lowering the barrier for further research and development.</li></ul> <p data-svelte-h="svelte-1w45r60">For more details, please refer to the comprehensive <a href="https://arxiv.org/abs/2412.11963" rel="nofollow"><strong><em>LongCat-Image Technical Report</em></strong></a></p>  <h2 class="relative group"><a id="usage-example" 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="#usage-example"><span><svg class="" 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>Usage Example</span></h2> <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 class="" 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> Copied</div></button></div> <pre class="language-py "><!-- HTML_TAG_START --><span class="hljs-keyword">import</span> torch
<span class="hljs-keyword">import</span> diffusers
<span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> LongCatImagePipeline

weight_dtype = torch.bfloat16
pipe = LongCatImagePipeline.from_pretrained(<span class="hljs-string">&quot;meituan-longcat/LongCat-Image&quot;</span>, torch_dtype=torch.bfloat16 )
pipe.to(<span class="hljs-string">&#x27;cuda&#x27;</span>)
<span class="hljs-comment"># pipe.enable_model_cpu_offload()</span>

prompt = <span class="hljs-string">&#x27;一个年轻的亚裔女性，身穿黄色针织衫，搭配白色项链。她的双手放在膝盖上，表情恬静。背景是一堵粗糙的砖墙，午后的阳光温暖地洒在她身上，营造出一种宁静而温馨的氛围。镜头采用中距离视角，突出她的神态和服饰的细节。光线柔和地打在她的脸上，强调她的五官和饰品的质感，增加画面的层次感与亲和力。整个画面构图简洁，砖墙的纹理与阳光的光影效果相得益彰，突显出人物的优雅与从容。&#x27;</span>
image = pipe(
    prompt,
    height=<span class="hljs-number">768</span>,
    width=<span class="hljs-number">1344</span>,
    guidance_scale=<span class="hljs-number">4.0</span>,
    num_inference_steps=<span class="hljs-number">50</span>,
    num_images_per_prompt=<span class="hljs-number">1</span>,
    generator=torch.Generator(<span class="hljs-string">&quot;cpu&quot;</span>).manual_seed(<span class="hljs-number">43</span>),
    enable_cfg_renorm=<span class="hljs-literal">True</span>,
    enable_prompt_rewrite=<span class="hljs-literal">True</span>,
).images[<span class="hljs-number">0</span>]
image.save(<span class="hljs-string">f&#x27;./longcat_image_t2i_example.png&#x27;</span>)<!-- HTML_TAG_END --></pre></div> <p data-svelte-h="svelte-oanamx">This pipeline was contributed by LongCat-Image Team. The original codebase can be found <a href="https://github.com/meituan-longcat/LongCat-Image" rel="nofollow">here</a>.</p> <p data-svelte-h="svelte-1bob28v">Available models:</p> <div style="overflow-x: auto; margin-bottom: 16px;" data-svelte-h="svelte-tfnkyg"><table style="border-collapse: collapse; width: 100%;"><thead><tr><th style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa;">Models</th> <th style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa;">Type</th> <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa;">Description</th> <th style="padding: 8px; border: 1px solid #d0d7de; background-color: #f6f8fa;">Download Link</th></tr></thead> <tbody><tr><td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">LongCat‑Image</td> <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">Text‑to‑Image</td> <td style="padding: 8px; border: 1px solid #d0d7de;">Final Release. The standard model for out‑of‑the‑box inference.</td> <td style="padding: 8px; border: 1px solid #d0d7de;"><span style="white-space: nowrap;">🤗 <a href="https://huggingface.co/meituan-longcat/LongCat-Image">Huggingface</a></span></td></tr> <tr><td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">LongCat‑Image‑Dev</td> <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">Text‑to‑Image</td> <td style="padding: 8px; border: 1px solid #d0d7de;">Development. Mid-training checkpoint, suitable for fine-tuning.</td> <td style="padding: 8px; border: 1px solid #d0d7de;"><span style="white-space: nowrap;">🤗 <a href="https://huggingface.co/meituan-longcat/LongCat-Image-Dev">Huggingface</a></span></td></tr> <tr><td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">LongCat‑Image‑Edit</td> <td style="white-space: nowrap; padding: 8px; border: 1px solid #d0d7de;">Image Editing</td> <td style="padding: 8px; border: 1px solid #d0d7de;">Specialized model for image editing.</td> <td style="padding: 8px; border: 1px solid #d0d7de;"><span style="white-space: nowrap;">🤗 <a href="https://huggingface.co/meituan-longcat/LongCat-Image-Edit">Huggingface</a></span></td></tr></tbody></table></div>  <h2 class="relative group"><a id="diffusers.LongCatImagePipeline" 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="#diffusers.LongCatImagePipeline"><span><svg class="" 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>LongCatImagePipeline</span></h2> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"> <div><span class="group flex space-x-1.5 items-center text-gray-800 bg-gradient-to-r rounded-tr-lg -mt-4 -ml-4 pt-3 px-2.5" id="diffusers.LongCatImagePipeline"><!-- HTML_TAG_START --><h3 class="!m-0"><span class="flex-1 break-all md:text-lg bg-gradient-to-r px-2.5 py-1.5 rounded-xl from-indigo-50/70 to-white dark:from-gray-900 dark:to-gray-950 dark:text-indigo-300 text-indigo-700"><svg class="mr-1.5 text-indigo-500 inline-block -mt-0.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width=".8em" height=".8em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 24 24"><path class="uim-quaternary" d="M20.23 7.24L12 12L3.77 7.24a1.98 1.98 0 0 1 .7-.71L11 2.76c.62-.35 1.38-.35 2 0l6.53 3.77c.29.173.531.418.7.71z" opacity=".25" fill="currentColor"></path><path class="uim-tertiary" d="M12 12v9.5a2.09 2.09 0 0 1-.91-.21L4.5 17.48a2.003 2.003 0 0 1-1-1.73v-7.5a2.06 2.06 0 0 1 .27-1.01L12 12z" opacity=".5" fill="currentColor"></path><path class="uim-primary" d="M20.5 8.25v7.5a2.003 2.003 0 0 1-1 1.73l-6.62 3.82c-.275.13-.576.198-.88.2V12l8.23-4.76c.175.308.268.656.27 1.01z" fill="currentColor"></path></svg><span class="font-light">class</span> <span class="font-medium">diffusers.</span><span class="font-semibold">LongCatImagePipeline</span></span></h3><!-- HTML_TAG_END --> <a id="diffusers.LongCatImagePipeline" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.LongCatImagePipeline"><svg class="" 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></a> <a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/diffusers/blob/vr_13813/src/diffusers/pipelines/longcat_image/pipeline_longcat_image.py#L205" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span class="hidden md:block mx-0.5 hover:!underline" data-svelte-h="svelte-122apf4">source</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span></a></span> <p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span data-svelte-h="svelte-8mvn6a">(</span> <span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">scheduler<span class="opacity-60">: FlowMatchEulerDiscreteScheduler</span></span> </span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">vae<span class="opacity-60">: AutoencoderKL</span></span> </span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">text_encoder<span class="opacity-60">: Qwen2_5_VLForConditionalGeneration</span></span> </span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">tokenizer<span class="opacity-60">: Qwen2Tokenizer</span></span> </span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">text_processor<span class="opacity-60">: Qwen2VLProcessor</span></span> </span><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">transformer<span class="opacity-60">: LongCatImageTransformer2DModel</span></span> </span> <span data-svelte-h="svelte-1jq0pl7">)</span> </p>  <div class="!mb-10 relative docstring-details ">    </div></div> <p data-svelte-h="svelte-og3qel">The pipeline for text-to-image generation.</p></div> <ul data-svelte-h="svelte-1p6h59i"><li>all</li> <li><strong>call</strong></li></ul>  <h2 class="relative group"><a id="diffusers.pipelines.longcat_image.LongCatImagePipelineOutput" 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="#diffusers.pipelines.longcat_image.LongCatImagePipelineOutput"><span><svg class="" 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>LongCatImagePipelineOutput</span></h2> <div class="docstring border-l-2 border-t-2 pl-4 pt-3.5 border-gray-100 rounded-tl-xl mb-6 mt-8"> <div><span class="group flex space-x-1.5 items-center text-gray-800 bg-gradient-to-r rounded-tr-lg -mt-4 -ml-4 pt-3 px-2.5" id="diffusers.pipelines.longcat_image.LongCatImagePipelineOutput"><!-- HTML_TAG_START --><h3 class="!m-0"><span class="flex-1 break-all md:text-lg bg-gradient-to-r px-2.5 py-1.5 rounded-xl from-indigo-50/70 to-white dark:from-gray-900 dark:to-gray-950 dark:text-indigo-300 text-indigo-700"><svg class="mr-1.5 text-indigo-500 inline-block -mt-0.5" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" focusable="false" role="img" width=".8em" height=".8em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 24 24"><path class="uim-quaternary" d="M20.23 7.24L12 12L3.77 7.24a1.98 1.98 0 0 1 .7-.71L11 2.76c.62-.35 1.38-.35 2 0l6.53 3.77c.29.173.531.418.7.71z" opacity=".25" fill="currentColor"></path><path class="uim-tertiary" d="M12 12v9.5a2.09 2.09 0 0 1-.91-.21L4.5 17.48a2.003 2.003 0 0 1-1-1.73v-7.5a2.06 2.06 0 0 1 .27-1.01L12 12z" opacity=".5" fill="currentColor"></path><path class="uim-primary" d="M20.5 8.25v7.5a2.003 2.003 0 0 1-1 1.73l-6.62 3.82c-.275.13-.576.198-.88.2V12l8.23-4.76c.175.308.268.656.27 1.01z" fill="currentColor"></path></svg><span class="font-light">class</span> <span class="font-medium">diffusers.pipelines.longcat_image.</span><span class="font-semibold">LongCatImagePipelineOutput</span></span></h3><!-- HTML_TAG_END --> <a id="diffusers.pipelines.longcat_image.LongCatImagePipelineOutput" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.pipelines.longcat_image.LongCatImagePipelineOutput"><svg class="" 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></a> <a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/diffusers/blob/vr_13813/src/diffusers/pipelines/longcat_image/pipeline_output.py#L10" target="_blank"><span data-svelte-h="svelte-1kd6by1">&lt;</span> <span class="hidden md:block mx-0.5 hover:!underline" data-svelte-h="svelte-122apf4">source</span> <span data-svelte-h="svelte-x0xyl0">&gt;</span></a></span> <p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span data-svelte-h="svelte-8mvn6a">(</span> <span class="comma cursor-pointer"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">images<span class="opacity-60">: list</span></span> </span> <span data-svelte-h="svelte-1jq0pl7">)</span> </p>  <div class="!mb-10 relative docstring-details "> <p class="flex items-center font-semibold !mt-2 !mb-2 text-gray-800" data-svelte-h="svelte-lt6pb6">Parameters <span class="flex-auto border-t-2 border-gray-100 dark:border-gray-700 ml-3"></span></p> <ul class="px-2"><li class="text-base !pl-4 my-3 rounded "><span class="group flex space-x-1.5 items-start"><a id="diffusers.pipelines.longcat_image.LongCatImagePipelineOutput.images" class="header-link block pr-0.5 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="#diffusers.pipelines.longcat_image.LongCatImagePipelineOutput.images"><span><svg class="text-smd" 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><!-- HTML_TAG_START --><strong>images</strong> (<code>list[PIL.Image.Image]</code> or <code>np.ndarray</code>) &#x2014;
List of denoised PIL images of length <code>batch_size</code> or numpy array of shape <code>(batch_size, height, width, num_channels)</code>. PIL images or numpy array present the denoised images of the diffusion pipeline.<!-- HTML_TAG_END --> </span></span> </li></ul>   </div></div> <p data-svelte-h="svelte-1qpjiuf">Output class for Stable Diffusion pipelines.</p></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/api/pipelines/longcat_image.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 data-svelte-h="svelte-zjs2n5"><span class="underline">Update</span> on GitHub</span></a>  <p></p> 
			
			<script>
				{
					__sveltekit_ylq59y = {
						assets: "/docs/diffusers/pr_13813/en",
						base: "/docs/diffusers/pr_13813/en",
						env: {}
					};

					const element = document.currentScript.parentElement;

					const data = [null,null];

					Promise.all([
						import("/docs/diffusers/pr_13813/en/_app/immutable/entry/start.514fc400.js"),
						import("/docs/diffusers/pr_13813/en/_app/immutable/entry/app.931786ad.js")
					]).then(([kit, app]) => {
						kit.start(app, element, {
							node_ids: [0, 172],
							data,
							form: null,
							error: null
						});
					});
				}
			</script>