Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"FLUX 3 Image Klein","local":"flux-3-image-klein","sections":[{"title":"Prompt upsampling","local":"prompt-upsampling","sections":[],"depth":2},{"title":"Image-to-image","local":"image-to-image","sections":[],"depth":2},{"title":"Layout control","local":"layout-control","sections":[],"depth":2},{"title":"Guidance scale","local":"guidance-scale","sections":[],"depth":2},{"title":"Step-distilled model","local":"step-distilled-model","sections":[],"depth":2},{"title":"Reproducible generation","local":"reproducible-generation","sections":[],"depth":2},{"title":"Workflows","local":"workflows","sections":[],"depth":2},{"title":"Per-step callbacks","local":"per-step-callbacks","sections":[],"depth":2},{"title":"Memory","local":"memory","sections":[],"depth":2},{"title":"Single-file loading","local":"single-file-loading","sections":[],"depth":2},{"title":"Flux3ModularPipeline","local":"diffusers.Flux3ModularPipeline","sections":[],"depth":2},{"title":"Flux3AutoBlocks","local":"diffusers.Flux3AutoBlocks","sections":[],"depth":2},{"title":"Flux3DistilledAutoBlocks","local":"diffusers.Flux3DistilledAutoBlocks","sections":[],"depth":2},{"title":"Flux3DistilledModularPipeline","local":"diffusers.Flux3DistilledModularPipeline","sections":[],"depth":2}],"depth":1}"/> | |
| <link href="/docs/diffusers/pr_14737/en/_app/immutable/entry/start.BsCWMOsu.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/pr_14737/en/_app/immutable/chunks/CPUOQDlE.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/pr_14737/en/_app/immutable/chunks/jDjavuwI.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/pr_14737/en/_app/immutable/entry/app.BES-iAOI.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/pr_14737/en/_app/immutable/chunks/CMF6C6Mt.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/pr_14737/en/_app/immutable/chunks/CvFcJ2dJ.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/pr_14737/en/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/pr_14737/en/_app/immutable/chunks/i0LL_sTA.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/pr_14737/en/_app/immutable/nodes/0.CBER5iUq.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/pr_14737/en/_app/immutable/chunks/9Uo8d8lw.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/pr_14737/en/_app/immutable/nodes/170.COpVs0hN.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/pr_14737/en/_app/immutable/chunks/BLbO27j4.js" rel="modulepreload"> | |
| <!--hchutw--><meta name="hf:doc:metadata" content="{"title":"FLUX 3 Image Klein","local":"flux-3-image-klein","sections":[{"title":"Prompt upsampling","local":"prompt-upsampling","sections":[],"depth":2},{"title":"Image-to-image","local":"image-to-image","sections":[],"depth":2},{"title":"Layout control","local":"layout-control","sections":[],"depth":2},{"title":"Guidance scale","local":"guidance-scale","sections":[],"depth":2},{"title":"Step-distilled model","local":"step-distilled-model","sections":[],"depth":2},{"title":"Reproducible generation","local":"reproducible-generation","sections":[],"depth":2},{"title":"Workflows","local":"workflows","sections":[],"depth":2},{"title":"Per-step callbacks","local":"per-step-callbacks","sections":[],"depth":2},{"title":"Memory","local":"memory","sections":[],"depth":2},{"title":"Single-file loading","local":"single-file-loading","sections":[],"depth":2},{"title":"Flux3ModularPipeline","local":"diffusers.Flux3ModularPipeline","sections":[],"depth":2},{"title":"Flux3AutoBlocks","local":"diffusers.Flux3AutoBlocks","sections":[],"depth":2},{"title":"Flux3DistilledAutoBlocks","local":"diffusers.Flux3DistilledAutoBlocks","sections":[],"depth":2},{"title":"Flux3DistilledModularPipeline","local":"diffusers.Flux3DistilledModularPipeline","sections":[],"depth":2}],"depth":1}"/><!----> | |
| <link href="/docs/diffusers/pr_14737/en/_app/immutable/assets/0.tn0RQdqM.css" rel="modulepreload"> <!--[--><!--[0--><!--[--><!--[0--><!--[--><p></p> <!--[0--><h1 class="relative group"><a id="flux-3-image-klein" 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="#flux-3-image-klein"><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>FLUX 3 Image Klein</span></h1><!--]--><!----> <p>FLUX 3 Image Klein is a 5.6B image generation model from Black Forest Labs: a single transformer (<a href="/docs/diffusers/pr_14737/en/api/models/flux3_transformer#diffusers.Flux3Transformer2DModel">Flux3Transformer2DModel</a>) generates images from a text prompt, alone or together with one or more reference images. Text conditioning comes from Qwen3-VL, and images use the FLUX.2 packed autoencoder (<code>AutoencoderKLFlux2</code>).</p> <p>FLUX 3 Image Klein ships as a <a href="../../modular_diffusers/overview">modular pipeline</a>. Get started with a text-to-image generation:</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!----><span class="hljs-keyword">import</span> torch | |
| <span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> ModularPipeline | |
| pipe = ModularPipeline.from_pretrained(<span class="hljs-string">"black-forest-labs/flux-3-image-klein-base"</span>) | |
| pipe.load_components(dtype={<span class="hljs-string">"vae"</span>: torch.float32, <span class="hljs-string">"default"</span>: torch.bfloat16}) | |
| pipe.to(<span class="hljs-string">"cuda"</span>) | |
| image = pipe( | |
| prompt=<span class="hljs-string">"A red fox in a snow-covered forest clearing at golden hour"</span>, | |
| generator=torch.Generator().manual_seed(<span class="hljs-number">0</span>), | |
| output=<span class="hljs-string">"images"</span>, | |
| )[<span class="hljs-number">0</span>] | |
| image.save(<span class="hljs-string">"fox.png"</span>)<!----></pre></div><!----> <p><code>prompt</code> is the only required input: the pipeline carries the recommended sampling settings (50 steps, guidance scale 3.5, scheduler shift 6.93) and generates 1024 x 1024 images by default. It takes one prompt per call; use <code>num_images_per_prompt</code> for several images of the same prompt.</p> <p>As you can see in the example above, loading and running differ a little from a <code>DiffusionPipeline</code>. Loading is lazy: <a href="/docs/diffusers/pr_14737/en/api/modular_diffusers/pipeline#diffusers.ModularPipeline.from_pretrained">from_pretrained()</a> only builds the pipeline, and you call <a href="/docs/diffusers/pr_14737/en/api/modular_diffusers/pipeline#diffusers.ModularPipeline.load_components">load_components()</a> to load the weights. A call returns the pipeline state, and you ask for what you need with <code>output</code>: <code>output="images"</code> here, or <code>output=["images", "prompt"]</code> to also get the caption the prompt upsampler wrote.</p> <blockquote class="tip"><p>If you’re working with <code>ModularPipeline</code> for the first time, read the <a href="../../modular_diffusers/quickstart">quickstart</a>, and <a href="../../modular_diffusers/coming_from_diffusion_pipeline">Coming from DiffusionPipeline</a> if you know the standard pipelines. Besides loading and outputs, a few other things differ: <a href="#guidance-scale">guidance</a>, <a href="#per-step-callbacks">callbacks</a> and <a href="#memory">offloading</a>.</p></blockquote> <!--[1--><h2 class="relative group"><a id="prompt-upsampling" 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-upsampling"><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>Prompt upsampling</span></h2><!--]--><!----> <p>Prompting matters: FLUX 3 Image Klein takes full scene captions that describe the subject, composition, lighting, and atmosphere, not short prompts; a request sent as typed gives generic output. That is why the pipeline runs the prompt upsampler first on every request, text-to-image and editing alike. It is a separate 9B model from Black Forest Labs (<a href="https://huggingface.co/black-forest-labs/flux-3-image-klein-pup" rel="nofollow">black-forest-labs/flux-3-image-klein-pup</a>) that expands <code>prompt</code> into such a caption before the text encoder, and a short prompt is all it takes.</p> <p>The prompt upsampler turns a short request, together with the reference images when editing, into the full scene caption the model takes: medium and style, scene, lighting and camera, each subject with its colors, materials and position in the frame. One model covers text-to-image, editing with reference images and layout with boxes. The caption it wrote comes back as the <code>prompt</code> output. In the example above, ask for it alongside the images to see what the image model received:</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!---->out = pipe( | |
| prompt=<span class="hljs-string">"A red fox in a snow-covered forest clearing at golden hour"</span>, | |
| generator=torch.Generator().manual_seed(<span class="hljs-number">0</span>), | |
| output=[<span class="hljs-string">"images"</span>, <span class="hljs-string">"prompt"</span>], | |
| ) | |
| <span class="hljs-built_in">print</span>(out[<span class="hljs-string">"prompt"</span>])<!----></pre></div><!----> <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> Copied</div><!----></button><!----></div> <pre class=" "><!---->Full-color outdoor wildlife photograph taken <span class="hljs-built_in">from</span> <span class="hljs-keyword">a</span> low eye-level perspective <span class="hljs-keyword">in</span> <span class="hljs-keyword">a</span> snow-covered forest clearing <span class="hljs-keyword">at</span> golden hour. In <span class="hljs-keyword">the</span> center foreground, <span class="hljs-keyword">a</span> red fox stands <span class="hljs-keyword">in</span> profile facing left, its body turned toward <span class="hljs-keyword">the</span> viewer <span class="hljs-keyword">and</span> its head raised <span class="hljs-keyword">as</span> <span class="hljs-keyword">it</span> looks across <span class="hljs-keyword">the</span> clearing. The fox has dense rust-red winter fur, <span class="hljs-keyword">a</span> white throat <span class="hljs-keyword">and</span> chest, <span class="hljs-keyword">black</span> <span class="hljs-built_in">lower</span> legs, pointed ears <span class="hljs-keyword">with</span> dark tips, <span class="hljs-keyword">and</span> <span class="hljs-keyword">a</span> <span class="hljs-keyword">long</span> bushy tail ending <span class="hljs-keyword">in</span> white. ...<!----></pre></div><!----> <p>The full caption runs to about 240 words; <code>max_new_tokens</code> caps its length (3584 by default).</p> <p>You can print the step’s <code>doc</code> to see what it takes and what it writes:</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!----><span class="hljs-built_in">print</span>(pipe.blocks.sub_blocks[<span class="hljs-string">"prompt_upsampler"</span>].doc)<!----></pre></div><!----> <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> Copied</div><!----></button><!----></div> <pre class=" "><!----> <span class="hljs-symbol">Inputs</span>: | |
| prompt (<span class="hljs-string">`str`</span>): | |
| <span class="hljs-symbol">The</span> edit instruction to expand into the full caption (one per call). | |
| image (<span class="hljs-string">`Image | list`</span>, *optional*): | |
| <span class="hljs-symbol">The</span> reference image(s) of the edit, at most <span class="hljs-number">10</span>; the same ones the pipeline receives. | |
| boxes (<span class="hljs-string">`list`</span>, *optional*): | |
| <span class="hljs-symbol">Layout</span> boxes, each {<span class="hljs-string">'id'</span>, <span class="hljs-string">'desc'</span>, <span class="hljs-string">'from'</span>, <span class="hljs-string">'src_bbox'</span>, <span class="hljs-string">'tgt_bbox'</span>} with the boxes as [y_min, x_min, y_max, x_max] in | |
| <span class="hljs-number">0</span><span class="hljs-number">-1</span>: ... | |
| max_new_tokens (<span class="hljs-string">`int`</span>, *optional*, defaults to <span class="hljs-number">3584</span>): | |
| <span class="hljs-symbol">The</span> most tokens the upsampler may generate for the caption. | |
| <span class="hljs-symbol">Outputs</span>: | |
| prompt (<span class="hljs-string">`str`</span>): | |
| <span class="hljs-symbol">The</span> full caption, replacing the request.<!----></pre></div><!----> <p>Like other blocks in the pipeline, the <code>prompt_upsampler</code> block also runs on its own. The recommended way is to pop it out of the blocks: the popped block becomes a standalone upsampler, and the remaining blocks become a pipeline that takes the expanded caption as <code>prompt</code>:</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!---->blocks = ModularPipeline.from_pretrained(<span class="hljs-string">"black-forest-labs/flux-3-image-klein-base"</span>).blocks | |
| pup_block = blocks.sub_blocks.pop(<span class="hljs-string">"prompt_upsampler"</span>) | |
| pup = pup_block.init_pipeline(<span class="hljs-string">"black-forest-labs/flux-3-image-klein-base"</span>) | |
| pup.load_components(dtype=torch.bfloat16) | |
| pup.to(<span class="hljs-string">"cuda"</span>) | |
| caption = pup(prompt=<span class="hljs-string">"A red fox in a snow-covered forest clearing at golden hour"</span>, output=<span class="hljs-string">"prompt"</span>) | |
| pipe = blocks.init_pipeline(<span class="hljs-string">"black-forest-labs/flux-3-image-klein-base"</span>) | |
| pipe.load_components(dtype={<span class="hljs-string">"vae"</span>: torch.float32, <span class="hljs-string">"default"</span>: torch.bfloat16}) | |
| pipe.to(<span class="hljs-string">"cuda"</span>) | |
| image = pipe(prompt=caption, generator=torch.Generator().manual_seed(<span class="hljs-number">0</span>), output=<span class="hljs-string">"images"</span>)[<span class="hljs-number">0</span>]<!----></pre></div><!----> <p>This way it can be served as a separate stage, on its own GPU or behind its own endpoint, and a UI can show the caption it wrote and let the user edit it before generating. Any other LLM can take the upsampler’s place, with the same system prompts: give it <code>system_prompts["t2i"]</code> from the upsampler repository (or <code>"i2i"</code>, with the references first in the user message) as the system prompt and the request as the user message, and pass the caption it returns as <code>prompt</code> to <code>pipe</code>.</p> <!--[1--><h2 class="relative group"><a id="image-to-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="#image-to-image"><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>Image-to-image</span></h2><!--]--><!----> <p>Pass one or more reference images with <code>image</code>. A single reference is kept whole: it is downscaled only above 4 megapixels, padded to the 16-pixel grid, and the generation defaults to its size, so the edit comes back at the size of the input. Several references are each fitted under 1 megapixel and cropped to the grid, and the generation defaults to the first one’s size. A given <code>height</code>/<code>width</code> overrides the default. Describe the <em>target</em> image as a complete caption of the reference with your edit folded in, rather than a one-line instruction, or let the <a href="#prompt-upsampling">prompt upsampler</a> write it from the instruction and the references:</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!---->night = pipe( | |
| prompt=<span class="hljs-string">"the same scene at night under a full moon"</span>, | |
| image=image, | |
| generator=torch.Generator().manual_seed(<span class="hljs-number">0</span>), | |
| output=[<span class="hljs-string">"images"</span>, <span class="hljs-string">"prompt"</span>], | |
| )<!----></pre></div><!----> <p>With several references, refer to them as the first image, the second image, … in the order they are passed to <code>image</code>; the caption names them <code><ref_image_0></code>, <code><ref_image_1></code>, … for the image model:</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!---->combined = pipe( | |
| prompt=<span class="hljs-string">"the fox from the first image sitting on the wooden bench from the second image"</span>, | |
| image=[image, bench], | |
| height=<span class="hljs-number">768</span>, | |
| width=<span class="hljs-number">1360</span>, | |
| output=<span class="hljs-string">"images"</span>, | |
| )[<span class="hljs-number">0</span>]<!----></pre></div><!----> <p>Pass <code>height</code> and/or <code>width</code> to override the derived size.</p> <!--[1--><h2 class="relative group"><a id="layout-control" 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="#layout-control"><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>Layout control</span></h2><!--]--><!----> <p>To place content explicitly, pass <code>boxes</code>: for each element an <code>id</code>, a short <code>desc</code>, and a <code>bbox</code> of <code>[y_min, x_min, y_max, x_max]</code> in 0-1 (origin top-left), so it is independent of the output size. The upsampler writes the caption around them, citing each element as <code><id></code>, and appends the table of boxes, yours kept exactly:</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!---->boxes = [ | |
| {<span class="hljs-string">"id"</span>: <span class="hljs-string">"balloon_1"</span>, <span class="hljs-string">"desc"</span>: <span class="hljs-string">"a red and yellow striped hot-air balloon"</span>, <span class="hljs-string">"bbox"</span>: [<span class="hljs-number">0.08</span>, <span class="hljs-number">0.06</span>, <span class="hljs-number">0.48</span>, <span class="hljs-number">0.38</span>]}, | |
| {<span class="hljs-string">"id"</span>: <span class="hljs-string">"balloon_2"</span>, <span class="hljs-string">"desc"</span>: <span class="hljs-string">"a small blue hot-air balloon"</span>, <span class="hljs-string">"bbox"</span>: [<span class="hljs-number">0.20</span>, <span class="hljs-number">0.62</span>, <span class="hljs-number">0.42</span>, <span class="hljs-number">0.80</span>]}, | |
| ] | |
| out = pipe(prompt=<span class="hljs-string">"hot-air balloons over a green valley at sunrise"</span>, boxes=boxes, output=[<span class="hljs-string">"images"</span>, <span class="hljs-string">"prompt"</span>])<!----></pre></div><!----> <p>When editing, a box names its source with <code>from</code>: <code>"target"</code> with a <code>tgt_bbox</code> adds a new element there, <code>"ref_image_0"</code> with a <code>src_bbox</code> and a <code>tgt_bbox</code> moves an element of that reference (equal boxes keep it in place):</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!---->boxes = [{<span class="hljs-string">"id"</span>: <span class="hljs-string">"cactus"</span>, <span class="hljs-string">"desc"</span>: <span class="hljs-string">"a small potted cactus"</span>, <span class="hljs-string">"from"</span>: <span class="hljs-string">"target"</span>, <span class="hljs-string">"src_bbox"</span>: <span class="hljs-literal">None</span>, <span class="hljs-string">"tgt_bbox"</span>: [<span class="hljs-number">0.55</span>, <span class="hljs-number">0.62</span>, <span class="hljs-number">0.85</span>, <span class="hljs-number">0.85</span>]}] | |
| out = pipe(prompt=<span class="hljs-string">"add a small potted cactus in the marked spot"</span>, image=mug, boxes=boxes, output=[<span class="hljs-string">"images"</span>, <span class="hljs-string">"prompt"</span>]) | |
| boxes = [{<span class="hljs-string">"id"</span>: <span class="hljs-string">"knight"</span>, <span class="hljs-string">"desc"</span>: <span class="hljs-string">"the knight figure"</span>, <span class="hljs-string">"from"</span>: <span class="hljs-string">"ref_image_0"</span>, <span class="hljs-string">"src_bbox"</span>: [<span class="hljs-number">0.50</span>, <span class="hljs-number">0.15</span>, <span class="hljs-number">0.85</span>, <span class="hljs-number">0.35</span>], <span class="hljs-string">"tgt_bbox"</span>: [<span class="hljs-number">0.19</span>, <span class="hljs-number">0.06</span>, <span class="hljs-number">0.54</span>, <span class="hljs-number">0.26</span>]}] | |
| out = pipe(prompt=<span class="hljs-string">"move the knight up and to the left, keep the rest unchanged"</span>, image=knight, boxes=boxes, output=[<span class="hljs-string">"images"</span>, <span class="hljs-string">"prompt"</span>])<!----></pre></div><!----> <p>The caption the image model reads has the elements tagged <code><id></code> in the text and the table appended as JSON, with the boxes on a 0-1000 canvas; print the <code>prompt</code> output to see it. A caption written in that form by hand goes to the pipeline without the step, as in <a href="#prompt-upsampling">Prompt upsampling</a>.</p> <!--[1--><h2 class="relative group"><a id="guidance-scale" 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-scale"><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>Guidance scale</span></h2><!--]--><!----> <p>The pipeline applies classifier-free guidance through its <code>guider</code> component and does not take a <code>guidance_scale</code> argument at call time. The default guider is <a href="/docs/diffusers/pr_14737/en/api/modular_diffusers/guiders#diffusers.ClassifierFreeGuidance">ClassifierFreeGuidance</a> with <code>guidance_scale=3.5</code>, the recommended setting for both workflows. To change it, create an updated copy of the guider:</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!---->pipe.guider = pipe.guider.new(guidance_scale=<span class="hljs-number">5.0</span>)<!----></pre></div><!----> <p>See the <a href="../../using-diffusers/guiders">guiders guide</a> to switch to a different guidance method.</p> <!--[1--><h2 class="relative group"><a id="step-distilled-model" 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="#step-distilled-model"><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>Step-distilled model</span></h2><!--]--><!----> <p>The step-distilled checkpoint generates in 16 steps without classifier-free guidance. Its transformer is a flow map: at every step it is told the current timestep and the one the step jumps to. It loads like the base model (the repo’s <code>modular_model_index.json</code> resolves to <a href="/docs/diffusers/pr_14737/en/api/pipelines/flux3#diffusers.Flux3DistilledModularPipeline">Flux3DistilledModularPipeline</a> and <a href="/docs/diffusers/pr_14737/en/api/pipelines/flux3#diffusers.Flux3DistilledAutoBlocks">Flux3DistilledAutoBlocks</a>); the pipeline has no <code>guider</code> and does not take <code>negative_prompt</code>:</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!---->pipe = ModularPipeline.from_pretrained(<span class="hljs-string">"black-forest-labs/flux-3-image-klein"</span>) | |
| pipe.load_components(dtype=torch.bfloat16) | |
| pipe.to(<span class="hljs-string">"cuda"</span>) | |
| image = pipe(prompt=prompt, generator=torch.Generator().manual_seed(<span class="hljs-number">0</span>), output=<span class="hljs-string">"images"</span>)[<span class="hljs-number">0</span>]<!----></pre></div><!----> <p>It serves the same two workflows as the base model. <code>num_inference_steps</code> defaults to 16; the model is trained for 4 to 16 steps.</p> <!--[1--><h2 class="relative group"><a id="reproducible-generation" 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="#reproducible-generation"><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>Reproducible generation</span></h2><!--]--><!----> <p>A <code>generator</code> fixes the noise the pipeline draws (see <a href="../../using-diffusers/reusing_seeds">Reproducibility</a>). To reuse noise drawn elsewhere, pass it as <code>latents</code> with shape <code>(batch_size, 128, height // 16, width // 16)</code>. For example, the <a href="https://github.com/black-forest-labs/flux-3" rel="nofollow">BFL implementation</a> draws its noise as image tokens on the CPU and casts it to bf16; this reproduces its sample for a given seed:</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!---->height, width = <span class="hljs-number">1024</span>, <span class="hljs-number">1024</span> | |
| h, w = height // <span class="hljs-number">16</span>, width // <span class="hljs-number">16</span> | |
| noise = torch.randn((h * w, <span class="hljs-number">128</span>), generator=torch.Generator().manual_seed(<span class="hljs-number">0</span>)).to(torch.bfloat16) | |
| latents = noise.T.reshape(<span class="hljs-number">1</span>, <span class="hljs-number">128</span>, h, w) | |
| image = pipe(prompt=prompt, latents=latents, height=height, width=width, output=<span class="hljs-string">"images"</span>)[<span class="hljs-number">0</span>]<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="workflows" 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="#workflows"><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>Workflows</span></h2><!--]--><!----> <p>The pipeline serves two workflows, <code>text2image</code> and <code>image_conditioned</code>; the one that runs is picked by the inputs (<code>image</code> selects image-to-image). <a href="/docs/diffusers/pr_14737/en/api/modular_diffusers/pipeline#diffusers.ModularPipeline.from_pretrained">from_pretrained()</a> can also build a pipeline for one workflow with the <code>workflow</code> argument, which then only expects and loads the components that workflow needs:</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!----><span class="hljs-keyword">from</span> diffusers.modular_pipelines <span class="hljs-keyword">import</span> Flux3AutoBlocks | |
| <span class="hljs-built_in">print</span>(Flux3AutoBlocks().available_workflows) | |
| <span class="hljs-comment"># ["text2image", "image_conditioned"]</span> | |
| t2i = ModularPipeline.from_pretrained(<span class="hljs-string">"black-forest-labs/flux-3-image-klein-base"</span>, workflow=<span class="hljs-string">"text2image"</span>) | |
| <span class="hljs-built_in">print</span>(t2i.blocks.doc)<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="per-step-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="#per-step-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>Per-step callbacks</span></h2><!--]--><!----> <p>To use an existing callback function, insert a block into the denoising loop. The <a href="../../using-diffusers/callback#modular-pipelines">callbacks guide</a> has a simple example with the <code>CallbackOnStepEnd</code> block and the <code>walk_denoise_loops</code> helper:</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!---->blocks = Flux3AutoBlocks() <span class="hljs-comment"># or Flux3DistilledAutoBlocks</span> | |
| <span class="hljs-keyword">for</span> loop <span class="hljs-keyword">in</span> walk_denoise_loops(blocks): | |
| loop.sub_blocks[<span class="hljs-string">"callback"</span>] = CallbackOnStepEnd() | |
| pipe = blocks.init_pipeline(<span class="hljs-string">"black-forest-labs/flux-3-image-klein-base"</span>) | |
| image = pipe(prompt=caption, callback_on_step_end=my_callback, output=<span class="hljs-string">"images"</span>)[<span class="hljs-number">0</span>]<!----></pre></div><!----> <p>To stop early, raise from the callback; there is no <code>interrupt</code> flag.</p> <!--[1--><h2 class="relative group"><a id="memory" 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="#memory"><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>Memory</span></h2><!--]--><!----> <p>Loading everything in bf16 takes about 39 GB of weights: the transformer is 5.5B parameters, the Qwen3-VL-4B text encoder 4B and the <a href="#prompt-upsampling">prompt upsampler</a> 9B (about 19 GB on its own), with the image VAE in fp32. A pipeline built without the upsampler step (see there) loads about 20 GB. For GPUs with less memory, enable component offloading; the manager moves components between the CPU and the GPU as each step needs them, the upsampler included:</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!----><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> ComponentsManager, ModularPipeline | |
| manager = ComponentsManager() | |
| pipe = ModularPipeline.from_pretrained(<span class="hljs-string">"black-forest-labs/flux-3-image-klein-base"</span>, components_manager=manager) | |
| pipe.load_components(dtype={<span class="hljs-string">"vae"</span>: torch.float32, <span class="hljs-string">"default"</span>: torch.bfloat16}) | |
| manager.enable_auto_cpu_offload(device=<span class="hljs-string">"cuda"</span>)<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="single-file-loading" 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="#single-file-loading"><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>Single-file loading</span></h2><!--]--><!----> <p><a href="/docs/diffusers/pr_14737/en/api/models/flux3_transformer#diffusers.Flux3Transformer2DModel">Flux3Transformer2DModel</a> loads the transformer straight from a Black Forest Labs model package with <a href="/docs/diffusers/pr_14737/en/api/loaders/single_file#diffusers.loaders.FromOriginalModelMixin.from_single_file">from_single_file()</a>. The package <code>config.json</code> is not read; pass the diffusers config with <code>config</code> and <code>subfolder</code>.</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!----><span class="hljs-keyword">import</span> torch | |
| <span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> Flux3Transformer2DModel, ModularPipeline | |
| transformer = Flux3Transformer2DModel.from_single_file( | |
| <span class="hljs-string">"https://huggingface.co/black-forest-labs/flux-3-image-klein-base/blob/main/model.safetensors"</span>, | |
| config=<span class="hljs-string">"black-forest-labs/flux-3-image-klein-base"</span>, | |
| subfolder=<span class="hljs-string">"transformer"</span>, | |
| dtype=torch.bfloat16, | |
| ) | |
| pipe = ModularPipeline.from_pretrained(<span class="hljs-string">"black-forest-labs/flux-3-image-klein-base"</span>) | |
| pipe.load_components(dtype={<span class="hljs-string">"vae"</span>: torch.float32, <span class="hljs-string">"default"</span>: torch.bfloat16}) | |
| pipe.update_components(transformer=transformer) | |
| pipe.to(<span class="hljs-string">"cuda"</span>)<!----></pre></div><!----> <p>Load the other components by name first: <a href="/docs/diffusers/pr_14737/en/api/modular_diffusers/pipeline#diffusers.ModularPipeline.load_components">load_components()</a> without <code>names</code> would also load the transformer from the pipeline repo.</p> <p>Loading the FP8r and NVFP4 single-file checkpoints are also supported. Both load through the same call with a <a href="/docs/diffusers/pr_14737/en/api/quantization#diffusers.BFLQuantizationConfig">BFLQuantizationConfig</a>. See the <a href="../../quantization/bfl">BFL quantization guide</a> for the kernel requirements of each scheme.</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!----><span class="hljs-keyword">from</span> diffusers <span class="hljs-keyword">import</span> BFLQuantizationConfig | |
| transformer = Flux3Transformer2DModel.from_single_file( | |
| <span class="hljs-string">"https://huggingface.co/black-forest-labs/flux-3-image-klein-base/blob/main/variants/nvfp4/model.safetensors"</span>, | |
| config=<span class="hljs-string">"black-forest-labs/flux-3-image-klein-base"</span>, | |
| subfolder=<span class="hljs-string">"transformer"</span>, | |
| quantization_config=BFLQuantizationConfig(compute_dtype=torch.bfloat16), | |
| dtype=torch.bfloat16, | |
| )<!----></pre></div><!----> <p>When loading the step-distilled checkpoints, we need their | |
| configs (<code>flow_map=True</code>):</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> Copied</div><!----></button><!----></div> <pre class="language-python "><!---->transformer = Flux3Transformer2DModel.from_single_file( | |
| <span class="hljs-string">"https://huggingface.co/black-forest-labs/flux-3-image-klein/blob/main/variants/nvfp4/model.safetensors"</span>, | |
| config=<span class="hljs-string">"black-forest-labs/flux-3-image-klein"</span>, | |
| subfolder=<span class="hljs-string">"transformer"</span>, | |
| quantization_config=BFLQuantizationConfig(compute_dtype=torch.bfloat16), | |
| dtype=torch.bfloat16, | |
| )<!----></pre></div><!----> <!--[1--><h2 class="relative group"><a id="diffusers.Flux3ModularPipeline" 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.Flux3ModularPipeline"><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>Flux3ModularPipeline</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.Flux3ModularPipeline"><!----><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">Flux3ModularPipeline</span></span></h3><!----> <a id="diffusers.Flux3ModularPipeline" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.Flux3ModularPipeline"><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><!----></a> <!--[0--><a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/diffusers/blob/vr_14737/src/diffusers/modular_pipelines/flux3/modular_pipeline.py#L24" target="_blank"><span><</span> <span class="hidden md:block mx-0.5 hover:!underline">source</span> <span>></span></a><!--]--></span> <!--[0--><p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span>(</span> <!--[--><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">blocks<span class="opacity-60">: diffusers.modular_pipelines.modular_pipeline.ModularPipelineBlocks | None = None</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">pretrained_model_name_or_path<span class="opacity-60">: str | os.PathLike | None = None</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">components_manager<span class="opacity-60">: diffusers.modular_pipelines.components_manager.ComponentsManager | None = None</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">collection<span class="opacity-60">: str | None = None</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">workflow<span class="opacity-60">: str | None = None</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">modular_config_dict<span class="opacity-60">: dict[str, typing.Any] | None = None</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">config_dict<span class="opacity-60">: dict[str, typing.Any] | None = None</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">**kwargs<span class="opacity-60"></span></span></span><!--]--> <span>)</span> <!--[-1--><!--]--></p><!--]--> <div class="!mb-10 relative docstring-details "><!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--></div></div><!----> <p>A ModularPipeline for FLUX.3.</p></div> <!--[1--><h2 class="relative group"><a id="diffusers.Flux3AutoBlocks" 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.Flux3AutoBlocks"><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>Flux3AutoBlocks</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.Flux3AutoBlocks"><!----><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">Flux3AutoBlocks</span></span></h3><!----> <a id="diffusers.Flux3AutoBlocks" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.Flux3AutoBlocks"><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><!----></a> <!--[0--><a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/diffusers/blob/vr_14737/src/diffusers/modular_pipelines/flux3/modular_blocks_flux3.py#L339" target="_blank"><span><</span> <span class="hidden md:block mx-0.5 hover:!underline">source</span> <span>></span></a><!--]--></span> <!--[0--><p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span>(</span> <!--[--><!--]--> <span>)</span> <!--[-1--><!--]--></p><!--]--> <div class="!mb-10 relative docstring-details "><!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--></div></div><!----> <p>Auto blocks that perform text-to-image and image-to-image generation using FLUX.3. <code>prompt</code> goes through the prompt | |
| upsampler first; pop the <code>prompt_upsampler</code> step to encode it as given.</p> <p>Supported workflows:</p> <ul><li><code>text2image</code>: requires <code>prompt</code></li> <li><code>image_conditioned</code>: requires <code>prompt</code>, <code>image</code></li></ul> <p>Components: | |
| prompt_upsampler (<code>Qwen3_5ForConditionalGeneration</code>): The prompt upsampler. prompt_upsampler_processor | |
| (<code>AutoProcessor</code>): Its processor. text_encoder (<code>Qwen3VLForConditionalGeneration</code>) tokenizer | |
| (<code>AutoProcessor</code>) image_processor (<code>Flux3ImageProcessor</code>) vae (<code>AutoencoderKLFlux2</code>) transformer | |
| (<code>Flux3Transformer2DModel</code>) scheduler (<code>FlowMatchEulerDiscreteScheduler</code>) guider (<code>ClassifierFreeGuidance</code>)</p> <p>Inputs: | |
| prompt (<code>str</code>): | |
| The edit instruction to expand into the full caption (one per call). | |
| image (<code>Image | list</code>, <em>optional</em>): | |
| The reference image(s) of the edit, at most 10; the same ones the pipeline receives. | |
| boxes (<code>list</code>, <em>optional</em>): | |
| Layout boxes, each {‘id’, ‘desc’, ‘from’, ‘src_bbox’, ‘tgt_bbox’} with the boxes as [y_min, x_min, y_max, | |
| x_max] in 0-1: ‘from’: ‘target’ with <code>tgt_bbox</code> adds an element there, ‘from’: ‘ref_image_0’, … with <code>src_bbox</code> and <code>tgt_bbox</code> moves one from a reference image. | |
| max_new_tokens (<code>int</code>, <em>optional</em>, defaults to 3584): | |
| The most tokens the upsampler may generate for the caption. | |
| negative_prompt (<code>str</code>, <em>optional</em>): | |
| The prompt not to guide the generation | |
| max_sequence_length (<code>int</code>, <em>optional</em>, defaults to 8192): | |
| Maximum number of prompt tokens; longer prompts are truncated. | |
| text_encoder_out_layers (<code>tuple</code>, <em>optional</em>, defaults to (4, 8, 12, 16, 20, 24, 28, 32)): | |
| Indices of the text-encoder hidden layers whose states are stacked to form the text embeddings | |
| num_images_per_prompt (<code>int</code>, <em>optional</em>, defaults to 1): | |
| The number of images to generate per prompt. | |
| image_cond_latents (<code>list</code>, <em>optional</em>): | |
| Normalized packed latents of the reference images, one tensor of shape (B, C, height_i//16, width_i//16) | |
| per image | |
| height (<code>int</code>, <em>optional</em>, defaults to None or 1024, depending on the workflow): | |
| The height in pixels of the generated image; defaults to the first reference image’s own height | |
| width (<code>int</code>, <em>optional</em>, defaults to None or 1024, depending on the workflow): | |
| The width in pixels of the generated image; defaults to the first reference image’s own width | |
| reference_crop (<code>list | NoneType</code>, <em>optional</em>): | |
| Per reference, the box of the reference inside its padded canvas or None, from the preprocess step | |
| latents (<code>Tensor</code>): | |
| Pre-generated noisy latents for image generation. | |
| generator (<code>Generator</code>, <em>optional</em>): | |
| Torch generator for deterministic generation. | |
| num_inference_steps (<code>int</code>): | |
| The number of denoising steps. | |
| timesteps (<code>Tensor</code>): | |
| Timesteps for the denoising process. (overrides <code>num_inference_steps</code> when provided) | |
| sigmas (<code>list</code>, <em>optional</em>): | |
| Custom sigmas for the denoising process. (overrides <code>num_inference_steps</code> when provided) | |
| *<em>denoiser_input_fields (<code>None</code>,</em>optional<em>): | |
| conditional model inputs for the denoiser: e.g. prompt_embeds, negative_prompt_embeds, etc. | |
| attention_kwargs (<code>dict</code>,</em>optional<em>): | |
| Additional kwargs for attention processors. | |
| output_type (<code>str</code>,</em>optional*, defaults to pil): | |
| Output format: ‘pil’, ‘np’, ‘pt’.</p> <p>Outputs: | |
| images (<code>list</code>): | |
| Generated images. | |
| latents (<code>Tensor</code>): | |
| Denoised latents.</p></div> <!--[1--><h2 class="relative group"><a id="diffusers.Flux3DistilledAutoBlocks" 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.Flux3DistilledAutoBlocks"><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>Flux3DistilledAutoBlocks</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.Flux3DistilledAutoBlocks"><!----><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">Flux3DistilledAutoBlocks</span></span></h3><!----> <a id="diffusers.Flux3DistilledAutoBlocks" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.Flux3DistilledAutoBlocks"><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><!----></a> <!--[0--><a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/diffusers/blob/vr_14737/src/diffusers/modular_pipelines/flux3/modular_blocks_flux3_distilled.py#L258" target="_blank"><span><</span> <span class="hidden md:block mx-0.5 hover:!underline">source</span> <span>></span></a><!--]--></span> <!--[0--><p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span>(</span> <!--[--><!--]--> <span>)</span> <!--[-1--><!--]--></p><!--]--> <div class="!mb-10 relative docstring-details "><!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--></div></div><!----> <p>Auto blocks that perform text-to-image and image-to-image generation using the step-distilled FLUX.3 model (16 | |
| steps, no classifier-free guidance). <code>prompt</code> goes through the prompt upsampler first; pop the <code>prompt_upsampler</code> step to encode it as given.</p> <p>Supported workflows:</p> <ul><li><code>text2image</code>: requires <code>prompt</code></li> <li><code>image_conditioned</code>: requires <code>prompt</code>, <code>image</code></li></ul> <p>Components: | |
| prompt_upsampler (<code>Qwen3_5ForConditionalGeneration</code>): The prompt upsampler. prompt_upsampler_processor | |
| (<code>AutoProcessor</code>): Its processor. text_encoder (<code>Qwen3VLForConditionalGeneration</code>) tokenizer | |
| (<code>AutoProcessor</code>) image_processor (<code>Flux3ImageProcessor</code>) vae (<code>AutoencoderKLFlux2</code>) transformer | |
| (<code>Flux3Transformer2DModel</code>) scheduler (<code>FlowMatchEulerDiscreteScheduler</code>)</p> <p>Inputs: | |
| prompt (<code>str</code>): | |
| The edit instruction to expand into the full caption (one per call). | |
| image (<code>Image | list</code>, <em>optional</em>): | |
| The reference image(s) of the edit, at most 10; the same ones the pipeline receives. | |
| boxes (<code>list</code>, <em>optional</em>): | |
| Layout boxes, each {‘id’, ‘desc’, ‘from’, ‘src_bbox’, ‘tgt_bbox’} with the boxes as [y_min, x_min, y_max, | |
| x_max] in 0-1: ‘from’: ‘target’ with <code>tgt_bbox</code> adds an element there, ‘from’: ‘ref_image_0’, … with <code>src_bbox</code> and <code>tgt_bbox</code> moves one from a reference image. | |
| max_new_tokens (<code>int</code>, <em>optional</em>, defaults to 3584): | |
| The most tokens the upsampler may generate for the caption. | |
| max_sequence_length (<code>int</code>, <em>optional</em>, defaults to 8192): | |
| Maximum number of prompt tokens; longer prompts are truncated. | |
| text_encoder_out_layers (<code>tuple</code>, <em>optional</em>, defaults to (4, 8, 12, 16, 20, 24, 28, 32)): | |
| Indices of the text-encoder hidden layers whose states are stacked to form the text embeddings | |
| num_images_per_prompt (<code>int</code>, <em>optional</em>, defaults to 1): | |
| The number of images to generate per prompt. | |
| image_cond_latents (<code>list</code>, <em>optional</em>): | |
| Normalized packed latents of the reference images, one tensor of shape (B, C, height_i//16, width_i//16) | |
| per image | |
| height (<code>int</code>, <em>optional</em>, defaults to None or 1024, depending on the workflow): | |
| The height in pixels of the generated image; defaults to the first reference image’s own height | |
| width (<code>int</code>, <em>optional</em>, defaults to None or 1024, depending on the workflow): | |
| The width in pixels of the generated image; defaults to the first reference image’s own width | |
| reference_crop (<code>list | NoneType</code>, <em>optional</em>): | |
| Per reference, the box of the reference inside its padded canvas or None, from the preprocess step | |
| latents (<code>Tensor</code>): | |
| Pre-generated noisy latents for image generation. | |
| generator (<code>Generator</code>, <em>optional</em>): | |
| Torch generator for deterministic generation. | |
| num_inference_steps (<code>int</code>): | |
| The number of denoising steps. | |
| timesteps (<code>Tensor</code>): | |
| Timesteps for the denoising process. (overrides <code>num_inference_steps</code> when provided) | |
| sigmas (<code>list</code>, <em>optional</em>): | |
| Custom sigmas for the denoising process. (overrides <code>num_inference_steps</code> when provided) | |
| *<em>denoiser_input_fields (<code>None</code>,</em>optional<em>): | |
| conditional model inputs for the denoiser: e.g. prompt_embeds, negative_prompt_embeds, etc. | |
| output_type (<code>str</code>,</em>optional*, defaults to pil): | |
| Output format: ‘pil’, ‘np’, ‘pt’.</p> <p>Outputs: | |
| images (<code>list</code>): | |
| Generated images. | |
| latents (<code>Tensor</code>): | |
| Denoised latents.</p></div> <!--[1--><h2 class="relative group"><a id="diffusers.Flux3DistilledModularPipeline" 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.Flux3DistilledModularPipeline"><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>Flux3DistilledModularPipeline</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.Flux3DistilledModularPipeline"><!----><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">Flux3DistilledModularPipeline</span></span></h3><!----> <a id="diffusers.Flux3DistilledModularPipeline" class="header-link invisible with-hover:group-hover:visible pr-2" href="#diffusers.Flux3DistilledModularPipeline"><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><!----></a> <!--[0--><a class="!ml-auto !text-gray-400 !no-underline text-sm flex items-center" href="https://github.com/huggingface/diffusers/blob/vr_14737/src/diffusers/modular_pipelines/flux3/modular_pipeline.py#L52" target="_blank"><span><</span> <span class="hidden md:block mx-0.5 hover:!underline">source</span> <span>></span></a><!--]--></span> <!--[0--><p class="font-mono text-xs md:text-sm !leading-relaxed !my-6"><span>(</span> <!--[--><span class="comma cursor-default"><span class="rounded hover:bg-black hover:text-white dark:hover:bg-white dark:hover:text-black">blocks<span class="opacity-60">: diffusers.modular_pipelines.modular_pipeline.ModularPipelineBlocks | None = None</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">pretrained_model_name_or_path<span class="opacity-60">: str | os.PathLike | None = None</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">components_manager<span class="opacity-60">: diffusers.modular_pipelines.components_manager.ComponentsManager | None = None</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">collection<span class="opacity-60">: str | None = None</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">workflow<span class="opacity-60">: str | None = None</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">modular_config_dict<span class="opacity-60">: dict[str, typing.Any] | None = None</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">config_dict<span class="opacity-60">: dict[str, typing.Any] | None = None</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">**kwargs<span class="opacity-60"></span></span></span><!--]--> <span>)</span> <!--[-1--><!--]--></p><!--]--> <div class="!mb-10 relative docstring-details "><!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--> <!--[-1--><!--]--></div></div><!----> <p>A ModularPipeline for the step-distilled FLUX.3 model (16 steps, no classifier-free guidance).</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/flux3.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_1eduo1r = { | |
| base: "/docs/diffusers/pr_14737/en", | |
| assets: "/docs/diffusers/pr_14737/en" | |
| }; | |
| const element = document.currentScript.parentElement; | |
| Promise.all([ | |
| import("/docs/diffusers/pr_14737/en/_app/immutable/entry/start.BsCWMOsu.js"), | |
| import("/docs/diffusers/pr_14737/en/_app/immutable/entry/app.BES-iAOI.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 170], | |
| data: [null,null], | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 95.3 kB
- Xet hash:
- 5289d0471690f3150e6e36ba28a5bf7a0f1a187fcc0baf1a452d761c1016afb6
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.