Buckets:
| <meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"FLUX 3 Image Klein","local":"flux-3-image-klein","sections":[{"title":"プロンプトのアップサンプリング","local":"prompt-upsampling","sections":[],"depth":2},{"title":"画像から画像へ","local":"image-to-image","sections":[],"depth":2},{"title":"レイアウトの制御","local":"layout-control","sections":[],"depth":2},{"title":"ガイダンススケール","local":"guidance-scale","sections":[],"depth":2},{"title":"ステップ蒸留モデル","local":"step-distilled-model","sections":[],"depth":2},{"title":"再現可能な生成","local":"reproducible-generation","sections":[],"depth":2},{"title":"ワークフロー","local":"workflows","sections":[],"depth":2},{"title":"ステップごとのコールバック","local":"per-step-callbacks","sections":[],"depth":2},{"title":"メモリ","local":"memory","sections":[],"depth":2},{"title":"単一ファイルの読み込み","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/main/en/_app/immutable/entry/start.U6TUchwJ.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/main/en/_app/immutable/chunks/yxSHiGDF.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/main/en/_app/immutable/chunks/CPfOwUO_.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/main/en/_app/immutable/entry/app.3qKhPoX-.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/main/en/_app/immutable/chunks/BYe-f74j.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/main/en/_app/immutable/chunks/DnVIJfC5.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/main/en/_app/immutable/chunks/DsnmJJEf.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/main/en/_app/immutable/chunks/D32hXVzh.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/main/en/_app/immutable/nodes/0.DqpuBF3n.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/main/en/_app/immutable/chunks/Dyp9xKq8.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/main/en/_app/immutable/nodes/8.AKHyGgGH.js" rel="modulepreload"> | |
| <link href="/docs/diffusers/main/en/_app/immutable/chunks/Dk44y1gU.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/main/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 は、Black Forest Labs による 5.6B パラメータの画像生成モデルです。単一の Transformer（<a href="/docs/diffusers/main/ja/api/models/flux3_transformer#diffusers.Flux3Transformer2DModel">Flux3Transformer2DModel</a>）が、テキストプロンプトから、単独または 1 つ以上の参照画像と組み合わせて画像を生成します。テキストの条件付けは Qwen3-VL から取得され、画像には FLUX.2 packed autoencoder（<code>AutoencoderKLFlux2</code>）が使用されます。</p> <p>FLUX 3 Image Klein は <a href="../../modular_diffusers/overview">モジュール型パイプライン</a>として提供されています。テキストから画像を生成する処理から始めましょう:</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> コピーしました</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> は唯一必須の入力です。パイプラインは推奨されるサンプリング設定（ステップ数 50、guidance scale 3.5、scheduler shift 6.93）を保持し、デフォルトでは 1024 x 1024 の画像を生成します。1 回の呼び出しにつき 1 つのプロンプトを受け取ります。同じプロンプトで複数の画像を生成するには、<code>num_images_per_prompt</code> を使用してください。</p> <p>上記の例に示すように、<code>DiffusionPipeline</code> とは少し異なります。読み込みは遅延実行です。<a href="/docs/diffusers/main/ja/api/modular_diffusers/pipeline#diffusers.ModularPipeline.from_pretrained">from_pretrained()</a> はパイプラインを構築するだけで、重みの読み込みには <a href="/docs/diffusers/main/ja/api/modular_diffusers/pipeline#diffusers.ModularPipeline.load_components">load_components()</a> を呼び出します。呼び出しはパイプラインの状態を返し、<code>output</code> で必要なものを指定します。ここでは <code>output="images"</code> ですが、プロンプトアップサンプラーが生成したキャプションも取得するには <code>output=["images", "prompt"]</code> とします。</p> <blockquote class="tip"><p><code>ModularPipeline</code> を初めて扱う場合は、<a href="../../modular_diffusers/quickstart">クイックスタート</a>をお読みください。標準的なパイプラインに精通している場合は、<a href="../../modular_diffusers/coming_from_diffusion_pipeline">DiffusionPipelineからの移行</a>も参照してください。読み込みと出力のほかに、<a href="#guidance-scale">ガイダンス</a>、<a href="#per-step-callbacks">コールバック</a>、<a href="#memory">オフローディング</a>の3点についても、動作が異なります。</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><!---->プロンプトのアップサンプリング<!----></span></h2><!--]--><!----> <p>プロンプトの重要性: FLUX 3 Image Klein は、短いプロンプトではなく、被写体、構図、ライティング、雰囲気を記述した完全なシーンキャプションを要求します。そのまま入力された短いリクエストでは、汎用的な出力しか得られません。そのため、このパイプラインでは、テキストから画像生成や編集を問わず、すべてのリクエストに対して最初にプロンプトアップサンプラーを実行します。これは Black Forest Labs による別個の 9B モデル (<a href="https://huggingface.co/black-forest-labs/flux-3-image-klein-pup" rel="nofollow">black-forest-labs/flux-3-image-klein-pup</a>) で、テキストエンコーダーに渡す前に <code>prompt</code> をそのようなキャプションに拡張します。したがって、短いプロンプトを入力するだけで十分です。</p> <p>プロンプトアップサマーは、短いリクエストと、編集時の参照画像を、モデルが受け取る完全なシーンキャプションに変換します。キャプションには、ミディアムとスタイル、シーン、ライティングとカメラ、各被写体の色・素材・フレーム内での位置が含まれます。1つのモデルで、テキストから画像への生成、参照画像を用いた編集、ボックスを用いたレイアウトに対応します。生成されたキャプションは<code>prompt</code>出力として返されます。上記の例では、画像と一緒にリクエストすることで、画像モデルが受け取った内容を確認できます。</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> コピーしました</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> コピーしました</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>キャプション全体は約240語に及びます。<code>max_new_tokens</code>はキャプションの長さを制限します（デフォルト値は3584）。</p> <p>ステップの<code>doc</code>を出力すると、そのステップが受け取る引数と書き出す内容を確認できます。</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> コピーしました</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> コピーしました</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>パイプラインの他のブロックと同様に、<code>prompt_upsampler</code>ブロックも単独で実行されます。推奨される方法は、ブロックからこれをポップアウトすることです。ポップアウトされたブロックはスタンドアロンのアップサンプラーとなり、残りのブロックは、拡張されたキャプションを<code>prompt</code>として受け取るパイプラインになります。</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> コピーしました</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>この方式により、アップサマーを独立したステージとして提供でき、専用の GPU を使用したり、専用のエンドポイントの背後に配置したりできます。また、UI ではアップサマーが生成したキャプションを表示し、生成前にユーザーが編集できるようにできます。アップサマーの代わりに他の LLM を使用することも可能で、システムプロンプトは同じです。アップサマーのリポジトリから<code>system_prompts["t2i"]</code>（または、ユーザーメッセージの先頭に参照画像を配置した<code>"i2i"</code>）をシステムプロンプトとして、リクエストをユーザーメッセージとして渡します。そして、LLM が返したキャプションを<code>prompt</code>として<code>pipe</code>に渡します。</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><!---->画像から画像へ<!----></span></h2><!--]--><!----> <p><code>image</code> に1枚以上の参照画像を渡します。参照が1枚の場合は、4メガピクセルを超える場合のみ縮小され、16ピクセルのグリッドにパディングされ、生成サイズはデフォルトでそのサイズに設定されるため、編集結果は入力と同じサイズで返されます。参照が複数ある場合は、それぞれ1メガピクセル以下に調整され、グリッドに合わせてクロップされ、生成サイズはデフォルトで最初の参照のサイズに設定されます。指定された<code>height</code>/<code>width</code>がデフォルトを上書きします。<em>ターゲット</em>画像は、1行の指示ではなく、編集内容を組み込んだ参照画像の完全なキャプションとして記述するか、<a href="#prompt-upsampling">プロンプトアップサンプラー</a>に指示と参照から記述させます:</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> コピーしました</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>複数の参照画像がある場合は、<code>image</code> に渡された順序に従って、1枚目の画像、2枚目の画像、…と呼びます。キャプションでは、画像モデルに対して <code><ref_image_0></code>、<code><ref_image_1></code>、… と呼びます。</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> コピーしました</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><code>height</code> および/または <code>width</code> を渡すことで、導出されたサイズを上書きできます。</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><!---->レイアウトの制御<!----></span></h2><!--]--><!----> <p>コンテンツを明示的に配置するには、<code>boxes</code> を渡します。各要素について、<code>id</code>、短い <code>desc</code>、および 0〜1 の範囲で左上を原点とする <code>bbox</code>（<code>[y_min, x_min, y_max, x_max]</code>）を指定します。これにより、出力サイズに依存しないようになります。アップサンプラーはそれらの周囲にキャプションを書き込み、各要素を <code><id></code> として参照し、ボックスの表を末尾に追加します。指定したボックスはそのまま保持されます。</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> コピーしました</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>編集時、ボックスは<code>from</code>によってソースを指定します。<code>"target"</code>に<code>tgt_bbox</code>を指定すると、そこに新しい要素が追加され、<code>"ref_image_0"</code>に<code>src_bbox</code>と<code>tgt_bbox</code>を指定すると、その参照画像の要素が移動します（ボックスが同じ場合は、その場で保持されます）。</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> コピーしました</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>画像モデルが読み取るキャプションには、テキスト内の要素が<code><id></code>でタグ付けされ、テーブルがJSON形式で付加されています。ボックスは0〜1000のキャンバス上に配置されます。<code>prompt</code>の出力を表示すると、その内容を確認できます。手動でその形式で記述されたキャプションは、<a href="#prompt-upsampling">Prompt upsampling</a>と同様に、このステップなしでパイプラインに渡されます。</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><!---->ガイダンススケール<!----></span></h2><!--]--><!----> <p>パイプラインは<code>guider</code>コンポーネントを介してclassifier-free guidanceを適用し、呼び出し時に<code>guidance_scale</code>引数を受け取りません。デフォルトのguiderは<code>guidance_scale=3.5</code>の<a href="/docs/diffusers/main/ja/api/modular_diffusers/guiders#diffusers.ClassifierFreeGuidance">ClassifierFreeGuidance</a>であり、これは両方のワークフローに推奨される設定です。変更するには、guiderの更新されたコピーを作成します。</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> コピーしました</div><!----></button><!----></div> <pre class="language-python "><!---->pipe.guider = pipe.guider.new(guidance_scale=<span class="hljs-number">5.0</span>)<!----></pre></div><!----> <p>別のガイダンス手法に切り替えるには、<a href="../../using-diffusers/guiders">ガイダーのガイド</a>を参照してください。</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><!---->ステップ蒸留モデル<!----></span></h2><!--]--><!----> <p>ステップ蒸留されたチェックポイントは、classifier-free guidance なしで 16 ステップで生成します。その transformer は flow map であり、各ステップで現在のタイムステップと、そのステップがジャンプ先とするタイムステップが与えられます。ベースモデルと同様にロードされます（リポジトリの <code>modular_model_index.json</code> は <a href="/docs/diffusers/main/ja/api/pipelines/flux3#diffusers.Flux3DistilledModularPipeline">Flux3DistilledModularPipeline</a> と <a href="/docs/diffusers/main/ja/api/pipelines/flux3#diffusers.Flux3DistilledAutoBlocks">Flux3DistilledAutoBlocks</a> に解決されます）。このパイプラインには <code>guider</code> がなく、<code>negative_prompt</code> を受け取りません。</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> コピーしました</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>ベースモデルと同様に、2つのワークフローに対応しています。<code>num_inference_steps</code>のデフォルト値は16です。モデルは4ステップから16ステップで学習されています。</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><!---->再現可能な生成<!----></span></h2><!--]--><!----> <p><code>generator</code> は、パイプラインがサンプリングするノイズを固定します（<a href="../../using-diffusers/reusing_seeds">再現性</a>を参照）。他の場所でサンプリングしたノイズを再利用するには、<code>latents</code> として、形状が <code>(batch_size, 128, height // 16, width // 16)</code> のテンソルを渡します。例えば、<a href="https://github.com/black-forest-labs/flux-3-image-klein" rel="nofollow">BFL の実装</a> では、CPU 上でノイズを画像トークンとしてサンプリングし、bf16 にキャストしています。これにより、指定されたシードに対するサンプルを再現できます。</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> コピーしました</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><!---->ワークフロー<!----></span></h2><!--]--><!----> <p>パイプラインは <code>text2image</code> と <code>image_conditioned</code> の2つのワークフローに対応しています。実行されるワークフローは入力によって選択され、<code>image</code> が指定されると image-to-image が選択されます。<a href="/docs/diffusers/main/ja/api/modular_diffusers/pipeline#diffusers.ModularPipeline.from_pretrained">from_pretrained()</a> は <code>workflow</code> 引数を用いることで、特定のワークフロー用のパイプラインを構築することもできます。この場合、そのワークフローに必要なコンポーネントのみが期待され、読み込まれます。</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> コピーしました</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><!---->ステップごとのコールバック<!----></span></h2><!--]--><!----> <p>既存のコールバック関数を使用するには、デノイジングループにブロックを挿入します。<a href="../../using-diffusers/callback#modular-pipelines">コールバックのガイド</a>には、<code>CallbackOnStepEnd</code>ブロックと<code>walk_denoise_loops</code>ヘルパーを使ったシンプルな例が記載されています。</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> コピーしました</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>早期に停止するには、コールバックから例外を送出します。<code>interrupt</code> フラグはありません。</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><!---->メモリ<!----></span></h2><!--]--><!----> <p>bf16 ですべてを読み込むと、重みのサイズは約 39 GB になります。transformer は 5.5B パラメータ、Qwen3-VL-4B テキストエンコーダーは 4B、<a href="#prompt-upsampling">prompt upsampler</a> は 9B（単体で約 19 GB）であり、画像 VAE は fp32 で読み込まれます。upsampler ステップなしで構築されたパイプライン（詳細はそちらを参照）は、約 20 GB を読み込みます。メモリが少ない GPU を使用する場合、コンポーネントのオフローディングを有効にしてください。マネージャーは、各ステップの必要に応じてコンポーネントを CPU と GPU の間で移動します。upsampler も含みます。</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> コピーしました</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><!---->単一ファイルの読み込み<!----></span></h2><!--]--><!----> <p><a href="/docs/diffusers/main/ja/api/models/flux3_transformer#diffusers.Flux3Transformer2DModel">Flux3Transformer2DModel</a> は、<a href="/docs/diffusers/main/ja/api/loaders/single_file#diffusers.loaders.FromOriginalModelMixin.from_single_file">from_single_file()</a> を使用して、Black Forest Labs のモデルパッケージから transformer を直接読み込みます。パッケージ内の <code>config.json</code> は読み込まれないため、diffusers の設定を <code>config</code> と <code>subfolder</code> で渡してください。</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> コピーしました</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>まず、他のコンポーネントを名前によって読み込みます: <code>names</code> を指定せずに <a href="/docs/diffusers/main/ja/api/modular_diffusers/pipeline#diffusers.ModularPipeline.load_components">load_components()</a> を呼び出すと、パイプラインのリポジトリから transformer も読み込まれてしまいます。</p> <p>FP8rおよびNVFP4の単一ファイルチェックポイントの読み込みもサポートされています。両方とも、<a href="/docs/diffusers/main/ja/api/quantization#diffusers.BFLQuantizationConfig">BFLQuantizationConfig</a>を指定して同じ呼び出しで読み込みます。各スキームのカーネル要件については、<a href="../../quantization/bfl">BFL量子化ガイド</a>を参照してください。</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> コピーしました</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>ステップ蒸留されたチェックポイントを読み込む際は、その設定（<code>flow_map=True</code>）が必要です。</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> コピーしました</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/main/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>FLUX.3用のModularPipeline。</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/main/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>FLUX.3 を使用してテキストから画像、および画像から画像の生成を行う Auto ブロックです。<code>prompt</code> はまずプロンプトアップサマーを通過します。<code>prompt_upsampler</code> ステップを削除すると、指定されたままエンコードされます。</p> <p>サポートされているワークフロー:</p> <ul><li><code>text2image</code>: <code>prompt</code> が必要です</li> <li><code>image_conditioned</code>: <code>prompt</code>と<code>image</code>が必要です</li></ul> <p>コンポーネント: | |
| prompt_upsampler (<code>Qwen3_5ForConditionalGeneration</code>): プロンプトアップサンプラー。prompt_upsampler_processor | |
| (<code>AutoProcessor</code>): そのプロセッサー。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>): | |
| 完全なキャプションに展開するための編集指示（1回の呼び出しにつき1つ）。 | |
| image (<code>Image | list</code>, <em>任意</em>): | |
| 編集の参照画像（最大10枚）。パイプラインが受け取るものと同じです。 | |
| boxes (<code>list</code>, <em>任意</em>): | |
| レイアウトボックス。各要素は {‘id’, ‘desc’, ‘from’, ‘src_bbox’, ‘tgt_bbox’} の形式で、ボックスは 0-1 の範囲で [y_min, x_min, y_max, x_max] として指定します。‘from’: ‘target’ で <code>tgt_bbox</code> を指定すると、その位置に要素を追加します。‘from’: ‘ref_image_0’, … で <code>src_bbox</code> と <code>tgt_bbox</code> を指定すると、参照画像から要素を移動します。 | |
| max_new_tokens (<code>int</code>, <em>任意</em>, デフォルトは 3584): | |
| キャプションの生成において、アップサンプラーが生成し得る最大トークン数。 | |
| negative_prompt (<code>str</code>, <em>任意</em>): | |
| 生成を導かないためのプロンプト。 | |
| max_sequence_length (<code>int</code>, <em>任意</em>, デフォルトは 8192): | |
| プロンプトの最大トークン数。これを超えるプロンプトは切り詰められます。 | |
| text_encoder_out_layers (<code>tuple</code>, <em>任意</em>, デフォルトは (4, 8, 12, 16, 20, 24, 28, 32)): | |
| テキストエンコーダーの隠れ層のインデックス。これらの状態をスタックしてテキスト埋め込みを形成します。 | |
| num_images_per_prompt (<code>int</code>, <em>任意</em>, デフォルトは 1): | |
| プロンプトごとに生成する画像の数。 | |
| image_cond_latents (<code>list</code>, <em>任意</em>): | |
| 参照画像の正規化されたパックされた潜在変数。画像ごとに1つのテンソルで、形状は (B, C, height_i//16, width_i//16) です。 | |
| height (<code>int</code>, <em>任意</em>, ワークフローによってデフォルトは None または 1024): | |
| 生成画像の高さ（ピクセル単位）。デフォルトでは、最初の参照画像の高さになります。 | |
| width (<code>int</code>, <em>任意</em>, ワークフローによってデフォルトは None または 1024): | |
| 生成画像の幅（ピクセル単位）。デフォルトでは、最初の参照画像の幅になります。 | |
| reference_crop (<code>list | NoneType</code>, <em>任意</em>): | |
| 各参照について、パディングされたキャンバス内の参照のボックス、または None。前処理ステップから取得します。 | |
| latents (<code>Tensor</code>): | |
| 画像生成用の事前生成されたノイズ付き潜在変数。 | |
| generator (<code>Generator</code>, <em>任意</em>): | |
| 決定論的な生成のための Torch ジェネレーター。 | |
| num_inference_steps (<code>int</code>): | |
| ノイズ除去ステップの数。 | |
| timesteps (<code>Tensor</code>): | |
| ノイズ除去プロセス用のタイムステップ。（指定された場合、<code>num_inference_steps</code> を上書きします） | |
| sigmas (<code>list</code>, <em>任意</em>): | |
| ノイズ除去プロセス用のカスタムシグマ。（指定された場合、<code>num_inference_steps</code> を上書きします） | |
| *<em>denoiser_input_fields (<code>None</code>,</em>任意<em>): | |
| デノイザー用の条件付きモデル入力。例: prompt_embeds, negative_prompt_embeds など。 | |
| attention_kwargs (<code>dict</code>,</em>任意<em>): | |
| アテンションプロセッサー用の追加の kwargs。 | |
| output_type (<code>str</code>,</em>任意*, デフォルトは pil): | |
| 出力形式: ‘pil’, ‘np’, ‘pt’。</p> <p>出力: | |
| images (<code>list</code>): | |
| 生成された画像。 | |
| latents (<code>Tensor</code>): | |
| ノイズ除去された潜在変数。</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/main/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>ステップ蒸留された FLUX.3 モデル（16 ステップ、classifier-free guidance なし）を使用して、テキストから画像および画像から画像の生成を行う Auto ブロックです。<code>prompt</code> はまずプロンプトアップサマーを通過します。<code>prompt_upsampler</code> ステップを削除すると、指定されたままエンコードされます。</p> <p>サポートされているワークフロー:</p> <ul><li><code>text2image</code>: <code>prompt</code> が必要です</li> <li><code>image_conditioned</code>: <code>prompt</code>と<code>image</code>が必要です</li></ul> <p>コンポーネント: | |
| prompt_upsampler (<code>Qwen3_5ForConditionalGeneration</code>): プロンプトアップサンプラー。 prompt_upsampler_processor | |
| (<code>AutoProcessor</code>): そのプロセッサー。 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>): | |
| 完全なキャプションに展開するための編集指示（1回の呼び出しにつき1つ）。 | |
| image (<code>Image | list</code>, <em>任意</em>): | |
| 編集の参照画像（最大10枚）。パイプラインが受け取るものと同じです。 | |
| boxes (<code>list</code>, <em>任意</em>): | |
| レイアウトボックス。各要素は {‘id’, ‘desc’, ‘from’, ‘src_bbox’, ‘tgt_bbox’} を持ち、ボックスは 0-1 の範囲で [y_min, x_min, y_max, x_max] で指定します。‘from’: ‘target’ で <code>tgt_bbox</code> を指定すると、その位置に要素を追加します。‘from’: ‘ref_image_0’, … で <code>src_bbox</code> と <code>tgt_bbox</code> を指定すると、参照画像から要素を移動します。 | |
| max_new_tokens (<code>int</code>, <em>任意</em>, デフォルトは 3584): | |
| キャプションの生成において、アップサンプラーが生成し得る最大トークン数。 | |
| max_sequence_length (<code>int</code>, <em>任意</em>, デフォルトは 8192): | |
| プロンプトの最大トークン数。これを超えるプロンプトは切り詰められます。 | |
| text_encoder_out_layers (<code>tuple</code>, <em>任意</em>, デフォルトは (4, 8, 12, 16, 20, 24, 28, 32)): | |
| テキストエンコーダーの隠れ層のインデックス。これらの状態をスタックしてテキスト埋め込みを形成します。 | |
| num_images_per_prompt (<code>int</code>, <em>任意</em>, デフォルトは 1): | |
| プロンプトごとに生成する画像の数。 | |
| image_cond_latents (<code>list</code>, <em>任意</em>): | |
| 参照画像の正規化済みパックされた潜在変数。画像ごとに1つのテンソルで、形状は (B, C, height_i//16, width_i//16) です。 | |
| height (<code>int</code>, <em>任意</em>, ワークフローに応じてデフォルトは None または 1024): | |
| 生成画像の高さ（ピクセル単位）。デフォルトでは、最初の参照画像の高さになります。 | |
| width (<code>int</code>, <em>任意</em>, ワークフローに応じてデフォルトは None または 1024): | |
| 生成画像の幅（ピクセル単位）。デフォルトでは、最初の参照画像の幅になります。 | |
| reference_crop (<code>list | NoneType</code>, <em>任意</em>): | |
| 各参照について、パディング済みキャンバス内の参照のボックス、または None。前処理ステップから取得します。 | |
| latents (<code>Tensor</code>): | |
| 画像生成用の事前生成されたノイズ付き潜在変数。 | |
| generator (<code>Generator</code>, <em>任意</em>): | |
| 決定論的な生成のための Torch ジェネレーター。 | |
| num_inference_steps (<code>int</code>): | |
| ノイズ除去ステップの数。 | |
| timesteps (<code>Tensor</code>): | |
| ノイズ除去プロセス用のタイムステップ。（指定された場合、<code>num_inference_steps</code> を上書きします） | |
| sigmas (<code>list</code>, <em>任意</em>): | |
| ノイズ除去プロセス用のカスタムシグマ。（指定された場合、<code>num_inference_steps</code> を上書きします） | |
| *<em>denoiser_input_fields (<code>None</code>,</em>optional<em>): | |
| デノイザー用の条件付きモデル入力。例: prompt_embeds, negative_prompt_embeds など。 | |
| output_type (<code>str</code>,</em>optional*, デフォルトは pil): | |
| 出力形式: ‘pil’, ‘np’, ‘pt’。</p> <p>出力: | |
| images (<code>list</code>): | |
| 生成された画像。 | |
| latents (<code>Tensor</code>): | |
| ノイズ除去された潜在変数。</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">クラス</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/main/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>ステップ蒸留された FLUX.3 モデル（16 ステップ、classifier-free guidance なし）用の ModularPipeline です。</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_gxjg5b = { | |
| base: "/docs/diffusers/main/en", | |
| assets: "/docs/diffusers/main/en" | |
| }; | |
| const element = document.currentScript.parentElement; | |
| Promise.all([ | |
| import("/docs/diffusers/main/en/_app/immutable/entry/start.U6TUchwJ.js"), | |
| import("/docs/diffusers/main/en/_app/immutable/entry/app.3qKhPoX-.js") | |
| ]).then(([kit, app]) => { | |
| kit.start(app, element, { | |
| node_ids: [0, 8], | |
| data: [null,null], | |
| form: null, | |
| error: null | |
| }); | |
| }); | |
| } | |
| </script> | |
Xet Storage Details
- Size:
- 102 kB
- Xet hash:
- eb76b4346a042d5b7df5b37ae6e2e9b7c7a9bcdc0bb17a6c5fab78fe40107ed3
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.