Buckets:

hf-doc-build
/

doc

Files

xet

hf-doc-build/doc / diffusers /v0.22.2 /ja /index.html

rtrm

27 days ago

download

raw

20.7 kB

	<meta charset="utf-8" /><meta name="hf:doc:metadata" content="{"title":"Diffusers","local":"diffusers","sections":[{"title":"Supported pipelines","local":"supported-pipelines","sections":[],"depth":2}],"depth":1}">
	<link href="/docs/diffusers/v0.22.2/ja/_app/immutable/assets/0.e3b0c442.css" rel="modulepreload">
	<link rel="modulepreload" href="/docs/diffusers/v0.22.2/ja/_app/immutable/entry/start.098f23e4.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.22.2/ja/_app/immutable/chunks/scheduler.d586627e.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.22.2/ja/_app/immutable/chunks/singletons.cfca712d.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.22.2/ja/_app/immutable/chunks/index.b0d7e1f3.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.22.2/ja/_app/immutable/chunks/paths.6bd102b2.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.22.2/ja/_app/immutable/entry/app.d9663000.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.22.2/ja/_app/immutable/chunks/index.8589a59c.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.22.2/ja/_app/immutable/nodes/0.8462433c.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.22.2/ja/_app/immutable/chunks/each.e59479a4.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.22.2/ja/_app/immutable/nodes/2.7b9cf6ec.js">
	<link rel="modulepreload" href="/docs/diffusers/v0.22.2/ja/_app/immutable/chunks/Heading.a70e045b.js"><!-- HEAD_svelte-u9bgzb_START --><meta name="hf:doc:metadata" content="{"title":"Diffusers","local":"diffusers","sections":[{"title":"Supported pipelines","local":"supported-pipelines","sections":[],"depth":2}],"depth":1}"><!-- HEAD_svelte-u9bgzb_END --> <p></p> <p align="center" data-svelte-h="svelte-aksdn0"><br> <img src="https://raw.githubusercontent.com/huggingface/diffusers/77aadfee6a891ab9fcfb780f87c693f7a5beeb8e/docs/source/imgs/diffusers_library.jpg" width="400"> <br></p> <h1 class="relative group"><a id="diffusers" 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"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Diffusers</span></h1> <p data-svelte-h="svelte-qtkxl1">🤗 Diffusers は、画像や音声、さらには分子の3D構造を生成するための、最先端の事前学習済みDiffusion Model(拡散モデル)を提供するライブラリです。シンプルな生成ソリューションをお探しの場合でも、独自の拡散モデルをトレーニングしたい場合でも、🤗 Diffusers はその両方をサポートするモジュール式のツールボックスです。我々のライブラリは、<a href="conceptual/philosophy#usability-over-performance">性能より使いやすさ</a>、<a href="conceptual/philosophy#simple-over-easy">簡単よりシンプル</a>、<a href="conceptual/philosophy#tweakable-contributorfriendly-over-abstraction">抽象化よりカスタマイズ性</a>に重点を置いて設計されています。</p> <p data-svelte-h="svelte-19opv9q">このライブラリには3つの主要コンポーネントがあります:</p> <ul data-svelte-h="svelte-1ue18ti"><li>最先端の<a href="api/pipelines/overview">拡散パイプライン</a>で数行のコードで生成が可能です。</li> <li>交換可能な<a href="api/schedulers/overview">ノイズスケジューラ</a>で生成速度と品質のトレードオフのバランスをとれます。</li> <li>事前に訓練された<a href="api/models">モデル</a>は、ビルディングブロックとして使用することができ、スケジューラと組み合わせることで、独自のエンドツーエンドの拡散システムを作成することができます。</li></ul> <div class="mt-10" data-svelte-h="svelte-1jtsp4b"><div class="w-full flex flex-col space-y-4 md:space-y-0 md:grid md:grid-cols-2 md:gap-y-4 md:gap-x-5"><a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./tutorials/tutorial_overview"><div class="w-full text-center bg-gradient-to-br from-blue-400 to-blue-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">チュートリアル</div> <p class="text-gray-700">出力の生成、独自の拡散システムの構築、拡散モデルのトレーニングを開始するために必要な基本的なスキルを学ぶことができます。初めて🤗Diffusersを使用する場合は、ここから始めることをお勧めします！</p></a> <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./using-diffusers/loading_overview"><div class="w-full text-center bg-gradient-to-br from-indigo-400 to-indigo-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">ガイド</div> <p class="text-gray-700">パイプライン、モデル、スケジューラのロードに役立つ実践的なガイドです。また、特定のタスクにパイプラインを使用する方法、出力の生成方法を制御する方法、生成速度を最適化する方法、さまざまなトレーニング手法についても学ぶことができます。</p></a> <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./conceptual/philosophy"><div class="w-full text-center bg-gradient-to-br from-pink-400 to-pink-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">Conceptual guides</div> <p class="text-gray-700">ライブラリがなぜこのように設計されたのかを理解し、ライブラリを利用する際の倫理的ガイドラインや安全対策について詳しく学べます。</p></a> <a class="!no-underline border dark:border-gray-700 p-5 rounded-lg shadow hover:shadow-lg" href="./api/models/overview"><div class="w-full text-center bg-gradient-to-br from-purple-400 to-purple-500 rounded-lg py-1.5 font-semibold mb-5 text-white text-lg leading-relaxed">Reference</div> <p class="text-gray-700">🤗 Diffusersのクラスとメソッドがどのように機能するかについての技術的な説明です。</p></a></div></div> <h2 class="relative group"><a id="supported-pipelines" class="header-link block pr-1.5 text-lg no-hover:hidden with-hover:absolute with-hover:p-1.5 with-hover:opacity-0 with-hover:group-hover:opacity-100 with-hover:right-full" href="#supported-pipelines"><span><svg class="" xmlns="http://www.w3.org/2000/svg" xmlns:xlink="http://www.w3.org/1999/xlink" aria-hidden="true" role="img" width="1em" height="1em" preserveAspectRatio="xMidYMid meet" viewBox="0 0 256 256"><path d="M167.594 88.393a8.001 8.001 0 0 1 0 11.314l-67.882 67.882a8 8 0 1 1-11.314-11.315l67.882-67.881a8.003 8.003 0 0 1 11.314 0zm-28.287 84.86l-28.284 28.284a40 40 0 0 1-56.567-56.567l28.284-28.284a8 8 0 0 0-11.315-11.315l-28.284 28.284a56 56 0 0 0 79.196 79.197l28.285-28.285a8 8 0 1 0-11.315-11.314zM212.852 43.14a56.002 56.002 0 0 0-79.196 0l-28.284 28.284a8 8 0 1 0 11.314 11.314l28.284-28.284a40 40 0 0 1 56.568 56.567l-28.285 28.285a8 8 0 0 0 11.315 11.314l28.284-28.284a56.065 56.065 0 0 0 0-79.196z" fill="currentColor"></path></svg></span></a> <span>Supported pipelines</span></h2> <table data-svelte-h="svelte-op06al"><thead><tr><th>Pipeline</th> <th>Paper/Repository</th> <th align="center">Tasks</th></tr></thead> <tbody><tr><td><a href="./api/pipelines/alt_diffusion">alt_diffusion</a></td> <td><a href="https://arxiv.org/abs/2211.06679" rel="nofollow">AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities</a></td> <td align="center">Image-to-Image Text-Guided Generation</td></tr> <tr><td><a href="./api/pipelines/audio_diffusion">audio_diffusion</a></td> <td><a href="https://github.com/teticio/audio-diffusion.git" rel="nofollow">Audio Diffusion</a></td> <td align="center">Unconditional Audio Generation</td></tr> <tr><td><a href="./api/pipelines/controlnet">controlnet</a></td> <td><a href="https://arxiv.org/abs/2302.05543" rel="nofollow">Adding Conditional Control to Text-to-Image Diffusion Models</a></td> <td align="center">Image-to-Image Text-Guided Generation</td></tr> <tr><td><a href="./api/pipelines/cycle_diffusion">cycle_diffusion</a></td> <td><a href="https://arxiv.org/abs/2210.05559" rel="nofollow">Unifying Diffusion Models’ Latent Space, with Applications to CycleDiffusion and Guidance</a></td> <td align="center">Image-to-Image Text-Guided Generation</td></tr> <tr><td><a href="./api/pipelines/dance_diffusion">dance_diffusion</a></td> <td><a href="https://github.com/williamberman/diffusers.git" rel="nofollow">Dance Diffusion</a></td> <td align="center">Unconditional Audio Generation</td></tr> <tr><td><a href="./api/pipelines/ddpm">ddpm</a></td> <td><a href="https://arxiv.org/abs/2006.11239" rel="nofollow">Denoising Diffusion Probabilistic Models</a></td> <td align="center">Unconditional Image Generation</td></tr> <tr><td><a href="./api/pipelines/ddim">ddim</a></td> <td><a href="https://arxiv.org/abs/2010.02502" rel="nofollow">Denoising Diffusion Implicit Models</a></td> <td align="center">Unconditional Image Generation</td></tr> <tr><td><a href="./if">if</a></td> <td><a href="./api/pipelines/if"><strong>IF</strong></a></td> <td align="center">Image Generation</td></tr> <tr><td><a href="./if">if_img2img</a></td> <td><a href="./api/pipelines/if"><strong>IF</strong></a></td> <td align="center">Image-to-Image Generation</td></tr> <tr><td><a href="./if">if_inpainting</a></td> <td><a href="./api/pipelines/if"><strong>IF</strong></a></td> <td align="center">Image-to-Image Generation</td></tr> <tr><td><a href="./api/pipelines/latent_diffusion">latent_diffusion</a></td> <td><a href="https://arxiv.org/abs/2112.10752" rel="nofollow">High-Resolution Image Synthesis with Latent Diffusion Models</a></td> <td align="center">Text-to-Image Generation</td></tr> <tr><td><a href="./api/pipelines/latent_diffusion">latent_diffusion</a></td> <td><a href="https://arxiv.org/abs/2112.10752" rel="nofollow">High-Resolution Image Synthesis with Latent Diffusion Models</a></td> <td align="center">Super Resolution Image-to-Image</td></tr> <tr><td><a href="./api/pipelines/latent_diffusion_uncond">latent_diffusion_uncond</a></td> <td><a href="https://arxiv.org/abs/2112.10752" rel="nofollow">High-Resolution Image Synthesis with Latent Diffusion Models</a></td> <td align="center">Unconditional Image Generation</td></tr> <tr><td><a href="./api/pipelines/paint_by_example">paint_by_example</a></td> <td><a href="https://arxiv.org/abs/2211.13227" rel="nofollow">Paint by Example: Exemplar-based Image Editing with Diffusion Models</a></td> <td align="center">Image-Guided Image Inpainting</td></tr> <tr><td><a href="./api/pipelines/pndm">pndm</a></td> <td><a href="https://arxiv.org/abs/2202.09778" rel="nofollow">Pseudo Numerical Methods for Diffusion Models on Manifolds</a></td> <td align="center">Unconditional Image Generation</td></tr> <tr><td><a href="./api/pipelines/score_sde_ve">score_sde_ve</a></td> <td><a href="https://openreview.net/forum?id=PxTIG12RRHS" rel="nofollow">Score-Based Generative Modeling through Stochastic Differential Equations</a></td> <td align="center">Unconditional Image Generation</td></tr> <tr><td><a href="./api/pipelines/score_sde_vp">score_sde_vp</a></td> <td><a href="https://openreview.net/forum?id=PxTIG12RRHS" rel="nofollow">Score-Based Generative Modeling through Stochastic Differential Equations</a></td> <td align="center">Unconditional Image Generation</td></tr> <tr><td><a href="./api/pipelines/semantic_stable_diffusion">semantic_stable_diffusion</a></td> <td><a href="https://arxiv.org/abs/2301.12247" rel="nofollow">Semantic Guidance</a></td> <td align="center">Text-Guided Generation</td></tr> <tr><td><a href="./api/pipelines/stable_diffusion/adapter">stable_diffusion_adapter</a></td> <td><a href="https://arxiv.org/abs/2302.08453" rel="nofollow"><strong>T2I-Adapter</strong></a></td> <td align="center">Image-to-Image Text-Guided Generation</td></tr> <tr><td><a href="./api/pipelines/stable_diffusion/text2img">stable_diffusion_text2img</a></td> <td><a href="https://stability.ai/blog/stable-diffusion-public-release" rel="nofollow">Stable Diffusion</a></td> <td align="center">Text-to-Image Generation</td></tr> <tr><td><a href="./api/pipelines/stable_diffusion/img2img">stable_diffusion_img2img</a></td> <td><a href="https://stability.ai/blog/stable-diffusion-public-release" rel="nofollow">Stable Diffusion</a></td> <td align="center">Image-to-Image Text-Guided Generation</td></tr> <tr><td><a href="./api/pipelines/stable_diffusion/inpaint">stable_diffusion_inpaint</a></td> <td><a href="https://stability.ai/blog/stable-diffusion-public-release" rel="nofollow">Stable Diffusion</a></td> <td align="center">Text-Guided Image Inpainting</td></tr> <tr><td><a href="./api/pipelines/stable_diffusion/panorama">stable_diffusion_panorama</a></td> <td><a href="https://multidiffusion.github.io/" rel="nofollow">MultiDiffusion</a></td> <td align="center">Text-to-Panorama Generation</td></tr> <tr><td><a href="./api/pipelines/stable_diffusion/pix2pix">stable_diffusion_pix2pix</a></td> <td><a href="https://arxiv.org/abs/2211.09800" rel="nofollow">InstructPix2Pix: Learning to Follow Image Editing Instructions</a></td> <td align="center">Text-Guided Image Editing</td></tr> <tr><td><a href="./api/pipelines/stable_diffusion/pix2pix_zero">stable_diffusion_pix2pix_zero</a></td> <td><a href="https://pix2pixzero.github.io/" rel="nofollow">Zero-shot Image-to-Image Translation</a></td> <td align="center">Text-Guided Image Editing</td></tr> <tr><td><a href="./api/pipelines/stable_diffusion/attend_and_excite">stable_diffusion_attend_and_excite</a></td> <td><a href="https://arxiv.org/abs/2301.13826" rel="nofollow">Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models</a></td> <td align="center">Text-to-Image Generation</td></tr> <tr><td><a href="./api/pipelines/stable_diffusion/self_attention_guidance">stable_diffusion_self_attention_guidance</a></td> <td><a href="https://arxiv.org/abs/2210.00939" rel="nofollow">Improving Sample Quality of Diffusion Models Using Self-Attention Guidance</a></td> <td align="center">Text-to-Image Generation Unconditional Image Generation</td></tr> <tr><td><a href="./stable_diffusion/image_variation">stable_diffusion_image_variation</a></td> <td><a href="https://github.com/LambdaLabsML/lambda-diffusers#stable-diffusion-image-variations" rel="nofollow">Stable Diffusion Image Variations</a></td> <td align="center">Image-to-Image Generation</td></tr> <tr><td><a href="./stable_diffusion/latent_upscale">stable_diffusion_latent_upscale</a></td> <td><a href="https://twitter.com/StabilityAI/status/1590531958815064065" rel="nofollow">Stable Diffusion Latent Upscaler</a></td> <td align="center">Text-Guided Super Resolution Image-to-Image</td></tr> <tr><td><a href="./api/pipelines/stable_diffusion/model_editing">stable_diffusion_model_editing</a></td> <td><a href="https://time-diffusion.github.io/" rel="nofollow">Editing Implicit Assumptions in Text-to-Image Diffusion Models</a></td> <td align="center">Text-to-Image Model Editing</td></tr> <tr><td><a href="./api/pipelines/stable_diffusion_2">stable_diffusion_2</a></td> <td><a href="https://stability.ai/blog/stable-diffusion-v2-release" rel="nofollow">Stable Diffusion 2</a></td> <td align="center">Text-to-Image Generation</td></tr> <tr><td><a href="./api/pipelines/stable_diffusion_2">stable_diffusion_2</a></td> <td><a href="https://stability.ai/blog/stable-diffusion-v2-release" rel="nofollow">Stable Diffusion 2</a></td> <td align="center">Text-Guided Image Inpainting</td></tr> <tr><td><a href="./api/pipelines/stable_diffusion_2">stable_diffusion_2</a></td> <td><a href="https://github.com/Stability-AI/stablediffusion#depth-conditional-stable-diffusion" rel="nofollow">Depth-Conditional Stable Diffusion</a></td> <td align="center">Depth-to-Image Generation</td></tr> <tr><td><a href="./api/pipelines/stable_diffusion_2">stable_diffusion_2</a></td> <td><a href="https://stability.ai/blog/stable-diffusion-v2-release" rel="nofollow">Stable Diffusion 2</a></td> <td align="center">Text-Guided Super Resolution Image-to-Image</td></tr> <tr><td><a href="./api/pipelines/stable_diffusion_safe">stable_diffusion_safe</a></td> <td><a href="https://arxiv.org/abs/2211.05105" rel="nofollow">Safe Stable Diffusion</a></td> <td align="center">Text-Guided Generation</td></tr> <tr><td><a href="./stable_unclip">stable_unclip</a></td> <td>Stable unCLIP</td> <td align="center">Text-to-Image Generation</td></tr> <tr><td><a href="./stable_unclip">stable_unclip</a></td> <td>Stable unCLIP</td> <td align="center">Image-to-Image Text-Guided Generation</td></tr> <tr><td><a href="./api/pipelines/stochastic_karras_ve">stochastic_karras_ve</a></td> <td><a href="https://arxiv.org/abs/2206.00364" rel="nofollow">Elucidating the Design Space of Diffusion-Based Generative Models</a></td> <td align="center">Unconditional Image Generation</td></tr> <tr><td><a href="./api/pipelines/text_to_video">text_to_video_sd</a></td> <td><a href="https://modelscope.cn/models/damo/text-to-video-synthesis/summary" rel="nofollow">Modelscope’s Text-to-video-synthesis Model in Open Domain</a></td> <td align="center">Text-to-Video Generation</td></tr> <tr><td><a href="./api/pipelines/unclip">unclip</a></td> <td><a href="https://arxiv.org/abs/2204.06125" rel="nofollow">Hierarchical Text-Conditional Image Generation with CLIP Latents</a>(implementation by <a href="https://github.com/kakaobrain/karlo" rel="nofollow">kakaobrain</a>)</td> <td align="center">Text-to-Image Generation</td></tr> <tr><td><a href="./api/pipelines/versatile_diffusion">versatile_diffusion</a></td> <td><a href="https://arxiv.org/abs/2211.08332" rel="nofollow">Versatile Diffusion: Text, Images and Variations All in One Diffusion Model</a></td> <td align="center">Text-to-Image Generation</td></tr> <tr><td><a href="./api/pipelines/versatile_diffusion">versatile_diffusion</a></td> <td><a href="https://arxiv.org/abs/2211.08332" rel="nofollow">Versatile Diffusion: Text, Images and Variations All in One Diffusion Model</a></td> <td align="center">Image Variations Generation</td></tr> <tr><td><a href="./api/pipelines/versatile_diffusion">versatile_diffusion</a></td> <td><a href="https://arxiv.org/abs/2211.08332" rel="nofollow">Versatile Diffusion: Text, Images and Variations All in One Diffusion Model</a></td> <td align="center">Dual Image and Text Guided Generation</td></tr> <tr><td><a href="./api/pipelines/vq_diffusion">vq_diffusion</a></td> <td><a href="https://arxiv.org/abs/2111.14822" rel="nofollow">Vector Quantized Diffusion Model for Text-to-Image Synthesis</a></td> <td align="center">Text-to-Image Generation</td></tr> <tr><td><a href="./api/pipelines/stable_diffusion/ldm3d_diffusion">stable_diffusion_ldm3d</a></td> <td><a href="https://arxiv.org/abs/2305.10853" rel="nofollow">LDM3D: Latent Diffusion Model for 3D</a></td> <td align="center">Text to Image and Depth Generation</td></tr></tbody></table> <p></p>

	<script>
	{
	__sveltekit_1k4yk0s = {
	assets: "/docs/diffusers/v0.22.2/ja",
	base: "/docs/diffusers/v0.22.2/ja",
	env: {}
	};

	const element = document.currentScript.parentElement;

	const data = [null,null];

	Promise.all([
	import("/docs/diffusers/v0.22.2/ja/_app/immutable/entry/start.098f23e4.js"),
	import("/docs/diffusers/v0.22.2/ja/_app/immutable/entry/app.d9663000.js")
	]).then(([kit, app]) => {
	kit.start(app, element, {
	node_ids: [0, 2],
	data,
	form: null,
	error: null
	});
	});
	}
	</script>

Xet Storage Details

Size:: 20.7 kB
Xet hash:: 990dbd2a1c27361ca57180ca544bdbbe85919637c6565dc01cfaa1e9882f9eb4

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