🤗 Diffusers库中文文档
🤗 Diffusers是用于生成图像、音频甚至分子的3D结构的最先进的预训练扩散模型的首选库。无论您是寻找简单的推理解决方案还是想要训练自己的扩散模型，🤗 Diffusers都是一个支持两者的模块化工具箱。我们的库的设计注重易用性而非性能，注重简单而非轻松，注重可定制性而非抽象化。!(data/attachment/forum/202306/13/145329t5j00t9t758tojog.jpg?imageMogr2/auto-orient/strip%7CimageView2/2/w/300 "diffusers_library.jpg")
该库包含三个主要组件：
1. 最先进的扩散管道，只需几行代码即可进行推理。(https://huggingface.co/docs/diffusers/api/pipelines/overview)
2. 可互换的噪声调度器，用于平衡生成速度和质量之间的权衡。(https://huggingface.co/docs/diffusers/api/schedulers/overview)
3. 预训练模型可用作构建模块，并与调度器组合，用于创建自己的端到端扩散系统。(https://huggingface.co/docs/diffusers/api/models)
**支持的管道pipelines**
| 管道 Pipeline | 论文/代码库 | 任务 |
| ---------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-----------------------------------------------------: |
| (https://huggingface.co/docs/diffusers/api/pipelines/alt_diffusion) | (https://arxiv.org/abs/2211.06679) | 图像到图像的文本引导生成 |
| (https://huggingface.co/docs/diffusers/api/pipelines/audio_diffusion) | (https://github.com/teticio/audio-diffusion.git) | 无条件音频生成 |
| (https://huggingface.co/docs/diffusers/api/pipelines/controlnet) | (https://arxiv.org/abs/2302.05543) | 图像到图像的文本引导生成 |
| (https://huggingface.co/docs/diffusers/api/pipelines/cycle_diffusion) | (https://arxiv.org/abs/2210.05559) | 图像到图像的文本引导生成 |
|(https://huggingface.co/docs/diffusers/api/pipelines/dance_diffusion) | (https://github.com/williamberman/diffusers.git) | Unconditional Audio Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/ddpm) | (https://arxiv.org/abs/2006.11239) | Unconditional Image Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/ddim) | (https://arxiv.org/abs/2010.02502) | Unconditional Image Generation |
| (https://huggingface.co/docs/diffusers/if) | [**IF**](https://huggingface.co/docs/diffusers/api/pipelines/if) | Image Generation |
| (https://huggingface.co/docs/diffusers/if) | [**IF**](https://huggingface.co/docs/diffusers/api/pipelines/if) | Image-to-Image Generation |
| (https://huggingface.co/docs/diffusers/if) | [**IF**](https://huggingface.co/docs/diffusers/api/pipelines/if) | Image-to-Image Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/latent_diffusion) | (https://arxiv.org/abs/2112.10752) | Text-to-Image Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/latent_diffusion) | (https://arxiv.org/abs/2112.10752) | Super Resolution Image-to-Image |
| (https://huggingface.co/docs/diffusers/api/pipelines/latent_diffusion_uncond) | (https://arxiv.org/abs/2112.10752) | Unconditional Image Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/paint_by_example) | (https://arxiv.org/abs/2211.13227) | Image-Guided Image Inpainting |
| (https://huggingface.co/docs/diffusers/api/pipelines/pndm) | (https://arxiv.org/abs/2202.09778) | Unconditional Image Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/score_sde_ve) | (https://openreview.net/forum?id=PxTIG12RRHS) | Unconditional Image Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/score_sde_vp) | (https://openreview.net/forum?id=PxTIG12RRHS) | Unconditional Image Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/semantic_stable_diffusion) | (https://arxiv.org/abs/2301.12247) | Text-Guided Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/text2img) | (https://stability.ai/blog/stable-diffusion-public-release) | Text-to-Image Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/img2img) | (https://stability.ai/blog/stable-diffusion-public-release) | Image-to-Image Text-Guided Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/inpaint) | (https://stability.ai/blog/stable-diffusion-public-release) | Text-Guided Image Inpainting |
| (https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/panorama) | (https://multidiffusion.github.io/) | Text-to-Panorama Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/pix2pix) | (https://arxiv.org/abs/2211.09800) | Text-Guided Image Editing |
| (https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/pix2pix_zero) | (https://pix2pixzero.github.io/) | Text-Guided Image Editing |
| (https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/attend_and_excite) | (https://arxiv.org/abs/2301.13826) | Text-to-Image Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/self_attention_guidance) | (https://arxiv.org/abs/2210.00939) | Text-to-Image Generation Unconditional Image Generation |
| (https://huggingface.co/docs/diffusers/stable_diffusion/image_variation) | (https://github.com/LambdaLabsML/lambda-diffusers#stable-diffusion-image-variations) | Image-to-Image Generation |
| (https://huggingface.co/docs/diffusers/stable_diffusion/latent_upscale) | (https://twitter.com/StabilityAI/status/1590531958815064065) | Text-Guided Super Resolution Image-to-Image |
| (https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion/model_editing) | (https://time-diffusion.github.io/) | Text-to-Image Model Editing |
| (https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion_2) | (https://stability.ai/blog/stable-diffusion-v2-release) | Text-to-Image Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion_2) | (https://stability.ai/blog/stable-diffusion-v2-release) | Text-Guided Image Inpainting |
| (https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion_2) | (https://github.com/Stability-AI/stablediffusion#depth-conditional-stable-diffusion) | Depth-to-Image Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion_2) | (https://stability.ai/blog/stable-diffusion-v2-release) | Text-Guided Super Resolution Image-to-Image |
| (https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion_safe) | (https://arxiv.org/abs/2211.05105) | Text-Guided Generation |
| (https://huggingface.co/docs/diffusers/stable_unclip) | Stable unCLIP | Text-to-Image Generation |
| (https://huggingface.co/docs/diffusers/stable_unclip) | Stable unCLIP | Image-to-Image Text-Guided Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/stochastic_karras_ve) | (https://arxiv.org/abs/2206.00364) | Unconditional Image Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/text_to_video) | (https://modelscope.cn/models/damo/text-to-video-synthesis/summary) | Text-to-Video Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/unclip) | (https://arxiv.org/abs/2204.06125)(implementation by (https://github.com/kakaobrain/karlo)) | Text-to-Image Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/versatile_diffusion) | (https://arxiv.org/abs/2211.08332) | Text-to-Image Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/versatile_diffusion) | (https://arxiv.org/abs/2211.08332) | Image Variations Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/versatile_diffusion) | (https://arxiv.org/abs/2211.08332) | Dual Image and Text Guided Generation |
| (https://huggingface.co/docs/diffusers/api/pipelines/vq_diffusion) | (https://arxiv.org/abs/2111.14822) | Text-to-Image Generation |
占位 占位 占位 占位 占位 占位
页:
[1]