latent-diffusion 开源项目推荐（173 个）

invoke-ai /InvokeAI

Invoke 是 Stable Diffusion 模型领先的创意引擎，赋能专业人士、艺术家和爱好者利用最新 AI 驱动技术生成和创作视觉媒体。该解决方案提供业界领先的 WebUI，并作为多个商业产品的基础。

Sanster /IOPaint

由 SOTA AI Model 驱动的图像修复工具。可从图片中删除任何不需要的物体、缺陷、人物，或擦除并替换（由 stable diffusion 驱动）图片上的任何内容。

leejet /stable-diffusion.cpp

纯 C/C++ 实现的扩散模型（SD、Flux、Wan、Qwen Image、Z-Image 等）推理

yl4579 /StyleTTS2

StyleTTS 2：通过风格扩散和大型语音语言模型对抗训练迈向人类水平的文本转语音

jina-ai /discoart

用一行代码创作 Disco Diffusion 艺术作品

JoePenna /Dreambooth-Stable-Diffusion

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) by way of Textual Inversion (https://arxiv.org/abs/2208.01618) for Stable Diffusion (https://arxiv.org/abs/2112.10752). Tweaks focused on training faces, objects, and styles.

Stability-AI /stability-sdk

用于与stability.ai API交互的SDK（例如稳定扩散推断）

carefree0910 /carefree-creator

AI magics meet Infinite draw board.

lucidrains /naturalspeech2-pytorch

Pytorch中实现自然语音2、零镜头语音和歌唱合成器

Uminosachi /sd-webui-inpaint-anything

Inpaint Anything扩展使用Segment Anything中的面膜在浏览器UI上执行稳定的扩散修复。

anapnoe /stable-diffusion-webui-ux

Stable Diffusion web UI UX

teticio /audio-diffusion

Apply diffusion models using the new Hugging Face diffusers package to synthesize music instead of images.

mikonvergence /DiffusionFastForward

DiffusionFastForward: a free course and experimental framework for diffusion-based generative models

Text-to-Audio /Make-An-Audio

PyTorch Implementation of Make-An-Audio (ICML'23) with a Text-to-Audio Generative Model

SkyWorkAIGC /SkyPaint-AI-Diffusion

基于Stable Diffusion优化的AI手绘模型。in one embodiment of that present invention，|一种基于稳定扩散的优化文本到图像模型。中文和英文文本输入都可用于生成图像。该模型可以生成多种现代艺术风格的高质量图像。

dailenson /One-DM

ECCV 2024 论文官方代码 — 手写文本生成的一次性扩散模拟器

atfortes /Awesome-Controllable-Diffusion

Papers and resources on Controllable Generation using Diffusion Models, including ControlNet, DreamBooth, IP-Adapter.

nihaomiao /CVPR23_LFDM

The pytorch implementation of our CVPR 2023 paper "Conditional Image-to-Video Generation with Latent Flow Diffusion Models"

magnusviri /InvokeAI

About Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.

facebookresearch /all-atom-diffusion-transformer

Official implementation of All Atom Diffusion Transformers (ICML 2025)