DiLightNet

《李宏毅深度学习教程》（李宏毅老师推荐?，苹果书?），PDF下载地址：https://github.com/datawhalechina/leedl-tutorial/releases

SD.Next: All-in-one for AI generative image

Stable Diffusion and Flux in pure C/C++

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

? Create Disco Diffusion artworks in one line

Stable diffusion for real-time music generation

[SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation

Kandinsky 2 — multilingual text2image latent diffusion model

Core Engine of Singing Voice Conversion & Singing Voice Clone

《大模型白盒子构建指南》：一个全手搓的Tiny-Universe