Pinned Loading

1. FlashML-org/FreeVideo FlashML-org/FreeVideo Public

   Make videos on the computer you already own. FreeVideo runs MiniMax H3 in as little as 8 GB of VRAM and 16 GB of RAM, and adapts its acceleration path to your hardware.

   Python 1.1k 100

2. WeChatCV/Stand-In WeChatCV/Stand-In Public

   [CVPR2026 🎉] Stand-In is a lightweight, plug-and-play framework for identity-preserving video generation.

   Python 790 50

3. nunchux-ai/nunchaku nunchux-ai/nunchaku Public

   [ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

   Python 4k 280

4. nunchux-ai/ComfyUI-nunchaku nunchux-ai/ComfyUI-nunchaku Public

   ComfyUI Plugin of Nunchaku

   Python 2.9k 172

5. WeChatCV/Stand-In_Preprocessor_ComfyUI WeChatCV/Stand-In_Preprocessor_ComfyUI Public

   The core component of Stand-In, the preprocessor, is essential—only images processed through it can fully unlock the capabilities of Stand-In.

   Python 158 13

6. FastEasyControl FastEasyControl Public

   This is an optimized version of EasyControl, maintaining pixel-level consistency while achieving approximately 30% faster inference speed. It also keeps VRAM usage close to that of using flux1.dev …

   Python 11