Store
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Official code of "Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding"
🎥 Auto-reframe videos for mobile using AI to track faces and analyze scenes, ensuring optimal framing for platforms like TikTok and Reels.
LIBERATED AI CHAT
Convert 360° equirectangular panoramas into viewable 3D Gaussian Splat files.
The highest-scoring AI memory system ever benchmarked. And it's free.
Contribute to CNCKitchen/stlTexturizer development by creating an account on GitHub.
[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
Hunt down social media accounts by username across social networks
[SIGGRAPH 2026] OmniRoam: World Wandering via Long-Horizon Panoramic Video Generation
World's first open-source, agentic video production system. 11 pipelines, 49 tools, 400+ agent skills. Turn your AI coding assistant into a full video production studio.
A demo of Indic Parler-TTS
Contribute to JMWL66/jmwl-autotrade development by creating an account on GitHub.
[SIGGRAPH Asia 2022] VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild
Moore-AnimateAnyone-MiniFeatured
[NVIDIA ONLY] Efficient Implementation of Animate Anyone (13G VRAM + 2G model size) https://github.com/sdbds/Moore-AnimateAnyone-for-windows
Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, with AMD GPU support via ROCm. Windows and Linux.
基于 manga-image-translator 的开源漫画翻译工具。支持日/韩/美漫自动翻译，内置 OpenAI、Gemini 等 5 种翻译引擎，并提供可视化编辑器自由调整文本样式。一键安装，开箱即用。如果喜欢，欢迎点亮 ⭐ Star 支持！
芒格.skill — 查理·芒格的认知操作系统。由女娲.skill生成。