I2VGen is an open-source image-to-video model by Alibaba DAMO Academy that transforms static images into high-resolution, temporally coherent videos using cascaded diffusion.
DDColor is an open-source AI image colorization framework that transforms black-and-white photos into vivid, realistic color images using a novel dual-decoder architecture.
Shandianshuo is a privacy-first AI voice input tool that processes speech locally on your device to deliver ultra-fast, accurate text entry with intelligent semantic optimization.
FaceChain is an open-source AI framework that lets users train and generate customizable, pose-controllable digital avatars and stylized portraits from personal photos using LoRA and Stable Diffusion.