Alibaba TongYi Vision Intelligence Lab

Official implementation of "Composer: Creative and Controllable Image Synthesis with Composable Conditions"

damo-vilab

Official repo for VideoComposer: Compositional Video Synthesis with Motion Controllability

ali-vilab

Official implementations for paper: Anydoor: zero-shot object-level image customization

ali-vilab

Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models

ali-vilab

Official implementations for paper: DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models

ali-vilab

Code for SCIS-2025 Paper "UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation".

ali-vilab

Official implementations for paper: Zero-shot Image Editing with Reference Imitation

ali-vilab

Official implementations for paper: VACE: All-in-One Video Creation and Editing

ali-vilab

All-round Creator and Editor

ali-vilab

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

ali-vilab