Alibaba TongYi Vision Intelligence Lab

AnyDoor

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

VGen

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

composer

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

dreamtalk

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

MimicBrush

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

videocomposer

Official repo for VideoComposer: Compositional Video Synthesis with Motion Controllability

UniAnimate

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

Cones-V2

Infusion

Official implementations for paper: InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior

FlashFace

Ranni

SCEdit

Official repo: SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing

dvdp

i2vgen-xl

Cones

composer-page

Homepage of Composer.

AnyDoor-Page

e-tsdm-page

stylebooth-page

largen-page

TFT2V