ali-vilab
ali-vilab's tracked open-source repos, sorted by stars.
- #1
Official implementations for paper: Anydoor: zero-shot object-level image customization
★ 4,239+1Star change over the last 7 days - #2
[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing
★ 3,936+3Star change over the last 7 days - #3
Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models
★ 3,155+0Star change over the last 7 days - #4
Official repository of In-Context LoRA for Diffusion Transformers
★ 2,085+2Star change over the last 7 days - #5
Official implementations for paper: DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models
★ 1,788+1Star change over the last 7 days - #6★ 1,371+2Star change over the last 7 days
- #7★ 1,364+0Star change over the last 7 days
- #8
Official implementations for paper: Zero-shot Image Editing with Reference Imitation
★ 1,312+1Star change over the last 7 days - #9
Code for SCIS-2025 Paper "UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation".
★ 1,189+0Star change over the last 7 days - #10
UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer
★ 850-1Star change over the last 7 days - #11
[CVPR 2025 Highlight] Official implementation of "MangaNinja: Line Art Colorization with Precise Reference Following"
★ 740+0Star change over the last 7 days - #12
[NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
★ 655+0Star change over the last 7 days - #13
Official implementation for paper: InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior
★ 558+0Star change over the last 7 days
