ali-vilab

Alibaba TongYi Vision Intelligence Lab Joined Feb 2023 View on GitHub

Stars: 28,399; across 61 public repos
Rank: #1,258; of 94,827 organizations, top 2%; Down 41 places this week

Repositories with 50+ stars

ali-vilab's repositories with their overall rank
Rank	Repository	Language	Stars
15,543	AnyDoor Official implementations for paper: Anydoor: zero-shot object-level image customization	Python	4,236
16,284	VACE [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing	Python	4,058
21,355	VGen Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models	Python	3,152
32,822	In-Context-LoRA Official repository of In-Context LoRA for Diffusion Transformers		2,075
38,262	dreamtalk Official implementations for paper: DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models	Python	1,788
43,920	composer Official implementation of "Composer: Creative and Controllable Image Synthesis with Composable Conditions"		1,559
49,327	TeaCache Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model	Python	1,388
50,189	ACE_plus	Python	1,363
52,452	MimicBrush Official implementations for paper: Zero-shot Image Editing with Reference Imitation	Python	1,301
56,838	UniAnimate Code for SCIS-2025 Paper "UniAnimate: Taming Unified Video Diﬀusion Models for Consistent Human Image Animation".	Python	1,191
69,157	videocomposer Official repo for VideoComposer: Compositional Video Synthesis with Motion Controllability	Python	954
76,526	UniAnimate-DiT UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer	Python	856
86,234	MangaNinjia [CVPR 2025 Highlight] Official implementation of "MangaNinja: Line Art Colorization with Precise Reference Following"	Python	754
96,687	Wan-Move [NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance	Python	665
112,508	Infusion Official implementation for paper: InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior	Python	564
139,246	Cones-V2 [ICML 2023 Oral, NeurIPS 2023] Official implementations for paper: Customizable Image Synthesis with Multiple Subjects	Python	444
142,115	FlashFace	Python	434
239,145	ACE All-round Creator and Editor	Python	238
239,934	Ranni	Python	237
280,682	DiffusionOPD [SIGGRAPH Asia 2026] DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models	Python	196
354,250	FreeScale [ICCV 2025] Code for FreeScale, a tuning-free method for higher-resolution visual generation	Python	148
360,099	FACM FACM: Flow-Anchored Consistency Models	Python	145
763,364	alitok [ICLR2026] AliTok: Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model	Python	56
797,197	SCEdit [CVPR 2024 Highlight] Official repo: SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing		53
797,197	ChatDiT	Python	53
797,197	ProMoE [ICLR2026] The official code of "Routing Matters in MoE: Scaling Diffusion Transformers with Explicit Routing Guidance"	Python	53

Among 94,827 organizations

25k–40k stars: 673 organizations, including ali-vilab

top 50%top 10%top 1%top 0.1%

Stars along the bottom, and organizations in each band on a log scale

Where the stars are

Languages

Python 24.3k stars, 85% · 23 repos

When they were made

26 repos with 50+ stars, made between 2023 and 2026

101001k10k VGenVACEAnyDoor

Quick stats

Next rank: +17 stars to reach #1,257
Next milestone: +6,574 stars to reach the top 1%
Public repos: 61, 26 with 50+ stars
Popular repos: 22 over 100 stars, 10 over 1k stars
Top repo: AnyDoor, #15,543 of all repos, 15% of stars
Smaller repos: 438 stars from repos under 50