Skip to content

@ali-vilab Alibaba TongYi Vision Intelligence Lab

Change the repository type filter

All

    Repositories list

    54 repositories

    • Wan-Move

      Public
      [NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
      Python
      •
      Apache License 2.0
      •18•460•5•1•Updated Dec 19, 2025Dec 19, 2025

    • Unison-Page

      Public
      JavaScript
      •
      MIT License
      •0•1•0•0•Updated Dec 11, 2025Dec 11, 2025

    • Unison

      Public
      Python
      •
      MIT License
      •0•15•0•0•Updated Dec 11, 2025Dec 11, 2025

    • DreamRelation

      Public
      [ICCV2025] The official code of "DreamRelation: Relation-Centric Video Customization"
      Python
      •
      MIT License
      •0•24•0•0•Updated Nov 4, 2025Nov 4, 2025

    • stylebooth-page

      Public
      HTML
      •
      MIT License
      •0•1•0•0•Updated Oct 20, 2025Oct 20, 2025

    • VACE

      Public
      [ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing
      video-editingvideo-generation
      Python
      •
      Apache License 2.0
      •244•3.5k•46•2•Updated Oct 17, 2025Oct 17, 2025

    • VACE-Page

      Public
      HTML
      •0•8•0•0•Updated Oct 17, 2025Oct 17, 2025

    • ACE

      Public
      All-round Creator and Editor
      editordiffusiondittongyiwanx
      Python
      •
      Apache License 2.0
      •19•237•3•0•Updated Oct 16, 2025Oct 16, 2025

    • alitok

      Public
      AliTok: Towards Sequence Modeling Alignment between Tokenizer and Autoregressive Model
      Python
      •2•50•2•0•Updated Oct 12, 2025Oct 12, 2025

    • FreeScale

      Public
      [ICCV 2025] Code for FreeScale, a tuning-free method for higher-resolution visual generation
      generative-modelimage-generationdiffusiondiffusion-modelssdxl
      Python
      •
      Apache License 2.0
      •5•146•1•0•Updated Oct 9, 2025Oct 9, 2025

    • TTS-VAR

      Public
      Test-time Scaling for VAR models
      Python
      •
      MIT License
      •3•28•1•0•Updated Sep 19, 2025Sep 19, 2025

    • DiffDoctor

      Public
      [ICCV 2025] DiffDoctor: Diagnosing Image Diffusion Models Before Treating
      fluxartifactstext-to-imageiccvdiffusion-models
      Python
      •
      MIT License
      •1•38•1•0•Updated Sep 9, 2025Sep 9, 2025

    • ICE-Bench-Page

      Public
      JavaScript
      •0•0•0•0•Updated Aug 27, 2025Aug 27, 2025

    • ICE-Bench

      Public
      Python
      •
      MIT License
      •0•6•0•0•Updated Aug 27, 2025Aug 27, 2025

    • DCPE

      Public
      Official code for DCPE
      Python
      •
      MIT License
      •1•4•0•0•Updated Aug 15, 2025Aug 15, 2025

    • FACM

      Public
      FACM: Flow-Anchored Consistency Models
      Python
      •
      Apache License 2.0
      •2•133•0•0•Updated Aug 6, 2025Aug 6, 2025

    • ViewPoint

      Public
      [NeurIPS 2025] ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models
      Python
      •2•27•3•0•Updated Jul 1, 2025Jul 1, 2025

    • TeaCache

      Public
      Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
      lattevideo-generationdiffusion-modelsinference-accelerationopen-sora-planopen-soracogvideoxhunyuan-video
      Python
      •
      Apache License 2.0
      •49•1.2k•28•0•Updated Jun 8, 2025Jun 8, 2025

    • CAPability

      Public
      What Is a Good Caption? A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness
      Python
      •
      Apache License 2.0
      •0•24•1•0•Updated May 16, 2025May 16, 2025

    • UniAnimate-DiT

      Public
      UniAnimate-DiT: Human Image Animation with Large-Scale Video Diffusion Transformer
      video-generationhuman-image-animationvideo-diffusion-transformers
      Python
      •55•825•43•0•Updated Apr 27, 2025Apr 27, 2025

    • ACE_plus

      Public
      Python
      •87•1.3k•54•1•Updated Apr 21, 2025Apr 21, 2025

    • UniAnimate

      Public
      Code for SCIS-2025 Paper "UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation".
      video-generationdance-generationhuman-image-animation
      Python
      •62•1.2k•63•0•Updated Apr 15, 2025Apr 15, 2025

    • matrix

      Public
      Python
      •
      Apache License 2.0
      •2•35•2•0•Updated Apr 8, 2025Apr 8, 2025

    • CDT

      Public
      Official implementation for our paper: Rethinking Video Tokenization: A Conditioned Diffusion-based Approach
      Python
      •
      MIT License
      •0•13•0•0•Updated Apr 2, 2025Apr 2, 2025

    • iv-vae

      Public
      Python
      •
      MIT License
      •1•27•1•0•Updated Mar 4, 2025Mar 4, 2025

    • MangaNinjia

      Public
      [CVPR 2025 Highlight] Official implementation of "MangaNinja: Line Art Colorization with Precise Reference Following"
      Python
      •
      Other
      •53•685•18•0•Updated Mar 2, 2025Mar 2, 2025

    • IDEA-Bench

      Public
      Official repository of IDEA-Bench
      image-editingtext-to-imageimage-to-imagebenchmark-datasetstext-to-image-generationtext-to-image-evaluation
      Python
      •
      Other
      •2•37•0•0•Updated Jan 24, 2025Jan 24, 2025

    • FreeMask

      Public
      Python
      •0•0•0•0•Updated Jan 16, 2025Jan 16, 2025

    • VGen

      Public
      Official repo for VGen: a holistic video generation ecosystem for video generation building on diffusion models
      diffusion-modelsvideo-synthesis
      Python
      •272•3.1k•112•3•Updated Jan 10, 2025Jan 10, 2025

    • ACE_plus_page

      Public
      JavaScript
      •0•2•0•0•Updated Jan 9, 2025Jan 9, 2025