Skip to content

GitHub User's stars

Welcome to the Vchitect homepage. Vchitect is mainly developed by Shanghai AI Laboratory. We keep working in the field of video generation, open-sourcing the models, benchmark suites, and efficient training tools.

🔥 Updates

Vchitect 2.0

  • [09/2024] We release Vchitect 2.0, including the model and the training system
    • Model:
      • Vchitect-2.0 is a high-quality video generative model with 2 billion parameters, supporting resolutions up to 720x480 and video durations of 10-20 seconds. Besides, We are also developing a larger verison with 5 billion parameters, and will be released in the future.
      • VEnhancer is a generative space-time enhancement framework. It integrates super-resolution, frame interpolation, and video refinement to elevate the video quality to 2K resolution at 24 FPS.
    • System:
      • LiteGen is a lightweight and highly efficient training framework for diffusion tasks. It supports sequence lengths of up to 1.63 million tokens using 8x NVIDIA A100 GPU cards during the training of the Vchitect-2.0 model.
    • Benchmark:
      • VBench is a comprehensive benchmark suite for video generative models, covering 28 text-to-video generation models and 12 image-to-video generation models.

🎁 Model

  • 🎉 [new] Vchitect-2.0: A high-quality video generation video with resolutions up to 720x480 and video durations of 10-20 seconds.
  • 🎉 [new] VEnhancer: A generative space-time enhancement framework that can improve the existing T2V results.

🚀 System

  • 🎉 [new] LiteGen: A light-weight and high-efficient training framework for accelerating diffusion tasks.

🏔️ Benchmark

  • 🎉 [new] VBench: A comprehensive benchmark suite for video generative models

Latte

  • Latte: Latent Diffusion Transformer for Video Generation

Vchitect 1.0

  • LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models
  • SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction
  • VideoBooth: Diffusion-based Video Generation with Image Prompts
  • Vlogger: A generic AI system for generating a minute-level video blog (i.e., vlog) of user descriptions.
  • Optix: Memory Efficient Training Framework for Large Video Generation Model

Pinned Loading

  1. LaVie LaVie Public

    [IJCV 2024] LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models

    Python 871 59

  2. SEINE SEINE Public

    [ICLR 2024] SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction

    Python 908 64

  3. Latte Latte Public

    Latte: Latent Diffusion Transformer for Video Generation.

    Python 1.7k 176

  4. Vchitect-2.0 Vchitect-2.0 Public

    Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models

    Python 635 17

  5. VEnhancer VEnhancer Public

    Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation

    Python 448 24

  6. VBench VBench Public

    [CVPR2024 Highlight] VBench - We Evaluate Video Generation

    Python 555 28

Repositories

Showing 10 of 17 repositories
  • FasterCache Public

    FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality

    Vchitect/FasterCache’s past year of commit activity
    Python 105 5 5 0 Updated Nov 1, 2024
  • VBench Public

    [CVPR2024 Highlight] VBench - We Evaluate Video Generation

    Vchitect/VBench’s past year of commit activity
    Python 555 Apache-2.0 28 30 2 Updated Oct 29, 2024
  • Latte Public

    Latte: Latent Diffusion Transformer for Video Generation.

    Vchitect/Latte’s past year of commit activity
    Python 1,692 Apache-2.0 176 0 3 Updated Sep 28, 2024
  • Vchitect-2.0 Public

    Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models

    Vchitect/Vchitect-2.0’s past year of commit activity
    Python 635 Apache-2.0 17 5 0 Updated Sep 18, 2024
  • VEnhancer Public

    Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation

    Vchitect/VEnhancer’s past year of commit activity
    Python 448 24 20 0 Updated Sep 16, 2024
  • LiteGen Public

    A light-weight and high-efficient training framework for accelerating diffusion tasks.

    Vchitect/LiteGen’s past year of commit activity
    Python 39 Apache-2.0 2 1 0 Updated Sep 14, 2024
  • .github Public
    Vchitect/.github’s past year of commit activity
    0 0 1 0 Updated Sep 9, 2024
  • VBench-project Public

    Project Page of [CVPR2024 Highlight] VBench - We Evaluate Video Generation https://vchitect.github.io/VBench-project/

    Vchitect/VBench-project’s past year of commit activity
    JavaScript 0 0 0 0 Updated Aug 28, 2024
  • LaVie Public

    [IJCV 2024] LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models

    Vchitect/LaVie’s past year of commit activity
    Python 871 Apache-2.0 59 18 5 Updated Aug 20, 2024
  • Vchitect/VEnhancer-project’s past year of commit activity
    JavaScript 1 0 0 0 Updated Jul 28, 2024

People

This organization has no public members. You must be a member to see who’s a part of this organization.