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.
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.
- 🎉 [new] LiteGen: A light-weight and high-efficient training framework for accelerating diffusion tasks.
- 🎉 [new] VBench: A comprehensive benchmark suite for video generative models
- Latte: Latent Diffusion Transformer for Video Generation
- 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