v1.2.0
joshiayush/inbv1.2.0Jun 18, 2024by FrankLeeeee
AI Summary
The v1.2 release of Open-Sora enhances training efficiency and video quality by introducing a video compression network, rectified-flow training, and improved multi-stage data processing.
Key Highlights
- New video compression network
- Implementation of rectified-flow training
- Enhanced multi-stage training with more data
- Improved model conditioning
- Better evaluation metrics
New Features
- Video compression network
- Rectified-flow training
- Enhanced multi-stage training pipeline
- Improved model conditioning
- Advanced evaluation metrics
Full Release Notes
Today, we are happy to announce the v1.2 release of the Open-Sora project. This release is built upon v1.1 and features extra exciting components: 1. 📦 Video compression network 2. 🔀 Rectifie-flow training 3. 🪅 More data and better multi-stage training 4. 🚀 Easy and effective model conditioning 5. 👍 Better evaluation metrics If you want to know more about this project, you can - read our [technical report](https://github.com/hpcaitech/Open-Sora/blob/main/docs/report_03.md) - view our [gallery](https://hpcaitech.github.io/Open-Sora/) - try our [checkpoints](https://github.com/hpcaitech/Open-Sora?tab=readme-ov-file#open-sora-12-model-weights) and [gradio demo](https://huggingface.co/spaces/hpcai-tech/open-sora)