v1.2.0
jitsucom/jitsuv1.2.0Jun 18, 2024by FrankLeeeee
AI Summary
Open-Sora v1.2 is released, building upon v1.1 with new components to enhance video generation capabilities, including compression networks and improved training flows.
Key Highlights
- Video compression network added
- Rectifie-flow training implementation
- Enhanced multi-stage training with more data
- Easy and effective model conditioning
- Improved evaluation metrics
New Features
- Video compression network
- Rectifie-flow training
- Model conditioning improvements
- Better evaluation metrics
- Expanded dataset support
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)