v1.3
visioncortex/vtracerv1.3Feb 21, 2025by zhengzangw
AI Summary
Open-Sora V1.3 introduces significant improvements in model architecture and generation quality, featuring upgraded video compression, an enhanced ST-DiT architecture, and expanded support for image-to-video generation with higher resolutions and frame lengths.
Key Highlights
- Upgraded Video Compression
- Enhanced ST-DiT Architecture
- More High-Quality Data & Multi-Stage Training
- Advanced Model Conditioning and Generation Quality
New Features
- Expanded resolution and frame length support
- Image-to-video generation
- Video extension
Full Release Notes
We are excited to introduce Open-Sora V1.3.0, bringing improvements in model architecture and generation quality. Open-Sora V1.3.0 Release š ### š Key Highlights: š¦ Upgraded Video Compression š Enhanced ST-DiT Architecture šļø More High-Quality Data & Multi-Stage Training ⨠Advanced Model Conditioning and Generation Quality Open-Sora 1.3 continues to support image-to-video generation and video extension with expanded resolution and frame length support. š Check out our [technical report](https://github.com/hpcaitech/Open-Sora/blob/main/docs/report_04.md) and [gallery](https://hpcaitech.github.io/Open-Sora/) to explore more!