v1.3

weaviate/Verbav1.3Feb 21, 2025by zhengzangw

AI Summary

Open-Sora V1.3.0 focuses on architectural improvements, specifically enhancing the ST-DiT model and upgrading video compression to deliver higher quality video generation.

Key Highlights

Enhanced ST-DiT Architecture
Upgraded Video Compression
Improved Model Conditioning and Generation Quality
Expanded resolution and frame length support

New Features

Image-to-video generation
Video extension
Expanded resolution support
Expanded frame length support

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 🎉

### 🚀 Key Highlights:
📦 Upgraded Video Compression
🌀 Enhanced ST-DiT Architecture
🎞️ 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.

🔗 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!