v1.1.0

silvia-odwyer/photonv1.1.0May 7, 2024by FrankLeeeee

AI Summary

Releases updated model weights, a new data processing pipeline, and architectural improvements to the ST-DiT model.

Key Highlights

Model weights for 0s~15s videos at 144p to 720p
Released data processing pipeline v1.1
Improved ST-DiT architecture (rope, qk norm)
Support for any resolution, aspect ratio, and duration

New Features

Data processing pipeline v1.1
Improved ST-DiT architecture
Support for image and video conditioning

Full Release Notes

📍 Open-Sora 1.1 released
- 🌠 Model weights are available [here](https://github.com/hpcaitech/Open-Sora). It is trained on 0s~15s, 144p to 720p, various aspect ratios videos. See our [report 1.1](https://github.com/hpcaitech/docs/report_02.md) for more discussions.
- 🔧 Data processing pipeline v1.1 is released. An automatic [processing pipeline](https://github.com/hpcaitech/Open-Sora#data-processing) from raw videos to (text, video clip) pairs is provided, including scene cutting, filtering(aesthetic, optical flow, OCR, etc.), captioning managing. With this tool, you can easily build your video dataset.
- ✅ Improved ST-DiT architecture includes rope positional encoding, qk norm, longer text length, etc.
- ✅ Support training with any resolution, aspect ratio, and duration (including images).
- ✅ Support image and video conditioning and video editing, and thus support animating images, connecting videos, etc.

Visit the [Open-Sora Gallery](https://hpcaitech.github.io/Open-Sora/) to view more samples.