v1.1.0

cloudflare/agentsv1.1.0May 7, 2024by FrankLeeeee

AI Summary

Open-Sora v1.1 introduces improved ST-DiT architecture, supports flexible resolution/duration, and provides a data processing pipeline for video datasets.

Key Highlights

Improved ST-DiT architecture including rope positional encoding and qk norm.
Support training with any resolution, aspect ratio, and duration (including images).
Data processing pipeline v1.1 released for dataset creation.
Support for image and video conditioning, editing, and animation.

New Features

ST-DiT architecture improvements
Flexible training support
Data processing pipeline
Image and video editing capabilities

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.