v1.0.0

jitsucom/jitsuv1.0.0Mar 17, 2024by FrankLeeeee

AI Summary

Open-Sora v1.0.0 launch, an initiative to democratize video generation by providing open-source source code, optimized training pipelines, and pre-trained model weights.

Key Highlights

Source code for data processing and video generation
System optimization powered by ColossalAI and flash attention
Model weights trained for 16x256x256 and 16x512x512 resolutions
Sora-like video generation training and inference pipeline

New Features

Data processing source code
Training and inference pipelines
ColossalAI and Flash Attention integration
Pre-trained model weights

Full Release Notes

We present Open-Sora, an initiative dedicated to efficiently produce high-quality video and make the model, tools and contents accessible to all. By embracing open-source principles, Open-Sora not only democratizes access to advanced video generation techniques, but also offers a streamlined and user-friendly platform that simplifies the complexities of video production. With Open-Sora, we aim to inspire innovation, creativity, and inclusivity in the realm of content creation.

In this release, we have included
- source code for data processing
- source code for sora-like video generation training and inference pipeline
- system optimization powered by ColossalAI and flash attention
- model weights trained for 16×256×256 and 16×512x512 resolutions, available on Hugging Face