v1.0.0
hpcaitech/Open-Sorav1.0.0Mar 17, 2024by FrankLeeeee
AI Summary
Open-Sora V1.0.0 presents an open-source initiative for efficient high-quality video production with source code for data processing and video generation training, system optimization via ColossalAI and flash attention, and pre-trained model weights.
Key Highlights
- 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
New Features
- Data processing source code
- Video generation training pipeline
- Inference pipeline
- Pre-trained model weights at 256×256 resolution
- Pre-trained model weights at 512×512 resolution
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