• Support for longer videos, dynamic resolution training and inference.
• Support for Ascend training and inferencing
• Release all training data and annotations.
• Improve CasualVideoVAE performance.

In this version, we employ ShareGPT4Video for video annotation, followed by training the model on 3k hours of video data. The resulting model exhibited advancements in both video quality and duration. For further details, please refer to our report.