Open-Sora Plan
Co-sponsored by the Peking University-Rabbit Exhibition AIGC Joint Laboratory, version 1.0 of the model has been launched, and a project called MagicTime has also been released to learn real-world physics from Time-lapse videos.
GitHub:https://github.com/PKU-YuanGroup/Open-Sora-Plan/
Mira
For projects launched by Tencent, the current model can generate 20-second video with a resolution of 128×80 and 10-second video with a resolution of 384×240. Tools for data annotation and model training are also provided.
GitHub:https://github.com/mira-space/Mira
Open-Sora
The project led by the Colossal-AI team has currently released a 1.1 model that supports 2s to 15s, 144p to 720p, with any aspect ratio text-to-image, text-to-video, image-to-video, video to video, unlimited time generation.
GitHub:https://github.com/hpcaitech/Open-Sora
If you want to learn more, you can click on the link below the video.
Thank you for watching this video. If you like it, please subscribe and like it. thank
Video: