| lib | hf version | original repo |
|---|---|---|
| mindone.diffusers | support v0.35 | https://github.com/huggingface/diffusers |
| mindone.transformers | support v4.50 | https://github.com/huggingface/transformers |
| model | codebase style | original repo |
|---|---|---|
| janus | DeekSeek | https://github.com/deepseek-ai/Janus |
| cogview | THUDM official | https://github.com/THUDM/CogView4 |
| wan2_1 | Alibaba Wan Group official | https://github.com/Wan-Video/Wan2.1 |
| step_video_t2v | StepFun official | https://github.com/stepfun-ai/Step-Video-T2V |
| janus | DeepSeek AI official | https://github.com/deepseek-ai/Janus |
| emu3 | BAAIVision official | https://github.com/baaivision/Emu3 |
| var | ByteDance FoundationVision official | https://github.com/FoundationVision/VAR |
| hpcai open sora | HPC-AI Tech official | https://github.com/hpcaitech/Open-Sora |
| open sora plan | PKU-YuanGroup official | https://github.com/PKU-YuanGroup/Open-Sora-Plan |
| flux | Black Forest Labs official | https://github.com/black-forest-labs/flux |
| movie gen | implemented by MindONE team, based on the MovieGen paper by Meta | https://arxiv.org/pdf/2310.05737 |
| hunyuanvideo | HunyuanVideo official | https://github.com/Tencent/HunyuanVideo |
| hunyuanvideo-i2v | Tencent official | https://github.com/Tencent/HunyuanVideo-I2V |