Views
No views yet
config.json # training config (consumed by src.config.read_config)
frankenmotion.ckpt # diffusion model weights (~170 MB)
motion_stats/{mean,std}.pt # normaliser stats for the 613-dim smplrifke features
text_stats/{mean,std}.pt # normaliser stats for the per-part CLIP text embeddings1from huggingface_hub import snapshot_download
2snapshot_download(repo_id="Coral79/frankenmotion", local_dir="pretrained/frankenmotion")1@inproceedings{li2026frankenmotion,
2 title={{FrankenMotion}: Part-level Human Motion Generation and Composition},
3 author={Li, Chuqiao and Xie, Xianghui and Cao, Yong and Geiger, Andreas and Pons-Moll, Gerard},
4 booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
5 year={2026}
6}