Downloads · 30 days
0
motion-flow-weights
Anonymousresearch101/motion-flow-weights
motion-flow-weights is a machine learning model from Anonymousresearch101. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as other.
Weights and dataset statistics for the motion flow demo Space. Layout:
Access
Public
Updated Sep 19, 2026
Repo size
695 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt693 MB · 100%
At a glance
- License
- other
- Access
- Public
- Created
- Sep 19, 2026
- Updated
- Sep 19, 2026
- SHA
- e5e62858
Model card
From the Hugging Face model README
Motion flow demo — checkpoints
Weights and dataset statistics for the motion flow demo Space. Layout:
| path | what |
|---|---|
weights/rvq_vae_best.pt | frozen RVQ-VAE (encoder + decoder) — required |
weights/latent_best.pt | LFM, the latent flow model |
weights/direct_best.pt | CDFM, the direct flow model — drives in-betweening, composition, keyframes |
weights/reflow_best.pt | rectified student, usable at 1–4 steps |
assets/Mean.npy, assets/Std.npy, assets/rest_len.npy | HumanML3D statistics — required |
assets/reference_clips.npz | in-betweening reference clips |
z_mean / z_std travel inside each latent checkpoint: they are the statistics of the
RVQ-VAE latents as they stood when that model was trained, so a checkpoint loaded with the
wrong pair decodes to noise.
No SMPL body model is included here. SMPL is not redistributable; register at smpl.is.tue.mpg.de to obtain it.
- License
- other
- Created
- Sep 19, 2026
- Updated
- Sep 19, 2026