GuyTevet/MotionCLIP

View on GitHub

Official Pytorch implementation of the paper "MotionCLIP: Exposing Human Motion Generation to CLIP Space"

Stars: 501
Forks: 46
Open beginner issues: 0
Indexed issues: 23

Dominant language: Python
License: MIT
Last GitHub push: Dec 18, 2023
Latest indexed: Sep 17, 2026
Contributing guide: No contributing guide
Code of conduct: No code of conduct
Beginner labels: No beginner labels indexed
PR merge metrics: No merged PRs in 30d

Open All

23 open issues indexed

the body of Text Motion render result is opposite Open

GuyTevet/MotionCLIP#11 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Motions are static Open

GuyTevet/MotionCLIP#15 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
environment creation using conda fails Open

GuyTevet/MotionCLIP#17 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Create conda environment failed Open

GuyTevet/MotionCLIP#18 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Why input size is 25 x 6? Open

GuyTevet/MotionCLIP#19 · 6 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
continuous issue about rendering the sample Open

GuyTevet/MotionCLIP#26 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
SImilarities computed using motion and text embeddings are incorrect Open

GuyTevet/MotionCLIP#27 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
two extra loss terms: mmd and hessian_penalty Open

GuyTevet/MotionCLIP#28 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
results on HumanML3D dataset Open

GuyTevet/MotionCLIP#29 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
train in num_frames == -2 Open

GuyTevet/MotionCLIP#31 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Reproducing paper results Open

GuyTevet/MotionCLIP#32 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
question about amass_parser.py Open

GuyTevet/MotionCLIP#33 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
consistency of the motion encoder and the motion decoder Open

GuyTevet/MotionCLIP#35 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
AttributeError: 'AMASS' object has no attribute 'nfeats' Open

GuyTevet/MotionCLIP#36 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
ffmpeg version Open

GuyTevet/MotionCLIP#37 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
What device did you use to train the model and how long did it cost? Open

GuyTevet/MotionCLIP#38 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
Was (0, 0, 0) being passed as translation to the encoder during training? Open

GuyTevet/MotionCLIP#39 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
different joint index for thetas(pose) and joints3d? Open

GuyTevet/MotionCLIP#41 · 0 comments · 1 reaction · 0 assignees · Indexed Sep 17, 2026
How do I train my own MotionCLIP? Open

GuyTevet/MotionCLIP#42 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
TypeError: __init__() missing 3 required positional arguments: 'njoints', 'nfeats', and 'num_classes' Open

GuyTevet/MotionCLIP#43 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 17, 2026
The Output is upside down! Open

GuyTevet/MotionCLIP#44 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
i want to know how to get this rendered frames, cuold you tell me, please? Open

GuyTevet/MotionCLIP#45 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026
babel_30fps_*.pt preprocessed files missing from Google Drive release Open

GuyTevet/MotionCLIP#46 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 17, 2026

GuyTevet/MotionCLIP

Get new issues in your inbox