Downloads · 30 days
47
100% of all-time downloads
MotionInsight-8B
JohnZhan/MotionInsight-8B
MotionInsight-8B is a video-text-to-text model from JohnZhan. Use it for the video-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
This is the released multidim-all/checkpoint-5500 for MotionInsight: Diagnosing Object Motion Deficiencies in Generated Videos.
All-time downloads
47
Public
Parameters
832K
17.7 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors17.7 GB · 100%
At a glance
- Task
- Video-Text-to-Text
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3_vl
- Access
- Public
- Created
- Aug 30, 2026
- Updated
- Aug 30, 2026
- SHA
- 7bd8c28c
Model card
From the Hugging Face model README
MotionInsight-8B
This is the released multidim-all/checkpoint-5500 for MotionInsight:
Diagnosing Object Motion Deficiencies in Generated Videos.
The model consumes sampled RGB frames, target-object motion features from SAM3 and CoTracker3, and camera motion from VIPE. It predicts diagnostic reasoning and three motion-quality scores.
Use this checkpoint with the code and custom Qwen3-VL implementation from:
https://github.com/JohnZhan2023/MotionInsight
hf download JohnZhan/MotionInsight-8B \
--local-dir checkpoints/MotionInsight-8B
python scripts/patch_transformers.py
python inference.py --help
The VidMotion dataset, videos, and annotations are not distributed.
- Task
- Video-Text-to-Text
- Library
- transformers
- Type
- qwen3_vl
- License
- apache-2.0
- Created
- Aug 30, 2026
- Updated
- Aug 30, 2026