Video-Text-to-Text
Transformers
Safetensors
qwen3_vl
image-text-to-text
qwen3-vl
video
motion-analysis
motion-quality-assessment
emnlp-2026-findings
custom-code
Instructions to use JohnZhan/MotionInsight-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JohnZhan/MotionInsight-8B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("JohnZhan/MotionInsight-8B") model = AutoModelForMultimodalLM.from_pretrained("JohnZhan/MotionInsight-8B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download CITATION.cff from JohnZhan/MotionInsight-8B: direct link, hf CLI and curl.
- Browser
- Download file 1.48 kB
-
https://huggingface.co/JohnZhan/MotionInsight-8B/resolve/main/CITATION.cff
- Command line
-
hf download hf://JohnZhan/MotionInsight-8B/CITATION.cff
-
curl -L -o CITATION.cff https://huggingface.co/JohnZhan/MotionInsight-8B/resolve/main/CITATION.cff
1.48 kB
| cff-version: 1.2.0 | |
| message: "If you use MotionInsight, please cite the paper below." | |
| title: "MotionInsight: Diagnosing Object Motion Deficiencies in Generated Videos" | |
| type: software | |
| authors: | |
| - family-names: Zhan | |
| given-names: Jiahao | |
| - family-names: Ma | |
| given-names: Yongrui | |
| - family-names: Xing | |
| given-names: Qunliang | |
| - family-names: Zhang | |
| given-names: Xuanyu | |
| - family-names: Tong | |
| given-names: Jingqi | |
| - family-names: Li | |
| given-names: Junlin | |
| - family-names: Li | |
| given-names: Zhang | |
| - family-names: Zhao | |
| given-names: Shijie | |
| - family-names: Xue | |
| given-names: Tianfan | |
| version: 0.1.0 | |
| date-released: 2026-08-30 | |
| license: Apache-2.0 | |
| repository-code: "https://github.com/JohnZhan2023/MotionInsight" | |
| preferred-citation: | |
| type: conference-paper | |
| title: "MotionInsight: Diagnosing Object Motion Deficiencies in Generated Videos" | |
| authors: | |
| - family-names: Zhan | |
| given-names: Jiahao | |
| - family-names: Ma | |
| given-names: Yongrui | |
| - family-names: Xing | |
| given-names: Qunliang | |
| - family-names: Zhang | |
| given-names: Xuanyu | |
| - family-names: Tong | |
| given-names: Jingqi | |
| - family-names: Li | |
| given-names: Junlin | |
| - family-names: Li | |
| given-names: Zhang | |
| - family-names: Zhao | |
| given-names: Shijie | |
| - family-names: Xue | |
| given-names: Tianfan | |
| collection-title: "Findings of the Association for Computational Linguistics: EMNLP 2026" | |
| year: 2026 | |
| url: "https://arxiv.org/abs/2609.37030" | |