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:
# 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 preprocessor_config.json from JohnZhan/MotionInsight-8B: direct link, hf CLI and curl.
- Browser
- Download file 782 Bytes
-
https://huggingface.co/JohnZhan/MotionInsight-8B/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://JohnZhan/MotionInsight-8B/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/JohnZhan/MotionInsight-8B/resolve/main/preprocessor_config.json
782 Bytes
| { | |
| "crop_size": null, | |
| "data_format": "channels_first", | |
| "default_to_square": true, | |
| "device": null, | |
| "disable_grouping": null, | |
| "do_center_crop": null, | |
| "do_convert_rgb": true, | |
| "do_normalize": true, | |
| "do_pad": null, | |
| "do_rescale": true, | |
| "do_resize": true, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_processor_type": "Qwen2VLImageProcessorFast", | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "input_data_format": null, | |
| "max_pixels": null, | |
| "merge_size": 2, | |
| "min_pixels": null, | |
| "pad_size": null, | |
| "patch_size": 16, | |
| "processor_class": "Qwen3VLProcessor", | |
| "resample": 3, | |
| "rescale_factor": 0.00392156862745098, | |
| "return_tensors": null, | |
| "size": { | |
| "longest_edge": 16777216, | |
| "shortest_edge": 65536 | |
| }, | |
| "temporal_patch_size": 2 | |
| } | |