Video-Text-to-Text
Transformers
Safetensors
English
qwen3_omni_moe
text-to-audio
video-captioning
multimodal
physical-reasoning
grounded-generation
physics
Instructions to use Fysics-AI/OmniFysics-Captioner with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Fysics-AI/OmniFysics-Captioner with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Fysics-AI/OmniFysics-Captioner") model = AutoModelForMultimodalLM.from_pretrained("Fysics-AI/OmniFysics-Captioner", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download PPM/preprocessor_config.json from Fysics-AI/OmniFysics-Captioner: direct link, hf CLI and curl.
- Browser
- Download file 390 Bytes
-
https://huggingface.co/Fysics-AI/OmniFysics-Captioner/resolve/main/PPM/preprocessor_config.json
- Command line
-
hf download hf://Fysics-AI/OmniFysics-Captioner/PPM/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/Fysics-AI/OmniFysics-Captioner/resolve/main/PPM/preprocessor_config.json
390 Bytes
| { | |
| "size": { | |
| "longest_edge": 16777216, | |
| "shortest_edge": 65536 | |
| }, | |
| "patch_size": 16, | |
| "temporal_patch_size": 2, | |
| "merge_size": 2, | |
| "image_mean": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "image_std": [ | |
| 0.5, | |
| 0.5, | |
| 0.5 | |
| ], | |
| "processor_class": "Qwen3VLProcessor", | |
| "image_processor_type": "Qwen2VLImageProcessorFast" | |
| } |