Instructions to use nvidia/Cosmos3-Super-Text2Image-4Step with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Cosmos
How to use nvidia/Cosmos3-Super-Text2Image-4Step with Cosmos:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Download video_preprocessor_config.json from nvidia/Cosmos3-Super-Text2Image-4Step: direct link, hf CLI and curl.
- Browser
- Download file 385 Bytes
-
https://huggingface.co/nvidia/Cosmos3-Super-Text2Image-4Step/resolve/refs%2Fpr%2F19/video_preprocessor_config.json
- Command line
-
hf download hf://nvidia/Cosmos3-Super-Text2Image-4Step@refs/pr/19/video_preprocessor_config.json
-
curl -L -o video_preprocessor_config.json https://huggingface.co/nvidia/Cosmos3-Super-Text2Image-4Step/resolve/refs%2Fpr%2F19/video_preprocessor_config.json
385 Bytes
| { | |
| "size": { | |
| "longest_edge": 25165824, | |
| "shortest_edge": 4096 | |
| }, | |
| "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", | |
| "video_processor_type": "Qwen3VLVideoProcessor" | |
| } |