Image-to-Image
NV-MedTech
ONNX
simulation
image-compression
image-autoencoding
healthcare-robotics
world-model
Instructions to use nvidia/Cosmos-Tokenizer-Surg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NV-MedTech
How to use nvidia/Cosmos-Tokenizer-Surg with NV-MedTech:
# 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
| { | |
| "project_name": "wan8_csquant_patch2_bs8_720p", | |
| "teacher_config": { | |
| "dim": "96", | |
| "z_dim": "16", | |
| "dim_mult": "[1, 2, 4, 4]", | |
| "num_res_blocks": "2", "attn_scales": "[]", "temperal_downsample": "[False, True, True]", "dropout": "0.0", "cls": "<class 'models.temporal_wan.WanVAE_'>" | |
| }, | |
| "student_config": { | |
| "dim": "64", | |
| "z_dim": "16", | |
| "dim_mult": "[1, 2, 4]", | |
| "patch_size": "2", | |
| "num_res_blocks": "3", | |
| "attn_scales": "[]", | |
| "dropout": "0.0", | |
| "cls": "<class 'models.image_vae.DiscreteImageVAE'>", | |
| "z_channels": "256", | |
| "z_factor": "1", | |
| "embedding_dim": "16", | |
| "levels": "[8, 8, 8, 5, 5, 5]", | |
| "dtype": "torch.float32", | |
| "model_type": "wan_2_1", | |
| "quantizer_cls": "<class 'models.quantizers.ChannelSplitFSQ'>", | |
| "num_codebooks": "1", | |
| "K": "2" | |
| } | |
| } |