Instructions to use nvidia/Cosmos3-Edge with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Cosmos
How to use nvidia/Cosmos3-Edge 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
Commit History
-
Update I2V, FD, and ID examples for the converted checkpoint
Verified signature## Summary - Update `example_i2v_prompt.json` to use the 5-second timing intervals `0-2`, `2-4`, and `4-5`. - Regenerate the 20-step I2V examples using the converted checkpoint with both vLLM-Omni and Diffusers. - Regenerate the forward-dynamics and inverse-dynamics outputs with both runtimes. - Regenerate the vLLM-Omni inverse-dynamics trajectory images from their corresponding output JSON files. ## Validation - Both I2V videos contain 121 frames at 832x480 and 24 FPS. - Both stitched forward-dynamics videos contain 32 generated frames at 256x256 and 20 FPS. - All inverse-dynamics JSON outputs contain 60x9 actions.6e7997c
-
Update Cosmos3-Edge I2V default recipe to 20 steps (#56)
- Update Cosmos3-Edge I2V default recipe to 20 steps (dd8925822ba35a150191c4b1cf300159e632fe36)9eff117
-
Add Diffusers user guide for Cosmos3 Edge (#52)
- Add Diffusers user guide for Cosmos3 Edge (7b02304851620049fd90a065a4a2579e6e938ce1) Co-authored-by: Atharva Joshi <atharvajoshi10@users.noreply.huggingface.co>2a00e87
-
Cleanup: remove 6 orphaned example_*_output.* assets superseded by edge_*_output.* (#51)
- Cleanup: remove 6 orphaned example_*_output.* assets superseded by edge_*_output.* (6eea5f2e088c3eb2ddce89ae35a2549d2e743d94) Co-authored-by: Shilin Zhu <shilinzhu-nvidia@users.noreply.huggingface.co>ff48d22
-
Engines: add vLLM-Omni and vLLM (listed first) alongside PyTorch
Verified signaturef54bf13 -
Usage: switch reasnor examples to vLLM (#48)
- Usage: switch reasnor examples to vLLM (aea74fb9d7576027b9d838b2603b42635746ad30) - Update vLLM video media I/O arguments (25962f78f182c79014542ef449e07d00655ca266) Co-authored-by: Xuan Li <xuanli1@users.noreply.huggingface.co>97ce140 -
Usage: switch Generation examples to vLLM-Omni (Nano/Super convention) (#46)
- Usage: switch Generation examples to vLLM-Omni (Nano/Super convention) (96941b0b735abab4d9d132be67b99d8f84acaab2) Co-authored-by: Shilin Zhu <shilinzhu-nvidia@users.noreply.huggingface.co>5b9b37b
-
Initial release
tangyue0820 +11: liang1225, jjf233, yaoxuhf, rickznv, xuanli1, atharvajoshi10, adsridhar, qianlim, shilinzhu-nvidia, fsergiy, BartoszStefaniak
Co-authored-by: liang1225 <liang1225@users.noreply.huggingface.co> Co-authored-by: jjf233 <jjf233@users.noreply.huggingface.co> Co-authored-by: yaoxuhf <yaoxuhf@users.noreply.huggingface.co> Co-authored-by: rickznv <rickznv@users.noreply.huggingface.co> Co-authored-by: xuanli1 <xuanli1@users.noreply.huggingface.co> Co-authored-by: atharvajoshi10 <atharvajoshi10@users.noreply.huggingface.co> Co-authored-by: adsridhar <adsridhar@users.noreply.huggingface.co> Co-authored-by: qianlim <qianlim@users.noreply.huggingface.co> Co-authored-by: shilinzhu-nvidia <shilinzhu-nvidia@users.noreply.huggingface.co> Co-authored-by: fsergiy <fsergiy@users.noreply.huggingface.co> Co-authored-by: BartoszStefaniak <BartoszStefaniak@users.noreply.huggingface.co>6f58f6b