NVIDIA / NVIDIA/cosmos-framework
Need released-code recipe to reproduce Cosmos3 PAIBench-C transfer results
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 535
- Forks
- 148
- Avg merge
- 13h 37m
- Merged PRs (30d)
- 35
Description
Hi, thanks for releasing Cosmos3.
I am trying to reproduce the Cosmos3 PAIBench-C transfer-generation results reported in the technical report/model documentation, especially the single-control segmentation setting.
The report describes the transfer-generation setup as using 50 denoising steps, text guidance 3, control guidance 1.5, shift 10, and full-range CFG. In the released cosmos-framework transfer inference path, I can find the standard guidance / shift / step settings, but I cannot find how to set the separate control-guidance weight described by the two-weight CFG setup.
I opened a related PAIBench issue for the evaluator/reference segmentation artifact side:
https://github.com/SHI-Labs/physical-ai-bench/issues/7
This issue is about the Cosmos3 inference/model side. Could you clarify:
- the exact released-code command/config used for the PAIBench-C Table 16 transfer-generation evaluation
- whether the two-weight CFG / separate control-guidance mechanism is implemented in the public repo
- if implemented, which CLI/config fields correspond to text guidance and control guidance
- the expected frame count and resolution for PAIBench-C reproduction
- whether the reported Cosmos3 Nano/Super PAIBench-C numbers are reproducible from the current public checkpoints and code
- any additional inference settings needed for the segmentation-control run
The goal is to distinguish a released-code Cosmos3 PAIBench-C reproduction from an approximate run using the public transfer inference defaults.
Thanks.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with the released cosmos-framework transfer inference path and the technical report/model documentation, then compare them with the related PAIBench evaluator issue #7. Done means documenting the exact PAIBench-C Table 16 command/config, separate guidance fields if available, expected frame count and resolution, required segmentation-control settings, and checkpoint reproducibility.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 38/100