docs(skills): add Cosmos transfer inference skill - #74
docs(skills): add Cosmos transfer inference skill#74chrisvoncsefalvay wants to merge 12 commits into
Conversation
Signed-off-by: Chris von Csefalvay <chris@chrisvoncsefalvay.com>
|
@trungtpham could have a review and check? THX |
Signed-off-by: Chris von Csefalvay <chris@chrisvoncsefalvay.com>
lfengad
left a comment
There was a problem hiding this comment.
Thanks a lot for putting this together! 🙏 This is genuinely useful — docs/inference.md has zero transfer coverage today, so this skill basically becomes the only documentation we have for the feature. The structure, frontmatter, and the .agents + .claude duplication all match our existing skills, so that part is spot on.
I went through it line by line against transfer.py / args.py / inference.py, and most of the "Source facts" check out exactly — hint enum ordering, weight normalization, single-hint-only defaults, the output filenames, the no-mixing / no-batching asserts, JSON prompt compaction, and single-frame metadata stripping are all accurate. Nice work on that.
I did bump into a handful of things while reading, left inline below. Two of them (the negative_prompt_file paths and the aspect_ratio rule) I think would actually break or silently mislead someone following the skill, so those are the ones I'd love to see addressed. The rest are smaller / take-them-or-leave-them.
One housekeeping note: I only commented on the .agents/ copy to avoid duplicating everything, but every comment applies to the identical .claude/skills/cosmos3-transfer-inference/SKILL.md too.
Happy to help with any of these if it's easier — just let me know!
…r-inference-skill
Clarify transfer paths, examples, launch settings, output composition, and batching constraints. Correct stale multi-GPU latency guidance while retaining full-world FSDP for Super. Signed-off-by: Chris von Csefalvay <chris@chrisvoncsefalvay.com>
|
Thank you again for such a thoughtful review, @lfengad. I’ve addressed all 14 threads in Beyond the narrowly required correction to the existing parallelism guidance, I have not added a broader transfer section to |
Teaches agents how to run Cosmos3 transfer inference with one or more conditioning controls (blur, edge, depth and so on).