Diagnoses training/inference failures in video world model pipelines. Triggers on: training hang, loss NaN, shape mismatch, NCCL timeout, SP bug, distillation collapse, half-video noise. Use when user describes a symptom and wants root-cause diagnosis.
shengshu-ai/minWM
SkillsMP has collected 3 skills from shengshu-ai/minWM. Open a skill to review its source and details.
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 3
- GitHub stars
- 803
- GitHub forks
- 23
Skills in this repository
1 occupation categories · 100% classified
Showing 3 of 3 collected skills.
skill
occupation
description
updated
occupation
Software Developers
description
updated
occupation
Software Developers
description
Step-by-step recipe for plugging a new video DiT backbone into minWM, grounded in the HunyuanVideo (HY15) and Wan 2.1 reference integrations. Use when a user wants to add a new backbone to the framework.
updated
occupation
Software Developers
description
Onboarding guide for newcomers to video world model training in minWM. Covers two parts: Foundations (background theory for the two-phase pipeline) and Pitfalls (non-obvious mistakes from hands-on experience). Use when a newcomer is starting on controllable…
updated
Showing 3 of 3 collected skills.