← ClaudeAtlas

minimax-h3-reel-makerlisted

Prepare MiniMax H3 Ref2VA reels in two workflows: reproduce a supplied source clip with scene photos, pose/depth ControlNet and TS smoother, or create a new video from photos and text alone. Use for H3 reference-based video preparation and its ComfyUI graphs.
teskor-hub/minimax-h3-skill · ★ 16 · AI & Automation · score 75
Install: claude install-skill teskor-hub/minimax-h3-skill
# MiniMax H3: two reference workflows Use the bundled graphs and preserve the user's intended scene, clothing, props, actions and audio requirements. This skill prepares a generative reconstruction, not a pixel-preserving face-swap. It does not authorize paid compute, uploads, installation, queue changes or messages to other people by itself. ## Select the workflow without requesting unnecessary assets - A source video is supplied and its motion/cuts should be reproduced: **Ref + ControlNet**, recorded as `control`. Use `assets/01_REF_CONTROLNET_TS.json`. Keep depth, DWPose and **TS Pose Keypoint Smoother**. - No source video is supplied: **Ref Only**, recorded as `refs`. Use `assets/02_REF_ONLY.json`. Work from available photos and the requested action. **Do not ask for or require a source reel, pose video, depth maps, ControlNet, TS smoother or source audio.** These nodes and source dependencies are absent from this graph. - An explicit mode choice overrides automatic selection. If the user supplies a clip but wants only its aesthetic, the clip need not become motion control. Do not turn a photos-only request into a reconstruction task. Both workflows use H3 `ref2va` weights. They are preparation workflows, not separate checkpoints. Motion Strip and Hybrid are not defaults in this handoff. Read [workflows.md](references/workflows.md) for models, dependencies, controls, alignment, installation and packaging. Read [prompting.md](references/prompting.md) before writing th