Minimax H3

Use a remote SeetaCloud or AutoDL ComfyUI GPU instance to generate MiniMax H3 videos. Connects over SSH, discovers the current H3 workflows, helps choose U03/U06/U02, uploads references, submits a job, and downloads the result. MiniMax H3 supports 5–15 seconds per generation; choose the duration from the user's request and the scene instead of assuming a fixed default. Use when the user asks for MiniMax H3, ComfyUI, SeetaCloud, AutoDL video generation, text-to-video, image-to-video, or reference-guided video. When the target is an AutoDL application instance, use autodl-app-instance as the lifecycle wrapper: boot once before an H3 batch and power off after all jobs finish.

mini-yifan Updated

File contents

mini-yifan/open-source-video-gen-skill/tree/main/skills/minimax-h3 commit a3225966b3

Frequently asked questions

npx skillmds@latest add mini-yifan/minimax-h3