MiniMax H3 Digital Humans in ComfyUI: One Presenter, Two Characters, One Audio Lock

说明与用途

该工作流程在 ComfyUI 中实现了使用 MiniMax H3 和 VoxCPM 模型的单人或双人数字人视频，并将其与音频同步。

问题

Generate coherent digital human videos with one or two characters exchanging lines while keeping the picture stable and lip‑syncing to a single audio track.

结果

The provided ComfyUI graphs enable creation of single‑character and two‑character digital human videos with audio locked to the generated performance, without requiring inference during the article.

工作流

• Load character image(s)
• Load VoxCPM reference audio
• Crop audio to desired segment(s)
• Generate spoken line with VoxCPM
• Lock audio with VRGDG_MiniMaxH3AudioDrive
• Generate video with MiniMax H3
• Create and save video output

证据

Two ComfyUI graphs ship with this release, both on the MiniMax H3 ref2va checkpoint with VoxCPM generating the speech and the generated (or concatenated) audio locked as the driving track.

来源

The node that shapes the whole thing is VRGDG_MiniMaxH3AudioDrive. In both saved files it is configured to lock the original audio and let H3 generate picture only.

来源