Skip to content
Stable Diffusion Art 教程· Andrew·· 2026-10-20PicksAI score78

MiniMax H3 reference-to-video (ref2va) ComfyUI workflow tutorial

Reference-to-Video (ref2va) with Sound in ComfyUI (Workflow Included) – MiniMax H3 Reference-to-Video

AI briefing

Stable Diffusion Art released a complete ComfyUI workflow tutorial for MiniMax H3 reference-to-video (ref2va), which can combine up to 9 reference images, 3 reference videos and 3 audio clips to generate a 24fps multi-shot video with synchronized stereo dialogue, sound effects and music in one pass.

Why it matters

The tutorial provides the complete node configuration and prompt structure for MiniMax H3 reference-to-video in ComfyUI, which can be transferred to multi-shot character consistency workflows.

Open original stable-diffusion-art.com