RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2086411688710066177?inviteCode=rh-v1111
MiniMax H3 Reference-To-Video — 24 GB Edition
A MiniMax H3 video graph from episode 291, part of the six-times-acceleration series that compares model tier, LoRA, attention and cache settings.
Saved configuration
27 nodes / 34 links. LoadImage + LoadVideo + LoadAudio. UNET minimax_h3_ref2va_bf16.safetensors; CLIP qwen3vl_32b_minimax_h3_bf16; video fp16/audio fp32 VAEs; turbo-v4 LoRA at 1; euler + beta 6 steps denoise 1.
How to use
The 24 GB reference-to-video edition: bf16 ref2va weights and an image + video + audio triple as input. Reference conditioning comes from the still and the clip together; the turbo LoRA keeps the sampler at six steps.
Limits and not-verified items
No inference was run for this listing: no speed, VRAM, quality, audio-sync or acceleration-factor claim is made. The "6x" in the episode title is the author's description and was not independently measured. Values are quoted from the saved nodes. H3 weights, LoRAs, encoder and VAEs are not bundled; check their licenses separately. The graph notes credit the official Comfy-Org/MiniMax-H3 model files; preserved as-is, no originality claim. The cover image is a promotional still, not a frame produced by this graph.
Tutorial: YouTube · Bilibili. Workflows supplied through AI-KSK; verify workflow, node, model, LoRA and cover rights separately. No blanket commercial or redistribution license is asserted.