RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2086411696771522561?inviteCode=rh-v1111
MiniMax H3 Image-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
24 nodes / 29 links. One LoadImage input. UNETLoader minimax_h3_fl2va_bf16.safetensors; CLIPLoader qwen3vl_32b_minimax_h3_bf16.safetensors (type minimax); VAELoader video minimax_h3_video_vae_fp16.safetensors + audio minimax_h3_audio_vae_fp32.safetensors. LoRA minimax_h3_turbo_v4_step600_ema_pruned_comfyui.safetensors at 1. Sampling: KSamplerSelect euler + BasicScheduler beta, 6 steps, denoise 1.
How to use
This is the 24 GB general edition: bf16 weights, fp16 video VAE, one image and the turbo-v4 LoRA at strength 1. Six steps is the whole sampler budget — there is no 20-step fallback in this graph.
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.