RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2086411679377743873?inviteCode=rh-v1111
MiniMax H3 Image-To-Video — 48 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. UNET minimax_h3_fl2va_int8_convrot.safetensors; CLIP qwen3vl_32b_minimax_h3_nvfp4_awq; int8 video/fp32 audio VAEs; turbo-v4 LoRA at 1; euler + beta 6 steps denoise 1.
How to use
The 48 GB image-to-video edition: int8-convrot fl2va weights with nvfp4-awq encoder. Same six-step turbo LoRA recipe; this is the tier to try if the bf16 24 GB file does not fit.
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.
Description
RunningHub workflow page: https://www.runninghub.ai/zh-cn/post/2086411679377743873?inviteCode=rh-v1111
MiniMax H3 Image-To-Video — 48 GB EditionA MiniMax H3 video graph from episode 291, part of the six-times-acceleration series that compares model tier, LoRA, attention and cache settings.
Saved configuration24 nodes / 29 links. One LoadImage. UNET minimax_h3_fl2va_int8_convrot.safetensors; CLIP qwen3vl_32b_minimax_h3_nvfp4_awq; int8 video/fp32 audio VAEs; turbo-v4 LoRA at 1; euler + beta 6 steps denoise 1.
The 48 GB image-to-video edition: int8-convrot fl2va weights with nvfp4-awq encoder. Same six-step turbo LoRA recipe; this is the tier to try if the bf16 24 GB file does not fit.
Limits and not-verified itemsNo 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.