Full video tutorial: every setting explained, plus the 12 GB VRAM setup step by step: https://youtu.be/UBgrzyj1sfg
The fastest MiniMax H3 setup I've found: the lightx2v 4-step turbo LoRA + the FastVideo sparse attention (VSA) gate + the Semantic Bridge adapter, text to video and image to video with native audio in one graph.
Measured on my test GPU (RTX A4500 20 GB, PyTorch cu130):
Text to video, 5 s, 640x960 (0.6 MP): 0:55 sampling, peak about 12.8 GB VRAM (a 12 GB limit still ran at full speed, 0:57)
Image to video, 1 MP: 2:08 sampling, 12.2 GB peak (on 12 GB cards use 0.6 MP: 1:04, 11.3 GB peak)
8 GB: not recommended (the sampler needs about 9 GB and spills into system RAM)
Settings that work for BOTH modes: sampler er_sde + scheduler sgm_uniform, 4 steps, MiniMax Sigma Shift ON (6 / 3). Already set in this file.
Top 3 tips
Use PyTorch cu130 (driver 580+). On cu128 ComfyUI disables its fast kernels: 4:30 vs 1:37 sampling, same workflow.
A full Task Manager is normal: ComfyUI fills free VRAM on purpose.
For image to video, use a full-size image and match the aspect ratio.
Models (Hugging Face):
MiniMax H3 by MiniMax: https://huggingface.co/MiniMaxAI/MiniMax-H3
ComfyUI files (ref2va pruned int8 or w6a8, Qwen3-VL text encoder, video + audio VAE) by Comfy-Org: https://huggingface.co/Comfy-Org/MiniMax-H3/tree/main
4-step turbo LoRA by lightx2v: https://huggingface.co/lightx2v/Minimax-h3-Turbo/tree/main
FastVideo VSA gate file: https://huggingface.co/barelymining/ComfyUI-MiniMax-H3-FastVideo/tree/main
Semantic Bridge adapter + node (zip, not in the Manager) by speach1sdef178: https://huggingface.co/speach1sdef178/MiniMax-H3-Semantic-Bridge/tree/main
Custom nodes: KJNodes, rgthree, Video Helper Suite, Memory Cleanup, Nvidia RTX Nodes (ComfyUI Manager > Install Missing Custom Nodes), plus:
Ref2VA VSA node by Kablex: https://github.com/Kablex/ComfyUI-Ref2VA-VSA
Optional live VRAM monitor, Crystools by crystian: https://github.com/crystian/ComfyUI-Crystools
Want the one-click setup? My MiniMax H3 All-In-One Windows installer sets up ComfyUI, the custom nodes and the models for you automatically:
Patreon (one-click installer): https://www.patreon.com/TheLocalLab/posts/minimax-h3-all-167996909
Individual purchase (locallabdigest.com): https://www.locallabdigest.com/product-page/minimax-h3-all-in-one-comfyui-one-click-windows-installer
Sampler comparison (community ratings for H3 4-step, by HouPeiyi): https://darkstarrddev.us.ci/
Credits: MiniMax (H3), Comfy-Org (ComfyUI files), lightx2v (turbo LoRA), FastVideo team / hao-ai-lab + Kablex (VSA node), speach1sdef178 (Semantic Bridge), HouPeiyi (sampler benchmark), crystian (Crystools). Demo images generated locally with Qwen Image 2.1.
License: MiniMax H3 is released under the MiniMax H3 license, which limits where the model and its outputs may be used. Read it before you use it: https://huggingface.co/MiniMaxAI/MiniMax-H3
More from me:
Description
First release. Sampler er_sde + scheduler sgm_uniform, 4 steps, MiniMax Sigma Shift ON (6 / 3): works for both text to video and image to video. lightx2v 4-step turbo LoRA, FastVideo VSA gate at 75 % sparsity and Semantic Bridge v1 wired in. Model links and settings are in the notes inside the graph.