Community ComfyUI workflow using H3 with a frame count of one to produce images. Demoed with an anime fox-eared shrine maiden; the creator says it isn't a frontier image model and prefers other models.
MiniMax H3 image workflow
Community ComfyUI workflows that use the MiniMax H3 video model with a one-frame count to output still images.
Updated EU status checked Last shown
MiniMax H3 image workflow at a glance
- What is MiniMax H3 image workflow?
- MiniMax H3 image workflow is an app. Community ComfyUI workflows that use the MiniMax H3 video model with a one-frame count to output still images.
- Does MiniMax H3 image workflow work in the EU?
- Unverified. No explicit evidence found. The workflows are downloadable from Hugging Face, but they depend on the MiniMax H3 license, whose terms on EU use were not provided. Last verified 14 Nov 2026.
- How much does MiniMax H3 image workflow cost?
- Open source. Workflow files are free to download from Hugging Face. They require MiniMax H3 weights under the MiniMax H3 license and local hardware. Licence: MiniMax H3 License (other).
- Where was MiniMax H3 image workflow shown?
- In 1 creator video by AI Search. Most recently by AI Search on 12 Aug 2026, at 21:24 in “The BEST local AI video generator just got BETTER!”.
Sources: the vendor's own pages (linked above) and creator videos at the linked timestamps. EU status is information, not legal advice; see how we check.
This is a set of community-made ComfyUI workflows, published on Hugging Face by the user reverentelusarca. They repurpose the MiniMax H3 video generation model for still images by setting the frame count to one, so a single frame is rendered instead of a clip. The workflow is not an official MiniMax product, and the vendor is listed as unknown.
A YouTube creator (AI Search) demonstrated it with an anime-style fox-eared shrine maiden image. The same creator said it is not a frontier image model and that they prefer other models for image generation. It is best treated as an experiment in reusing a video model's output for stills.
It runs locally in ComfyUI and needs the MiniMax H3 model weights, which are distributed under a separate MiniMax H3 license. The Hugging Face repository lists the license as "other" and links to the MiniMax-H3 license file. The repository had no recorded downloads at the time of the scrape, and no documentation or paper was provided.
- ComfyUI workflows for generating still images with MiniMax H3
- Uses a frame count of one to turn a video model into an image generator
- Runs locally; community-made, not an official MiniMax release
- Governed by the MiniMax H3 license
As seen on YouTube
Watch the moment: the exact second top creators show it. Videos load only when you press play, via youtube-nocookie.com.
Similar AI tools
Closest neighbours by meaning, not just by category.
ComfyUI-MiniMaxH3-Easy
Library · nkxx188
ComfyUI custom node suite that simplifies MiniMax H3 video and image generation in a single compact workflow.
MiniMax H3 Image
Model · MiniMax
Open-weights MiniMax image generation and editing model producing up to ~16 MP images in 6 sampling steps.
LTX 2.5 Upscaler with MiniMax
App
Community ComfyUI workflow that generates video with MiniMax and upscales it using the LTX 2.5 spatial upscaler.
MiniMax H3
Model · MiniMax
Open-weight video generation model from MiniMax, part of its H3 family alongside H3 Image.
MiniMax H3 W4A8 experimental models
Model · Kijai
Community-quantized W4A8 and int8 VAE checkpoints of MiniMax H3 video model for ComfyUI, by Kijai.
ComfyUI
App · Comfy Org
Node-based visual AI engine for running image, video, audio and 3D generation workflows locally, in the cloud or via API.