169 likesNew · 3d old

MiniMax H3 Image repackaged for ComfyUI gains traction

Model · Comfy-Org/MiniMax-H3-Image

ImageLLMs

What is MiniMax-H3-Image?

The repo bundles MiniMax's H3 image diffusion model, VAE, and Qwen text encoders into ready-to-drop files for ComfyUI. After copying the .safetensors into the prescribed folders you can generate images, optionally using the Qwen 3.5 model to improve prompts.

Who it is for

ComfyUI users who want high-quality text-to-image generation can adopt MiniMax H3 without fiddling with conversion scripts.

The morning email · free

Get tomorrow's biggest AI launches before everyone else.

One short email each morning: what launched, why it matters, how to try it. Five minutes, no spam, unsubscribe any time.

Email addressSubscribe

The story so far

Early Signal first spotted Comfy-Org/MiniMax-H3-Image on November 10, 2026, with 169 likes. On its busiest day it gained 56 likes. The project is 3 days old. Early Signal files it under Image, LLMs.

Questions about MiniMax-H3-Image

What do I need to run MiniMax-H3-Image?

ComfyUI installed and a GPU capable of running int8 diffusion models.