# MiniMax Releases H3 Image, Its Open Text-to-Image Model

> The Chinese AI lab enters the open image-generation space with a single model that both creates and edits pictures from text.

Published by The Open Weights on Nov 3, 2026. Canonical: https://theopenweights.com/news/minimax-h3-image-1hat

## Key facts

- Company: MiniMax
- Model: MiniMax H3 Image
- Version: H3 Image
- Category: Text → Image
- Modalities: Image Editing, Text → Image
- License: Other (Open weights, commercial use allowed)
- Significance: notable
- Published: 2026-11-03
- Last verified: 2026-11-20
- Hugging Face: https://huggingface.co/MiniMaxAI/MiniMax-H3-Image
- Canonical URL: https://theopenweights.com/news/minimax-h3-image-1hat

MiniMax has published [H3 Image](https://huggingface.co/MiniMaxAI/MiniMax-H3-Image), a text-to-image model that also handles image editing, on Hugging Face. It marks the company's first entry into open image generation, extending a portfolio that has so far leaned toward large language and agentic models.

The model covers two closely related tasks: generating pictures from text prompts and editing existing images based on instructions. Bundling both capabilities into one release is increasingly common, letting developers use a single system for creation and iterative refinement rather than stitching together separate tools.

## Why it matters

MiniMax is among the more prominent Chinese labs releasing model weights, and its move into images adds another option for developers building generative visual tools outside the walled gardens of proprietary APIs. A few things stand out:

- H3 Image is distributed under a custom license rather than a standard permissive one, so teams should read the terms before commercial use.
- MiniMax has not published parameter counts or detailed benchmarks alongside the release.

As always with a fresh image model, the real test will be how its outputs hold up against established open alternatives once the community starts running it. The weights and documentation are available now on [Hugging Face](https://huggingface.co/MiniMaxAI/MiniMax-H3-Image).

## Get the model

- [Hugging Face](https://huggingface.co/MiniMaxAI/MiniMax-H3-Image)

## Sources

- [MiniMaxAI/MiniMax-H3-Image](https://huggingface.co/MiniMaxAI/MiniMax-H3-Image) — Hugging Face, Nov 3, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "MiniMax Releases H3 Image, Its Open Text-to-Image Model", The Open Weights, Nov 3, 2026, https://theopenweights.com/news/minimax-h3-image-1hat