Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

MiniMax Releases Open-Weight H3-Image Image Generator

AI summary

MiniMax released H3-Image, an open-weight image generation and editing model derived from H3, with support for text-to-image generation and up to 16 reference images. MiniMax says it can generate 4096×4096-pixel, 16MP images in about 10 seconds and launched the model through its API, MiniMax Code, and Hailuo AI. Zhidx tested realism, style transfer, game scenes, poster typography, 16-image fusion, and complex tasks, while a community report said downloadable weights and a ComfyUI template were available.

In-depth insight

The release combines open weights, high-resolution generation, editing, and multi-reference support, giving developers an additional image model available for local and API-based workflows.

4K image generation in 10 seconds! ⚡

Meet MiniMax H3-Image.

16 million pixel resolution. Stunning realism. Precise prompt following & editing. Up to 16 reference images. All in 10 seconds.

And it's open-weight. 🚀

Available now via our API, MiniMax Code, and Hailuo AI — with 50% off 16MP+ generations during launch week!

Can't wait to see what you create. 🔥 Hugging Face: http://huggingface.co/MiniMaxAI/MiniMax-H3-Image API: http://platform.minimax.io/docs/guides/image-generation MiniMax Code: http://code.minimax.io/about

#MiniMax#MiniMax H3-Image#MiniMax Code#Hailuo AI#ComfyUI

Original · 1 min readRead the original
Group chat

No comments yet. Start the conversation.