The Open Weights
LatestModelsLeaderboardsCompanies
Subscribe
The Open Weights

The daily record of open-source AI. New model releases, leaderboards, and what's coming next — written for people who ship.

Refreshed every 12 hours

Discover

  • Latest releases
  • New today
  • Trending models

Browse

  • All models
  • Companies
  • Categories
  • Leaderboards

About

  • About
  • Editorial policy
  • Hardware estimates
  • RSS feed
  • llms.txt
  • Newsletter

© 2026 The Open Weights. An independent publication.

PrivacyTermsSMSAggregated by Claude · curated by humans.
LatestMiniMaxH3 Image
MiniMaxText → Image

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.

Nov 3, 2026
NotableOther
MiniMax H3 Image

MiniMax has published 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.

Sources

  • MiniMaxAI/MiniMax-H3-Image

    Hugging Face

    Visit
OlderMicrosoft's Mage-VL-Cowork takes on computer-use tasksMicrosoft · Vision-Language · 3 weeks agoNewerMeituan Releases LongCat 2.5, an MIT-Licensed MoEMeituan · Text / LLM · 2 weeks ago

Get the model

Hugging Face

Specs

LicenseOTHER
Downloads877K
Likes1.7K

Modalities

Image EditingText → Image

The Weekly Weights

Every open release that mattered, one email a week.

0 comments

No comments yet. Be the first to weigh in.

More from MiniMax

All MiniMax releases →
MiniMax-M3.1-Flash
MiniMax/Vision-LanguageMulti-GPU server

MiniMax Debuts M3.1 Flash, a Multimodal MoE Model

The new release pairs a mixture-of-experts design with agentic, coding, and video-understanding abilities in a single open model.

Oct 17, 2026
MiniMax-Music3
MiniMax/MusicRuns anywhere

MiniMax Opens Its Music3 Text-to-Music Model

The Chinese AI lab brings its music generation system to Hugging Face, expanding the roster of open audio models.

Aug 7, 2026
MiniMax-H3
MiniMax/Text → VideoWorkstation GPU

MiniMax Releases H3 Video Model on Hugging Face

The company's new diffusion model handles text-to-video and image-to-video, with support for joint audio-video generation.

Jul 28, 2026

More in Text → Image

All Text → Image →
Fibo 2.0-dev
Briaai/Text → ImageRuns on a laptop

Bria's Fibo 2.0 Brings Structured Prompts to Open Image AI

The new text-to-image and editing model leans on structured prompts and multi-reference inputs for more controllable generation.

Oct 18, 2026
FLUX.3 Image Klein
Black Forest Labs/Text → Image

Black Forest Labs ships FLUX.3 Image Klein for ComfyUI

The lab's latest open image model arrives packaged for ComfyUI with both generation and editing built in.

Oct 14, 2026
FLUX.3 Image Klein
Black Forest Labs/Text → ImageRuns on a laptop

Black Forest Labs ships FLUX.3 Image Klein

The latest open image model from the FLUX team handles both text-to-image generation and editing, and arrives ready to run in Diffusers.

Oct 13, 2026