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.
LatestLodestones1.0
LodestonesText → Image

Kroma: An MIT-Licensed Text-to-Image Model for ComfyUI

Lodestones releases an open image generator built on the Krea 2 lineage, aimed squarely at ComfyUI workflows.

Jul 31, 2026
UpdateMIT
Kroma

Lodestones has published Kroma, an open text-to-image model now available on Hugging Face. The initial 1.0 release arrives under a permissive MIT license, making it one of the more freely usable image generators to surface in recent weeks.

According to the release, Kroma is built on the Krea 2 lineage and packaged with ComfyUI in mind — the node-based interface that has become the default playground for the open image-generation community. That framing suggests the model is meant to slot directly into existing pipelines rather than ship as a standalone application.

Why it matters

Licensing remains one of the biggest friction points for people building on open image models, where restrictive terms often limit commercial use. An MIT license removes much of that ambiguity:

  • Free to use, modify, and redistribute, including in commercial projects
  • Compatible with the ComfyUI ecosystem many creators already rely on
  • A clean starting point for fine-tunes and derivative workflows

The record leaves several technical details unstated — there is no published parameter count or benchmark data yet — so the practical quality of Kroma will be judged by the community as people put it through real ComfyUI graphs. For now, its clear license and familiar tooling make it an easy model to try, with the specifics available on the project's Hugging Face page.

Sources

  • lodestones/Kroma

    Hugging Face

    Visit
OlderNVIDIA's Nemotron VoiceChat 11B Targets Spoken AINVIDIA · Text → Speech · 4 months agoNewerDeepSeek Ships V4-Flash, a 304B MoE Tuned for AgentsDeepSeek · Text / LLM · 4 months ago

Get the model

Hugging Face

Specs

LicenseMIT
Likes545

Modalities

Text → 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 in Text → Image

All Text → Image →
MiniMax H3 Image
MiniMax/Text → 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
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