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
  • RSS feed
  • Newsletter

© 2026 The Open Weights. An independent publication.

PrivacyTermsSMSAggregated by Claude · curated by humans.
LatestBlack Forest Labs9B-Base
Black Forest LabsText → Image

Black Forest Labs Releases FLUX.2 Klein 9B

The open-weight text-to-image model brings a 9-billion-parameter base release to the FLUX.2 Klein family.

Jan 28, 2026
NotableOther

Black Forest Labs has released FLUX.2 Klein 9B, a new entry in its FLUX.2 Klein line of open-weight image generators. The model is a 9-billion-parameter base checkpoint built for text-to-image generation, and it's now available through Civitai.

The "9B-Base" label signals that this is a foundational release rather than a fine-tuned or instruction-shaped variant. Base models are typically the raw material the community builds on, providing a starting point for LoRAs, fine-tunes, and downstream workflows rather than a polished, opinionated end product.

Why it matters

Black Forest Labs has become one of the more closely watched names in open image generation since the original FLUX family arrived, and a sub-13B base model is a practical size for a wide swath of users. A 9B dense model strikes a balance between capability and the hardware demands of running and tuning it locally.

  • 9B parameters, dense (not a mixture-of-experts)
  • Text-to-image as the primary modality
  • Released as a base checkpoint for further adaptation

The release ships under a custom license, so teams planning to build commercial pipelines on top of it should review the terms before committing. As always with a fresh base model, the real test will come from what the community produces with it in the weeks ahead.

Sources

  • Flux.2 Klein

    civitai

    Visit

Get the model

civitai

Specs

Parameters9B
LicenseOTHER
Downloads335K
Likes1.2K

Modalities

Text → Image
7 versions — view changelog

0 comments

No comments yet. Be the first to weigh in.

More in Text → Image

Mage-Flow
Microsoft/Text → Image

Microsoft's Mage-Flow packs image editing into 4B

A compact model handles both text-to-image generation and instruction-based edits at native resolution, under a permissive MIT license.

Jul 21, 2026
Unknown/Any-to-Any

Boogu-Image-0.1 Brings Unified Multimodal to Open Source

A new Apache-licensed model family folds bilingual text-to-image generation and instruction editing into one system.

Jul 13, 2026
Qwen-Image-Flash
NVIDIA/Text → Image

NVIDIA distills Qwen-Image for few-step generation

A DMD2-distilled build of Qwen-Image trades sampling steps for speed while keeping the original model's output profile.

Jul 1, 2026