The Open Weights
LatestModelsLeaderboardsUpcomingCompanies
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
  • Upcoming launches

Browse

  • All models
  • Companies
  • Categories
  • Leaderboards

About

  • About
  • Editorial policy
  • RSS feed
  • Newsletter

© 2026 The Open Weights. An independent publication.

Aggregated by Claude · written with Gemini · 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 · Text → Image
FLUX.2 Klein 9B

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

0 comments

Protected by Turnstile

No comments yet. Be the first to weigh in.

Get the model

civitai

Specs

Parameters9B
Context window—
LicenseOTHER
Downloads25.3K

Modalities

Text → Image
7 versions — view changelog

More in Text → Image

Ideogram
Ideogram 4.0
Ideogram 4.0
Ideogram/Text → Image

Ideogram 4.0: A 9.3B Open-Weight Text-to-Image Model

The new 9.3 billion parameter model uses a Diffusion Transformer architecture and excels at rendering coherent text within generated images.

May 30, 2026
ByteDance
Lance
Lance
ByteDance/Any-to-Any

ByteDance Releases Lance, a Unified Generative AI Model

The 3-billion-parameter model handles image and video generation, editing, and understanding from a single set of weights under a permissive license.

May 15, 2026
SenseTime
SenseNova U1 8B MoT Infographic
SenseNova U1 8B MoT Infographic
SenseTime/Any-to-Any

SenseTime Releases 8B 'Any-to-Any' Infographic Model

The new 8B-parameter SenseNova U1 model from SenseTime is designed for complex multimodal tasks, including the in-conversation generation and editing of infographics.

May 14, 2026