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.
LatestBlack Forest LabsFLUX.3 Klein
Black Forest LabsText → Image

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
Major releaseOther
FLUX.3 Image Klein

Black Forest Labs has released FLUX.3 Image Klein, the newest entry in its FLUX line of open image models. The model handles both text-to-image generation and image editing, and it ships integrated with the Diffusers library, which means developers can pull it directly into existing Python pipelines without much glue code. Details are laid out in the company's announcement post.

The "Klein" naming follows Black Forest Labs' convention of distinct variants within a release, typically aimed at users who want a more accessible, lighter-weight option than the flagship. Packaging it for Diffusers lowers the barrier for experimentation and for folding the model into products that already rely on the Hugging Face stack.

Why it matters

FLUX models have become a common reference point in the open image-generation space, so a new major version draws attention from anyone building creative tools:

  • A single model covering both generation and editing simplifies workflows that previously stitched together separate systems.
  • Day-one Diffusers support shortens the path from download to deployment.
  • An openly distributed release gives teams a self-hostable alternative to closed image APIs.

The model is published under a custom license rather than a standard permissive one, so teams planning commercial use should read the terms on the model page before committing. As always with a fresh release, real-world quality and performance will come into focus as the community puts it through its paces.

Sources

  • black-forest-labs/flux-3-image-klein

    Hugging Face

    Visit
OlderLiquid AI's LFM2.5 Puts a 24B MoE on Your DeviceLiquidAI · Embeddings · 4 days agoNewerinclusionAI releases Ling-3.1-flash under MIT licenseinclusionAI · Text / LLM · 3 days ago

Get the model

Hugging Face

Specs

Size11.1 GB
PrecisionBF16
LicenseOTHER
Downloads3.2K
Likes217

Can you run it?

Runs on a laptop — about 6.6 GB at FP8.

  • BF16 (as published)

    16 GB GPU (RTX 4080 / 5070 Ti) · 24 GB Mac

    12.1 GB
  • FP8

    8 GB GPU (RTX 4060) · 16 GB laptop or Mac

    6.6 GB
Your machine
  • Covers the published checkpoint; text encoders and VAE loaded alongside may add a few GB (many runtimes offload them to CPU).

Based on Hugging Face weights metadata. Assumes an 8K context and ~1 GB runtime overhead; actual needs vary. How we estimate


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 Black Forest Labs

All Black Forest Labs releases →
FLUX 3 Action Base
Black Forest Labs/Any-to-Any

Black Forest Labs brings FLUX to robotics

The image-model maker's FLUX 3 Action Base extends its generative stack into world-action modeling, released through the LeRobot ecosystem.

Sep 22, 2026
Black Forest Labs/Text → ImageRuns on a laptop

Ideogram 4.0 arrives as an open-weight image model

A 9.3-billion-parameter text-to-image model lands on GitHub with downloadable weights and code.

Jun 3, 2026
FLUX.2 small decoder
Black Forest Labs/Text → ImageRuns anywhere

Black Forest Labs Releases Open FLUX.2 Image Decoder

This new component is part of a novel transformer-based architecture for text-to-image generation, released under a permissive Apache 2.0 license.

Apr 6, 2026

More in Text → Image

All Text → Image →
Qwen-Image-2.1-Turbo
Qwen · Alibaba/Text → ImageRuns on a laptop

Qwen-Image-2.1-Turbo targets faster generation

Alibaba's Qwen team ships a distilled, few-step variant of its image model built for speed.

Oct 9, 2026
Ming-Image-0.1-Design
inclusionAI/Text → ImageRuns on a laptop

inclusionAI's Ming-Image targets graphic design

A new MIT-licensed text-to-image model leans into legible text rendering and transparent RGBA output for design work.

Sep 17, 2026
Qwen-Image-2.1
Qwen · Alibaba/Text → ImageRuns on a laptop

Qwen-Image-2.1 Adds RGBA to Image Generation

Alibaba's Qwen team updates its open image model with transparency support and joint text-to-image and editing capabilities.

Sep 14, 2026