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 Labs1.0
Black Forest LabsText → Image

Black Forest Labs Releases FLUX.1 Krea Image Model

The new 12-billion-parameter model, tuned by creative AI platform Krea, focuses on high-quality aesthetic output and prompt fidelity.

Jul 7, 2025
Major releaseOther
FLUX.1 Krea [dev]

Black Forest Labs has introduced a new contender in the open-weight image generation space with the release of FLUX.1 Krea. This model represents a collaboration with the AI creative tools company Krea, aiming to produce images with superior visual appeal and a better understanding of user prompts.

The model is built upon the FLUX.1 architecture, which features a powerful 12-billion-parameter Transformer backbone. Unlike many other models that rely on a single text encoder, FLUX.1 uses a dual-encoder approach, combining both CLIP and T5 to interpret text prompts with greater nuance.

The key distinction of this release is the fine-tuning performed by Krea. This process was specifically designed to enhance the model's aesthetic output, making it a potentially valuable tool for artists, designers, and researchers focused on high-quality generative art. The goal is to generate images that are not just technically correct but also visually compelling.

This initial version is designated as a development release. While the weights are publicly accessible, they are governed by a custom license that restricts their use to non-commercial purposes. Researchers and hobbyists can explore the model's capabilities by downloading it from the official Hugging Face repository.

Sources

  • black-forest-labs/FLUX.1-Krea-dev

    Hugging Face

    Visit
OlderByteDance Releases Tar-7B for 'Any-to-Any' MultimodalityByteDance · Any-to-Any · last yearNewerMoonshot AI Releases Trillion-Parameter Kimi-K2 ModelMoonshot AI · Vision-Language · last year

Get the model

Hugging Face

Specs

Parameters12B
Size23.8 GB
PrecisionBF16
ArchitectureFluxPipeline
LicenseOTHER
Downloads26.6K
Likes956

Can you run it?

Runs on a laptop — about 12.9 GB at FP8.

  • BF16 (as published)

    32 GB GPU (RTX 5090) · 48 GB Mac

    24.8 GB
  • FP8

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

    12.9 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

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 from Black Forest Labs

All Black Forest Labs releases →
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
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

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
MOSS-Image SFT
OpenMOSS/Text → ImageRuns on a laptop

OpenMOSS Releases MOSS-Image Under Apache 2.0

The academic team behind the MOSS project moves into text-to-image generation with a permissively licensed model and a fine-tuned SFT variant.

Oct 11, 2026
MOSS-Image SFT
OpenMOSS/Text → ImageRuns on a laptop

OpenMOSS Releases Apache-2.0 Bilingual Image Model

MOSS-Image Base arrives as a permissively licensed text-to-image foundation with English and Chinese support.

Oct 11, 2026