Black Forest Labs releases open-source FLUX 3 Image Klein with native 4K image generation

Black Forest Labs releases open-source FLUX 3 Image Klein with native 4K image generation

N
News Editor
2026-10-15 17:00:18
Black Forest Labs has released FLUX 3 Image Klein, an open-source image model built for high-resolution generation and precise editing. The model has 5.6 billion parameters and supports native 4K image generation, pixel-level editing, and image creation using as many as 10 reference images. According to The Decoder, FLUX 3 Image Klein cuts parameter count by 38% from its predecessor while still outperforming closed-source rivals in the company’s internal tests. Another notable point is its hardware requirement: the model can run on a consumer GPU with just 8 GB of VRAM. The release adds another open-source option in the image generation market, pairing lower compute demands with high-resolution output and reference-based generation features.

Black Forest Labs has released FLUX 3 Image Klein, an open-source image model.

Model specs and features

FLUX 3 Image Klein has 5.6 billion parameters. It supports native 4K image generation, pixel-level precise editing, and generation with up to 10 reference images.

Smaller model, stronger internal test results

The model uses 38% fewer parameters than its predecessor. According to The Decoder, it still outperformed closed-source competitors in internal testing.

Hardware requirements

FLUX 3 Image Klein can run on a consumer GPU with only 8 GB of VRAM.

This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan.
100

Disclaimer:

The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.

Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.