Black Forest Labs Releases FLUX.3 Image Klein With Layout Control

Oct 15, 2026
FLUX.3 Image Klein combines image generation, editing, multiple references, and bounding box layout control in one open weights model. The distilled checkpoint generates a 1024 by 1024 image in about two seconds on an NVIDIA H100.

Black Forest Labs released FLUX.3 Image Klein with support in Diffusers from launch, as Hugging Face detailed in a company blog post. The 5.6 billion parameter image transformer handles text to image generation, image editing, and compositions using up to 10 reference images.

Layout control lets users add bounding boxes to prompts on a normalized 0 to 1000 grid. The boxes can place and scale elements in new images, while source and target boxes can move, replace, recolor, or remove content during editing.

The distilled checkpoint uses 16 inference steps and generates a 1024 by 1024 image in about 1.93 seconds on a single NVIDIA H100. A base checkpoint uses 50 steps and supports LoRA fine tuning. BF16, FP8, and NVFP4 weights are available for local deployment.

FLUX.3 Image Klein is available under the FLUX Kommunity License. It permits noncommercial use and allows commercial output generation for qualifying users with less than $5 million in annualized gross revenue, subject to the license terms.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.