Second Order AI

FLUX.3 Image Klein lets you place objects in an image with boxes

Black Forest Labs released an open image model that creates and edits images in one model and lets you set the layout by drawing boxes.

1 min read

Hugging Face

At a glance

per 1024 × 1024 image on an Nvidia H100 (distilled version)
~2 s
open checkpoints
2
What’s new
Layout control: add bounding boxes to the prompt to say where objects should go. It can also edit from several reference images.
Who it affects
Designers, advertisers and developers making product and marketing images with open models.

The model works in Hugging Face’s Diffusers library from day one, as a modular pipeline so developers can swap parts in and out. Smaller GPUs can load compressed FP8 and NVFP4 weights, and LoRA training scripts are included for both generation and editing.

Why it matters

Placing things precisely has long been a weak spot for image models, which often ignore where you ask objects to go. Box-based layout control makes open models more practical for design, advertising and product images, and day-one library support means developers can build with it straight away.

Original source

Welcome FLUX.3 Image Klein in Diffusers

Hugging Face

huggingface.co

Read the original

Summary by Second Order AI. Full reporting is at the original source.

Related stories

More in →