From the source
From the source
Open image model adds layout control via bounding boxes
Black Forest Labs released FLUX.3 Image Klein, an open image generation model that runs in Diffusers from day one.
The model supports text-to-image, multi-reference image-to-image, and bounding-box layout control.
The distilled checkpoint generates a 1024x1024 image in about 2 seconds on an H100.
From the source
One model does text-to-image and multi-reference image-to-image, and it adds something new, the layout control . You write bounding boxes into the prompt to say where each part of the image should go, or which parts of a reference image to move.
huggingface.co
