Welcome FLUX.3 Image Klein in Diffusers

Black Forest Labs has released FLUX.3 Image Klein, a new open image generation model available in the Diffusers library. The model performs text-to-image, multi-reference image-to-image, and introduces a novel layout control feature that uses bounding boxes in the prompt to place objects. A distilled version of the model can generate a 1024x1024 image in about two seconds on an H100 GPU, with quantized variants available for smaller hardware. The model's architecture, performance benchmarks, and implementation as a modular pipeline are also detailed, along with code examples for getting started.