Hugging Face introduces FLUX.3 Image Klein in Diffusers

Black Forest Labs released FLUX.3 Image Klein, a single model for text-to-image and multi-reference image-to-image generation that adds bounding-box layout control. The post says the distilled checkpoint generates a 1024 × 1024 image in about 2 seconds on an H100, and that NVFP4 and FP8 weights load for smaller GPUs. Diffusers ships LoRA training scripts for both tasks.