The FLUX.2 [klein] model series is our fastest image model to date. FLUX.2 [klein] unifies image generation and editing capabilities within a single compact architecture, completing end-to-end inference in under a second while delivering industry-leading image quality. The model is designed for use cases that require real-time image generation without sacrificing quality, and it can run on consumer-grade hardware.

FLUX.2 [klein] 9B Base is a 9-billion-parameter rectified flow Transformer model capable of generating images from text descriptions and supporting multi-reference image editing. This is a full-capacity base model that is undistilled, preserving complete training signals for maximum flexibility. It is ideal for fine-tuning, LoRA training, research, and custom workflows where control is prioritized over speed. Compared to distilled models, its outputs offer greater diversity.