Today we are releasing FLUX 3 Image Klein, a 5.6B parameter open weights model for text-to-image generation, image editing and multi-reference generation with up to 10 reference images. It shares core capabilities with the full FLUX 3 Image model: native 4K generation, pixel-perfect editing, and bounding boxes that control where elements are placed or confine edits to a defined area. FLUX 3 Image Klein builds on FLUX 3's shared learnings across images, video and audio, helping the model generate images that feel grounded in the real world.
The release includes a base model for fine-tuning and a step distilled model for low-latency generation, along with FP8, INT8 and NVFP4 builds developed with NVIDIA support, under the FLUX Kommunity License. In internal evaluations, FLUX 3 Image Klein ranks first in text-to-image, multi-reference generation and image editing, ahead of larger open weights models. Compared with FLUX.2 [klein] 9B, it gains 91 Elo in text-to-image and 70 in image editing, with 38% fewer parameters.
FLUX 3 Image Klein was optimized for consumer GPUs. With the INT8 build, it runs on NVIDIA GeForce RTX GPUs with as little as 8GB of VRAM, generating a 1MP image in about 4 seconds on an RTX 5090. The base checkpoint supports LoRA training from day one, and for faster production workloads, teams can work with specific customizations.
On the speed-quality frontier, FLUX 3 Image Klein delivers lower latency than Qwen-Image 2.1, FLUX.2 [pro], Ideogram V4.5 and Krea 2, and the highest rating at its latency. It is available today as open weights via the BFL API and as downloadable weights.
Source: Hacker News · Summarized by HeadlinesBriefing