FLUX.2-klein-9b-fp8

The FLUX.2 [klein] model family are our fastest image models to date. FLUX.2 [klein] unifies generation and editing in a single compact architecture, delivering state-of-the-art quality with end-to-end inference in as low as under a second. Built for applications that require real-time image generation without sacrificing quality.FLUX.2 [klein] 9B is a 9 billion parameter rectified flow transformer capable of generating images from text descriptions and supports multi-reference editing capabilities.Our flagship small model. Defines the Pareto frontier for quality vs. latency across text-to-image, single-reference editing, and multi-reference generation. Matches or exceeds models 5x its size—in under half a second. Built on a 9B flow model with 8B Qwen3 text embedder, step-distilled to 4 inference steps.This repository holds an FP8 version of FLUX.2 [klein] 9B. The main repository of this model (full BF16 weights) can be found here.For more information, please read our blog post.Key FeaturesA distilled model for sub-second image generation with outstanding quality.Text-to-image and image-to-image multi-reference editing in a single unified model.Great for real-time generation and integration into applications.Ideal for creative exploration with excellent prompt adherence and output diversity.Available for non-commercial use.UsageWe provide a reference implementation of FLUX.2 [klein] 9B, as well as sampling code, in a dedicated GitHub repository. Developers and creatives looking to build on top of FLUX.2 [klein] 9B are encouraged to use this as a starting point.API EndpointsThe FLUX.2 [klein] 9B model is available via the BFL API:bfl.aiFLUX.2 [klein] 9B is also available in both ComfyUI and Diffusers.Using with Diffusers 🧨To use FLUX.2 [klein] 9B with the 🧨 Diffusers python library, first install or upgrade diffusers:pip install -U diffusers Then you can use Flux2KleinPipeline to run the model:import torch from diffusers import Flux2KleinPipeline device = "cuda" dtyp