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, and runs on consumer hardware, with as little as 13GB VRAM. FLUX.2 [klein] 4B is a 4 billion parameter rectified flow transformer capable of generating images from text descriptions and supports multi-reference editing capabilities. Fully open under Apache 2.0. Our most accessible model runs on consumer GPUs like the RTX 3090/4070. Compact but capable: supports…
Open weights
apache-2.0
3.9B parameters
diffusers
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, and runs on consumer hardware, with as little as 13GB VRAM. FLUX.2 [klein] 4B Base is a 4 billion parameter rectified flow transformer capable of generating images from text descriptions and supports multi-reference editing capabilities. It's a full-capacity foundation model. Undistilled, preserving complete training signal for maximum flexibility. Ideal for…
Open weights
apache-2.0
3.9B parameters
diffusers
FLUX 3 Image Klein is a 5.6B open weights model for text-to-image generation and image editing. It takes a prompt and up to 10 reference images and returns one image. Text-to-image, single-reference edits and multi-reference compositions run through the same model, with Qwen3-VL-4B-Instruct as the text encoder. The 5.6B parameter label refers to the image transformer; the text encoder is separate. This repository holds the undistilled base checkpoint, for fine-tuning, LoRA training and research. You can find the distilled checkpoint here: FLUX 3 Image Klein. Inference code, prompt upsampling and the bounding box format: black-forest-labs/flux-3-image-klein on GitHub. Do not use the model…
Access requested at publisher
other
5.5B parameters
diffusers
FLUX 3 Image Klein is a 5.6B open weights model for text-to-image generation and image editing. It takes a prompt and up to 10 reference images and returns one image. Text-to-image, single-reference edits and multi-reference compositions run through the same model, with Qwen3-VL-4B-Instruct as the text encoder. The 5.6B parameter label refers to the image transformer; the text encoder is separate. This repository holds the distilled checkpoint for generation and image editing. For fine-tuning, LoRA training and research, use FLUX 3 Image Klein Base. Inference code, prompt upsampling and the bounding box format: black-forest-labs/flux-3-image-klein on GitHub. Do not use the model without a…
Access requested at publisher
other
5.5B parameters
diffusers
Model · Image to image
Ed
FLUX.2-klein-4B (commit e7b7dc27f91d) with the transformer quantized to bitsandbytes NF4. Loads with Flux2KleinPipeline.frompretrained. Image editing with 1-3 reference images, and text-to-image. Text encoder (Qwen3-4B) not included. Load it from the base repo, or pass promptembeds. - kept in bf16 (~0.37 GB): xembedder, contextembedder, timeguidanceembed, doublestreammodulationimg, doublestreammodulationtxt, singlestreammodulation, normout, projout klein-quantize.py re-shards the single 7.75 GB file into 1 GB shards before quantizing, so peak memory stays around 2.2 GB. Runs on an 8 GB Jetson. Rendered with the same seed, initial noise and prompt embeddings in NF4 and bf16. 4 steps…
Open weights
apache-2.0
2.1B parameters
diffusers
FLUX.2 Small Decoder is a distilled VAE decoder that serves as a drop-in replacement for the standard FLUX.2 decoder. It delivers faster decoding and lower VRAM usage with minimal to zero quality loss. The encoder remains unchanged. 1. ~1.4x faster decoding compared to the full decoder. 2. ~1.4x less VRAM at decode time, enabling higher resolutions without running out of memory. 3. ~28M decoder parameters (vs ~50M in the full decoder) thanks to narrower channel widths ([96, 192, 384, 384] vs [128, 256, 512, 512]). 4. Minimal quality loss — images are almost identical. 5. Available under the Apache 2.0 license. Compatible with all open FLUX.2 models: - This model is not intended or able to…
Open weights
apache-2.0
62M parameters
diffusers
