FLUX.2 [klein] 4B is a compact 4B-parameter text-to-image model from Black Forest Labs that delivers fast generation with quality results. Supports flexible sizing and JPEG, PNG, and WebP outputs.
Added May 18, 2026
Approx. Price
$0.010 per image
Model Type
text-to-image
Settings
Generation controls available for this model.
Images Per Run
Up to 4
Output images
Input Images
Up to 4
Reference/edit images accepted • Route max 30 MB
Output Sizes
Custom Resolution
LoRA 1 Scale
Default
1
Strength of the first LoRA (0.0 to 4.0).
LoRA 1 URL
Default
N/A
Path to the first LoRA model (e.g., owner/model-name or .safetensors URL).
LoRA 2 Scale
Default
1
Strength of the second LoRA (0.0 to 4.0).
LoRA 2 URL
Default
N/A
Path to the second LoRA model (optional).
LoRA 3 Scale
Default
1
Strength of the third LoRA (0.0 to 4.0).
LoRA 3 URL
Default
N/A
Path to the third LoRA model (optional).
Number of Images
Default
1
Resolution
Default
1024*1024
Options (6)
1024*1024 (Square (1024x1024)), 1280*720 (Landscape (1280x720)), 720*1280 (Portrait (720x1280)), 1536*1024 (Wide (1536x1024)) +2 more
Showing 9 of 10 settings.
Benchmarks
Benchmarks
Human preference benchmarks sourced from Artificial Analysis.
Text to Image
#105 / 146
ELO
1061.0
Appearances
6,555
95% CI
-9/9
Image Editing
#50 / 67
ELO
1117.0
Appearances
9,808
95% CI
-7/7
Release Date 2026-01 · Matched as FLUX.2 [klein] 4B
Artificial Analysis APIExamples
Loading examples…
Related image models
Compare FLUX.2 [klein] 4B with similar models from the same provider or model family.
FLUX.2 [klein] 9B
flux-2-klein-9bFLUX.2 [klein] 9B is a high-quality 9B-parameter text-to-image model from Black Forest Labs with enhanced realism and crisper text rendering. Supports flexible sizing, JPEG/PNG/WebP output, and prompt-based edits with up to three reference images.
FLUX Virtual Try-On
flux-pro/v1/vtoVirtual try-on model that applies a garment reference image to a person image using styling instructions.
FLUX.2 [flash]
flux-2-flashFLUX.2 [flash] is a fast text-to-image model built for low-latency, high-volume generation with realistic renders and crisp on-image text. A strong default for rapid iteration, batch pipelines, and production creatives.
FLUX.2 [flash] Edit
flux-2-flash-image-to-imageFLUX.2 [flash] Edit delivers prompt-based image editing for fast style shifts, background changes, and targeted retouching while keeping composition stable.
FLUX.2 [turbo]
flux-2-turboFLUX.2 [turbo] is a speed-optimized image model for real-time workflows with strong prompt adherence and clean typography. Generate from text or upload up to four reference images for fast edits and variations.
FLUX.2 [turbo] Edit
flux-2-turbo-image-to-imageFLUX.2 [turbo] Edit delivers ultra-fast prompt-based image updates while preserving composition and identity cues.