Black Forest Labs/black-forest-labs-flux-2-klein-9b/Released Jan 2026

FLUX.2 Klein 9B

Compact, fast text-to-image model

Fine-tunable
Image

About FLUX.2 Klein 9B

FLUX.2 Klein 9B from Black Forest Labs is a lightweight version of the FLUX.2 family featuring 9 billion parameters, designed for efficient text-to-image generation with support for various aspect ratios and quality settings. It accepts text prompts and optional image inputs for reference, producing high-quality PNG, JPEG, or WebP images. Key features include customizable inference steps (1-50), guidance scale, and seed control for reproducible results. Ideal for real-time applications and resource-constrained environments.

Ready to build with FLUX.2 Klein 9B?

Try FLUX.2 Klein 9B in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.

curl -sSf -X POST https://hub.oxen.ai/api/ai/images/edit \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer $OXEN_API_KEY" \
    -d '{
  "model": "black-forest-labs-flux-2-klein-9b",
  "prompt": "A cat sitting on a chair",
  "aspect_ratio": "16:9",
  "output_quality": "standard",
  "output_format": "png",
  "num_inference_steps": 28,
  "guidance_scale": 2
}'

Request parameters

Every field FLUX.2 Klein 9B accepts in the request body. See the API reference for response formats.

POSThttps://hub.oxen.ai/api/ai/images/edit
FieldTypeRequiredDefaultDescription
promptstringYes
Text description of the image to generate. Use @Image1, @Image2, etc. to reference the input images.
input_imagearray<string>
nullable
No
Input images to transform or use as reference. Reference them in the prompt as @Image1, @Image2, etc.
aspect_ratiostringNo"16:9"
1:116:99:164:33:4
output_qualitystringNo"standard"Quality setting for output image
standardhigh
output_formatstringNo"png"Format of the output image
pngjpgwebp
seedintegerNo
Random seed. Leave blank to randomize
num_inference_stepsintegerNo28Number of denoising steps
Range: 150
guidance_scalenumberNo2Scale for classifier-free guidance
Range: 010