Black Forest Labs/flux-2-pro/Released Nov 2025

FLUX.2 [pro]

Professional FLUX.2 image generation

Image

About FLUX.2 [pro]

FLUX.2 [pro] is an image generation model designed for high-fidelity, production-grade visual content and image editing. It excels in producing highly detailed, photorealistic images up to 4 megapixel resolution, with strong prompt adherence, reliable consistency across batch generations, advanced text rendering (including complex typography and multilingual content), and robust multi-reference support for maintaining character, product, or style consistency across images.

Some other noteworthy features of FLUX.2 [pro] include precise control over pose, color (including exact HEX codes), and compositional logic; support for structured (JSON-like) prompts; and efficient, reproducible results suitable for API-driven production workflows.

Ready to build with FLUX.2 [pro]?

Try FLUX.2 [pro] 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": "flux-2-pro",
  "prompt": "Wanderer above the Sea of Fog by Caspar David Friedrich, as the wanderer facing out towards the expanse. The character should be shown from behind, standing on the rocky peak, facing away from the viewer and looking out towards the vast landscape. The background should be in the style of Caspar David Friedrich.",
  "aspect_ratio": "16:9",
  "resolution": "1 MP",
  "num_inference_steps": 30,
  "guidance": 2,
  "output_format": "webp",
  "output_quality": 80,
  "disable_safety_checker": false
}'

Request parameters

Every field FLUX.2 [pro] accepts in the request body. See the API reference for response formats.

POSThttps://hub.oxen.ai/api/ai/images/edit
FieldTypeRequiredDefaultDescription
promptstringYes
Prompt for generated image. 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"
1:116:99:164:33:43:22:3match_input_image
resolutionstringNo"1 MP"
1 MP2 MP0.5 MP
num_inference_stepsintegerNo30Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster.
Range: 150
guidancenumberNo2Guidance for generated image. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5
Range: 010
seedinteger
nullable
No
Random seed. Set for reproducible generation
output_formatstringNo"webp"Format of the output images
webpjpgpng
output_qualityintegerNo80Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
Range: 0100
disable_safety_checkerbooleanNofalseDisable safety checker for generated images.