falImage to imageComing soon

fal-ai/flux-2/klein/4b/base/edit

fal-ai/flux-2/klein/4b/base/edit is an image to image tool from fal that runs in the background and returns images. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Priced by usage

Pricing

$0.0117 per megapixel. Each image_size preset counts as 1 MP, and a custom width × height rounds up to whole megapixels. Billed on num_images, default 1. The final charge comes from usage.

Limits

Runs
In the background
Returns
image
Longest queue wait
3600s
Run deadline
1800s
Largest inline input
1024 KB
Largest input file
500 MB
Largest output
4768 MB
Outputs per run
16

Input

FieldKindDefaultDescription
prompt requiredtext—The prompt to edit the image.
negative_prompttextNegative prompt for classifier-free guidance. Describes what to avoid in the image.
guidance_scalenumber
0 to 20
5Guidance scale for classifier-free guidance.
seednumber (whole)—The seed to use for the generation. If not provided, a random seed will be used.
num_inference_stepsnumber (whole)
4 to 50
28The number of inference steps to perform.
image_sizeJSON—The size of the generated image. If not provided, uses the input image size.
num_imagesnumber (whole)
1 to 4
1The number of images to generate.
accelerationone of
none, regular, high
regularThe acceleration level to use for image generation.
output_formatone of
jpeg, png, webp
pngThe format of the generated image.
image_urls requiredURLs or files—The URLs of the images for editing. A maximum of 4 images are allowed.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "fal",
    "model": "fal-ai/flux-2/klein/4b/base/edit",
    "input": {
      "prompt": "Imagine view of Fuji mount. Use style of reference image.",
      "image_urls": [
        "<image_urls>"
      ]
    }
  }'