falImage to imageComing soon

fal-ai/uso

fal-ai/uso 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

$0.13 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
prompttextText prompt for generation. Can be empty for pure style transfer.
input_image_urls requiredlist—List of image URLs in order: [content_image, style_image, extra_style_image].
image_sizeJSONsquare_hdThe size of the generated image.
negative_prompttextWhat you don't want in the image. Use it to exclude unwanted elements, styles, or artifacts.
num_inference_stepsnumber (whole)
1 to 50
28Number of denoising steps. More steps can improve quality but increase generation time.
guidance_scalenumber
1 to 10
4How closely to follow the prompt. Higher values stick closer to the prompt.
keep_sizetrue or falsefalsePreserve the layout and dimensions of the input content image. Useful for style transfer.
num_imagesnumber (whole)
1 to 4
1Number of images to generate in parallel.
seednumber (whole)—Random seed for reproducible generation. Use same seed for consistent results.
output_formatone of
jpeg, png
pngOutput image format. PNG preserves transparency, JPEG is smaller.

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/uso",
    "input": {
      "input_image_urls": [
        "<input_image_urls>"
      ]
    }
  }'