falImage to imageComing soon

fal-ai/image2pixel

Name: fal-ai/image2pixel
Brand: fal

fal-ai/image2pixel 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.

Price pending

Pricing

Price pending.

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

Field	Kind	Default	Description
`image_url` required	URL or file	—	The image URL to process into improved pixel art
`max_colors`	number (whole) 1 to 256	32	Maximum number of colors in the output palette. Set None to disable limit.
`auto_color_detect`	true or false	false	Enable automatic detection of optimal number of colors.
`fixed_palette`	list	—	Optional fixed color palette as hex strings (e.g., ['#000000', '#ffffff']).
`detect_method`	one of auto, runs, edge	auto	Scale detection method to use.
`scale`	number (whole) 1 to 64	—	Force a specific pixel scale. If None, auto-detect.
`downscale_method`	one of dominant, median, mode, mean, content-adaptive	dominant	Downscaling method to produce the pixel-art output.
`trim_borders`	true or false	false	Trim borders of the image.
`transparent_background`	true or false	false	Remove background of the image. This will check for contiguous color regions from the edges after correction and make them transparent.
`cleanup_morph`	true or false	false	Apply morphological operations to remove noise.
`cleanup_jaggy`	true or false	false	Remove isolated diagonal pixels (jaggy edge cleanup).
`snap_grid`	true or false	true	Align output to the pixel grid.
`alpha_threshold`	number (whole) 0 to 255	128	Alpha binarization threshold (0-255).
`dominant_color_threshold`	number 0 to 1	0.05	Dominant color threshold (0.0-1.0).
`background_tolerance`	number (whole) 0 to 255	0	Background tolerance (0-255).
`background_mode`	one of edges, corners, midpoints	corners	Controls where to flood-fill from when removing the background.

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/image2pixel",
    "input": {
      "image_url": "https://storage.googleapis.com/falserverless/example_inputs/image2pixel-input.jpg"
    }
  }'