falImage to imageComing soon

ideogram/v4.5/edit

Name: ideogram/v4.5/edit
Brand: fal

ideogram/v4.5/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.

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
`prompt` required	text	—	The generation or editing prompt.
`image_url` required	URL or file	—	Primary source image to edit.
`reference_image_urls`	URLs or files	—	Up to four references plus the primary source, or three references plus the primary source and mask.
`mask_url`	URL or file	—	Mask matching the source dimensions. Black edits, white preserves. Must contain both regions after rounding.
`edit_precision`	one of regular, high	regular	regular uses Generate; high uses Precise Edit with unchanged-pixel restoration. Both always prepare structured edit instructions.
`quality`	one of very_low, low, medium, high	medium	Quality tier for either edit precision. Defaults to medium.
`image_size`	JSON	auto	auto preserves source geometry, downscaled by the provider if needed. Only unmasked regular edits accept named presets or custom sizes: dimensions >=256, multiples of 32, area <=4194304, ratio <=6:1. Named presets use standard fal dimensions.
`num_images`	number (whole) 1 to 8	1	Number of images to generate.
`seed`	number (whole)	—	Random seed. Omit to choose automatically.

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": "ideogram/v4.5/edit",
    "input": {
      "prompt": "A colorful storefront with a sign reading hello",
      "image_url": "<image_url>"
    }
  }'