Ideogram V4

Run it

The smallest request that works: the required fields only.

curl https://api.percify.io/v3/playground/v1/run \
  -H "Authorization: Bearer $PERCIFY_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "modelId": "ideogram-v4",
    "input": {
      "prompt": "A red fox running through fresh snow at sunrise"
    }
  }'

1. EstimatePOST /estimate with the same body returns the price and charges nothing.
2. RunPOST /run returns an id at once, with status processing.
3. CollectGET /generations/{id}?wait=55 returns the file URLs, or pass a webhook.

Parameters

7 fields in input, required first.

• promptRequired
  string

  Text prompt describing the image to generate. Plain language is accepted and automatically expanded into Ideogram's structured caption format.

• imageOptional
  string

  Optional source image (URL) for image-to-image. When provided, the model edits this image guided by the prompt instead of generating from scratch.

• qualityOptional
  low, medium, highDefault medium

  Quality tier (sampling steps). low = fastest, high = best detail.

• strengthOptional
  numberDefault 0.65

  Image-to-image edit strength (only used when an image is provided). Lower = closer to the source, higher = more change.

• resolutionOptional
  1k, 2kDefault 1k

  Output resolution tier by total pixels. 1k ~= 1 MP, 2k ~= 4 MP.

• aspect_ratioOptional
  1:1, 3:2, 2:3, 4:3, 3:4, 16:9, 9:16, 21:9, 9:21Default 1:1

  Output image aspect ratio.

• output_formatOptional
  jpeg, png, webpDefault jpeg

  The format of the generated image.