Generate transparent-background images with Ideogram 4.0

Generate one or more images on a transparent background with Ideogram 4.0, delivered as PNGs with alpha. The prompt accepts either natural language or a structured Ideogram 4.0 JSON prompt; a structured prompt is consumed directly and skips magic prompt, except that its background description is replaced with a transparent-background directive.

magic_prompt controls how a natural-language prompt is prepared: AUTO/ON rewrite and expand the prompt before generation, while OFF keeps your wording and only converts the prompt into the structured format the model consumes.

output_resolution selects the output tier (1K to 8K); tiers above 2K are produced by upscaling after generation.

By default the request blocks until the images are ready and returns them in data. Set async to true to return immediately after the request is accepted, then poll for completion and results with GET /v1/generations/{generation_id} using the returned generation_id.

Request body

promptstring required

The prompt to generate images from. Accepts either natural language or a structured Ideogram 4.0 JSON prompt; the server detects which was supplied. A structured JSON prompt is consumed by the model directly and skips magic prompt, except that its background description is replaced with a transparent-background directive.

magic_prompt'AUTO' | 'ON' | 'OFF'

Determine if MagicPrompt should be used in generating the request or not.

seedinteger

Random seed. Set for reproducible generation.

num_imagesinteger

The number of images to generate.

aspect_ratio'AUTO' | '1x4' | '1x3' | '1x2' | '9x16' | '10x16' | '2x3' | '3x4' | '4x5' | '1x1' | '5x4' | '4x3' | '3x2' | '16x10' | '16x9' | '2x1' | '3x1' | '4x1'

The aspect ratio for an Ideogram 4.0 magic prompt. AUTO lets the model select the most suitable ratio from the prompt; any other value pins the ratio. The non-AUTO values are the buckets the 4.0 model supports.

output_resolution'1K' | '2K' | '4K' | '8K'

The output resolution tier for the generated images. Tiers are total-pixel budgets matching a square of the named size (for example, 8K delivers at most 8192x8192 total pixels); wide and tall aspect ratios keep the same pixel budget, so a single dimension may exceed the named size. Defaults to 1K.

rendering_speed'TURBO' | 'DEFAULT' | 'QUALITY'

The rendering speed to use.

enable_copyright_detectionboolean nullable

Optional. Opt this request into post-generation copyright detection. Adds detection latency; flagged images come back with is_image_safe: false.

asyncboolean

When false (the default), the request blocks until the images are ready and returns them in data. When true, the request returns as soon as it is accepted; poll for completion and results with GET /v1/generations/{generation_id} using the returned generation_id.

Example request

{
  "magic_prompt": "",
  "aspect_ratio": null,
  "async": false,
  "seed": 12345,
  "rendering_speed": "DEFAULT",
  "enable_copyright_detection": true,
  "output_resolution": "1K",
  "prompt": "prompt",
  "num_images": 1
}

Response

The generated images (synchronous requests), or an acknowledgement to poll with GET /v1/generations/{generation_id} (async requests).

generation_idstring required

URL-safe base64 ID of the accepted generation. Accepted by the GET /v1/generations/{generation_id} polling endpoint.

seedinteger required