images-generate

Generate images with Ideogram 4.5, from a prompt or by transforming source images

Generate one or more images with Ideogram 4.5. Supplying source images turns the request into an image-to-image transform: the model conditions on the sources, the prompt becomes optional guidance, and size may be "source" to keep the first source's own size or "auto" to let the server pick the canvas from the sources and the prompt. Provide sources either as image_asset_identifiers references or as raw images bytes (multipart requests only); if both are supplied, the references win and the bytes are ignored. The prompt accepts either natural language or a structured Ideogram 4.0 JSON prompt; the server detects which was supplied.

magic_prompt controls automatic prompt rewriting: auto (the default) and on rewrite a natural-language prompt, a prompt that is already a valid structured JSON prompt is always consumed directly, and off disables rewriting entirely so the model receives your prompt verbatim.

Ideogram 4.5 renders a fixed set of output sizes. When size is omitted, the server picks a supported size automatically based on the prompt, and on the source images when there are any.

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.

Supplying a webhook_url makes the request asynchronous whatever async says: the response returns as soon as the request is accepted, and the finished result is POSTed to that URL.

post/v2/image/generate/ideogram-4-5

Query parameters

dry_runboolean

When true, the request is validated and priced but not run: nothing is generated, stored, or billed, and no safety review is performed. The response is a PriceQuote object instead of the usual response for this endpoint. Send exactly the request you would send to generate, so the quote reflects the same options.

Request body

promptstring required

The prompt to generate images from, or the edit instruction to apply when source images are supplied. Accepts either natural language or a structured Ideogram 4.0 JSON prompt; the server detects which was supplied.

magic_prompt'auto' | 'on' | 'off'

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

imagesstring[]

The source images to transform (max 5, max size 25MB per image), as raw bytes; only JPEG, PNG, and WEBP formats are supported. Multipart requests only; ignored if image_asset_identifiers is also supplied.

maskstring binary

An optional mask confining the edit to part of the first source image, as raw bytes (multipart requests only; JPEG, PNG, or WEBP, max 25MB). Black marks the area to edit and white the area to preserve; values in between are rounded to whichever is nearer. The mask must have the same width and height as the first source image, and must contain both black and white areas. Requires source images uploaded as raw images bytes; masks cannot be combined with image_asset_identifiers. The mask is supplied to the model as an additional reference image, so a masked request may carry at most three other source images. Supplying a mask fixes the output to the first source's own size, so size is rejected alongside it.

sizestring nullable

The output size: "auto", "source" or an exact "WIDTHxHEIGHT".

Without source images, an exact size must be one of the supported 1K/2K presets (for example 1024x1024, 2048x2048 or 1440x2880); "auto" or omitted lets the server pick a supported size based on the prompt. "source" is rejected because there is no source image to size from.

With source images, "auto" (the default) lets the server pick a supported 2K size from the source images and the prompt, and "source" returns the output at the first source image's own width and height. With "source", a source too large for the model is scaled down to fit while keeping its exact proportion. Whatever the size, every source image's aspect ratio must be between 1:6 and 6:1; the model does not accept a reference outside that range.

An exact size must have both dimensions multiples of 32 and at least 256px, the total size at most 2048x2048 pixels, and the aspect ratio at most 6:1. Naming one reshapes the source to it.

Pricing is tiered by the resolved output pixels: up to 1024x1024 bills as 1K, above that as 2K. An "auto" size bills as 2K.

quality'low' | 'medium' | 'high'

The rendering quality to use. Higher quality renders take longer.

seedinteger

Random seed. Set for reproducible generation.

num_imagesinteger

The number of images to generate.

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.

webhook_urlstring uri

HTTPS URL that Ideogram delivers the generated result to. Ideogram sends a JSON POST to this URL once all images for the request have finished generating. The body mirrors the synchronous generate response: request_id, created, and a data array containing every generated image (url, prompt, resolution, seed, is_image_safe). Each delivery is signed with Ed25519 and verifiable against the public keys at https://api.ideogram.ai/v1/.well-known/jwks.json. Must be HTTPS; private and loopback hosts and the cloud metadata service are rejected.

privateboolean nullable

When true or omitted, the output is kept private to your account. Set to false to publish the output to the public feed. Enterprise accounts always generate privately.

target_collection_idstring

A collection you can write to, by its URL-safe base64 collection id. The output images are added to it when the request completes.

Example request

{
  "magic_prompt": "on",
  "image_asset_identifiers": [
    {
      "asset_type": "RESPONSE",
      "asset_id": "7uS_VESkRI6O3-sVgHQp_A"
    }
  ],
  "size": "2048x2048",
  "seed": 12345,
  "webhook_url": "https://api.example.com/webhooks/ideogram"
}

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