Remix with automatic model selection
Remix an image guided by a text prompt, with Ideogram choosing the
model. Upload the source image as image using multipart/form-data.
Returns results directly by default; set async or supply a
webhook_url to get a generation_id and poll
GET /v2/generations/{generation_id}.
Authentication
API key for access control. Use in the header with the name "Api-Key"
Query parameters
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
A request to remix one image with an automatically selected model. Send it as multipart/form-data with the source image.
The image to remix (max 50MB; JPEG, PNG, or WEBP). Multipart requests only. The image is used only for this request and is not saved to your account.
Optional. How closely the result should follow the source image, from 1 to 100. When omitted the selected model chooses its usual strength. Combining a weight with a resolution or aspect_ratio that changes the source's aspect ratio crops the source to the new shape; this is only available at the 1K tier and is rejected at 2K.
The requested output resolution, formatted as "WIDTHxHEIGHT" (for example "1280x800"). The output uses the closest supported resolution in the matching 1K or 2K tier. Omit aspect_ratio when supplying a resolution. If resolution_tier is also supplied, it must match the tier these dimensions fall in. Combining a shape-changing value with image_weight requires the 1K tier.
The requested output aspect ratio. Omit it to keep the source image's shape. auto also keeps the source shape. Omit resolution when supplying a concrete value. Combining a shape-changing value with image_weight requires the 1K tier.
The output resolution tier. When omitted, the tier is inferred from resolution, or defaults to 1k. A color palette, style codes, style preset, or non-auto style type are only supported at 1k.
Controls magic prompt (automatic prompt rewriting). Defaults to auto. The selected model decides how to interpret it.
Optional. Only honored when the request uses a model that supports reproducible remixes; results from the default model are not reproducible. The response reports the seed used.
A list of 8-character hexadecimal codes representing the style of the image. Refer to each endpoint for supported combinations with style types, presets, and reference images.
The style type to generate with. A value other than auto limits the request to a model that supports it and requires the 1K resolution tier.
Optional. Run copyright detection on the generated images. Adds latency; flagged images are returned with is_image_safe: false.
When false (the default), the request waits until the images are ready and returns them in data. When true, the request returns as soon as it is accepted; poll GET /v2/generations/{generation_id} with the returned generation_id for the result.
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.
Response
The remixed images (synchronous requests), or an acknowledgement to poll with GET /v2/generations/{generation_id} (async requests).
URL-safe base64 ID of the generation. Use it to poll
GET /v2/generations/{generation_id}.
The remixed images, in generation order. Present only for synchronous requests (async omitted or false).