--- title: "Generate images with Ideogram 4.5, from a prompt or by transforming source images" method: POST path: "/v2/image/generate/ideogram-4-5" tags: ["images-generate"] --- # Generate images with Ideogram 4.5, from a prompt or by transforming source images `POST /v2/image/generate/ideogram-4-5` 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. ## Query parameters - `dry_run` boolean ## Request body - GenerateImageIdeogram45Request — Source images are optional. When supplied, the request becomes an image-to-image transform and `size` defaults to "auto" (derived from the first source). A prompt is required either way. - `prompt` string, 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. - `image_asset_identifiers` AssetIdentifier[] — Existing upload or generated image assets to transform, by reference. Takes priority over `images` if both are supplied. The first source is the primary image; any further sources are additional references. Supplying sources turns the request into an image-to-image transform. - `asset_type` 'ASSET' | 'CANVAS_ASSET' | 'LAYERED_ASSET' | 'RESPONSE' | 'UPLOAD', required - `asset_id` string, required - `images` string[] — 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. - `mask` string, 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. - `size` string, 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` 'very_low' | 'low' | 'medium' | 'high' | 'very_high' | 'ultra' — The rendering quality to use. Higher quality renders take longer. `very_low` requires source images and is the fastest and cheapest. `very_high` and `ultra` require source images. `very_high` supports at most 4 images per request, takes longer than `high`, and is priced higher. `ultra` returns one image per request, takes longer than `very_high`, and is priced higher again. - `seed` integer — Random seed. Set for reproducible generation. - `num_images` integer — The number of images to generate. - `enable_copyright_detection` boolean, nullable — Optional. Opt this request into post-generation copyright detection. Adds detection latency; flagged images come back with `is_image_safe: false`. - `async` boolean — 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_url` string, 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. - `private` boolean, 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_id` string — A collection you can write to, by its URL-safe base64 collection id. The output images are added to it when the request completes. ## Response `200` The generated images (synchronous requests), or an acknowledgement to poll with `GET /v1/generations/{generation_id}` (`async` requests). - GenerateImageIdeogram45Response — Response returned by `POST /v2/image/generate/ideogram-4-5`. Synchronous requests (the default) include the generated images in `data`. Requests with `async` set to true omit `data`; poll for completion and results with `GET /v1/generations/{generation_id}` using the returned `generation_id`. The seed reports the value the request resolved to when the caller left it unset. - `generation_id` string, required — URL-safe base64 ID of the accepted generation. Accepted by the `GET /v1/generations/{generation_id}` polling endpoint. - `data` GeneratedImageObject[] — The generated images, in generation order. Present only for synchronous requests (`async` omitted or false). - `url` string, uri, nullable — The direct link to the generated image. Empty when the image did not pass safety checks. - `prompt` string, required — The final prompt the image was generated from. - `resolution` string, required — The resolution of the generated image, formatted as "WIDTHxHEIGHT". - `is_image_safe` boolean, required — Whether the image passed safety checks. If false, `url` is empty. - `seed` integer, required — Random seed. Set for reproducible generation. - `seed` integer, required — Random seed. Set for reproducible generation. ## Other responses - `400` — Invalid input provided. - `401` — Unauthorized. - `402` — Insufficient credits or quota. - `422` — The prompt did not pass safety checks. - `429` — Too many requests. - `500` — Internal server error. - `503` — The endpoint is temporarily unavailable. ## Changes - **2026-09-27** `9d8521b55c3d` — 4 info - added the new `ultra` enum value to the request property `quality` (media type: multipart/form-data) - added the new `ultra` enum value to the request property `quality` (media type: application/json) - added the new `very_low` enum value to the request property `quality` (media type: multipart/form-data) - added the new `very_low` enum value to the request property `quality` (media type: application/json) - **2026-09-27** `987f73fc82de` — 6 info - added the new `very_high` enum value to the request property `quality` (media type: multipart/form-data) - added the new `very_high` enum value to the request property `quality` (media type: application/json) - added the optional property `max_inflight_requests` to the response with the `402` status - added the optional property `max_inflight_requests` to the response with the `429` status - …2 more - **2026-09-25** `52c1c6497d87` — 4 breaking, 2 warning, 6 info - the request property `prompt` became required (media type: multipart/form-data) - the request property `prompt` became required (media type: application/json) - the `prompt` request property's minLength was increased from `0` to `1` (media type: multipart/form-data) - the `prompt` request property's minLength was increased from `0` to `1` (media type: application/json) - …8 more - **2026-09-19** `4e95197be44a` — 1 info - endpoint added [Change history](https://skmtc.dev/ideogram/apis/ideogram-openapi-3-0/changes/v2/image/generate/ideogram-4-5/post.md) --- [API](https://skmtc.dev/ideogram/apis/ideogram-openapi-3-0.md) · [All operations](https://skmtc.dev/ideogram/apis/ideogram-openapi-3-0/llms.txt) · [OpenAPI document](https://skmtc.dev/ideogram/apis/ideogram-openapi-3-0/revisions/9d8521b55c3d?raw)