---
title: "Remix an existing image, letting the server pick the best model"
method: POST
path: "/v2/image/remix/auto"
tags: ["auto-model"]
---

# Remix an existing image, letting the server pick the best model

`POST /v2/image/remix/auto`

Transform an existing image with a server-selected model, guided by a
text prompt. Supply the source as `image` bytes (multipart requests
only). `image_weight` controls how closely the result follows the
source; when omitted the selected model chooses its usual strength.

The server chooses a model that supports the requested remix controls:
style references (ad hoc or saved), a color palette, style codes, a
style preset, and a non-`AUTO` style type each
restrict the request to a compatible model and to the 1K tier;
remixes without those controls use the default model. Omit
`resolution` and `aspect_ratio` to keep the source image's shape.
Supplying `image_weight` together with a `resolution` or
`aspect_ratio` that changes the source's aspect ratio routes the
request to a model that crops the source to the new shape; that
combination is served only at the 1K tier and is rejected at 2K.
(The model-pinned remix endpoints such as
`/v2/image/remix/ideogram-v4` reject the combination outright.)
`seed` is honored only on the compatible model; the default model
synthesizes an unseeded instruction prompt, so results are not
reproducible there.

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

- ToolRemixRequest
  - `prompt` string, required — The prompt that guides the remix.
  - `image_asset_identifier` AssetIdentifier — An identifier for an ideogram asset.
    - `asset_type` 'ASSET' | 'CANVAS_ASSET' | 'LAYERED_ASSET' | 'RESPONSE' | 'UPLOAD', required
    - `asset_id` string, required
  - `image` string, binary — The image to transform (max size 50MB), as raw bytes; only JPEG, PNG and WEBP are supported. Multipart requests only. Supply this or `image_asset_identifier`, never both. The bytes are staged for this generation request and are not added to your account's image assets.
  - `image_weight` integer — 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 requires the 1K tier.
  - `negative_prompt` string — Description of what to exclude from the images. Descriptions in the prompt take precedence over descriptions in the negative prompt. Not every model consults it.
  - `resolution` string — The requested output resolution, formatted as "WIDTHxHEIGHT" (for example "1280x800"). The output is served at the closest resolution the selected model supports in the corresponding 1K or 2K tier. Omit `aspect_ratio` when supplying a resolution. If `resolution_tier` is also supplied, it must match the tier implied by these dimensions. Combining a shape-changing value with `image_weight` requires the 1K tier.
  - `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.
  - `resolution_tier` '1K' | '2K' — The output resolution tier. Influences which model serves the request. When omitted, the tier is inferred from `resolution`, or defaults to 1K when no exact resolution is supplied. Inputs that restrict the server's model choice (style references, saved styles, a color palette, style codes, a style preset, or a non-`AUTO` style type) currently support only 1K AUTO remixes.
  - `magic_prompt` 'AUTO' | 'ON' | 'OFF' — Determine if MagicPrompt should be used in generating the request or not.
  - `seed` integer — Optional. Honored when the server selects the model that supports deterministic remixes; the default model synthesizes its own prompt, so results are not reproducible there. The response reports the seed used.
  - `style_reference_asset_identifiers` AssetIdentifier[] — Existing upload or generated image assets whose style should guide the remix, by reference. Supplying style references restricts the server to a model that supports them and requires the 1K resolution tier. Ignored if `style_reference_collection_id` is also supplied.
    - `asset_type` 'ASSET' | 'CANVAS_ASSET' | 'LAYERED_ASSET' | 'RESPONSE' | 'UPLOAD', required
    - `asset_id` string, required
  - `style_reference_collection_id` string — A saved style to apply, by its URL-safe base64 collection id. Takes priority over `style_reference_asset_identifiers`. Restricts the server to a model that supports style references and requires the 1K resolution tier.
  - `style_reference_collection_version_id` string — Optional URL-safe base64 version id pinning a specific version of the `style_reference_collection_id` collection. Ignored without it.
  - `style_preset` '80S_ILLUSTRATION' | '90S_NOSTALGIA' | 'ABSTRACT_ORGANIC' | 'ANALOG_NOSTALGIA' | 'ART_BRUT' | 'ART_DECO' | 'ART_POSTER' | 'AURA' | 'AVANT_GARDE' | 'BAUHAUS' | 'BLUEPRINT' | 'BLURRY_MOTION' | 'BRIGHT_ART' | 'C4D_CARTOON' | 'CHILDRENS_BOOK' | 'COLLAGE' | 'COLORING_BOOK_I' | 'COLORING_BOOK_II' | 'CUBISM' | 'DARK_AURA' | 'DOODLE' | 'DOUBLE_EXPOSURE' | 'DRAMATIC_CINEMA' | 'EDITORIAL' | 'EMOTIONAL_MINIMAL' | 'ETHEREAL_PARTY' | 'EXPIRED_FILM' | 'FLAT_ART' | 'FLAT_VECTOR' | 'FOREST_REVERIE' | 'GEO_MINIMALIST' | 'GLASS_PRISM' | 'GOLDEN_HOUR' | 'GRAFFITI_I' | 'GRAFFITI_II' | 'HALFTONE_PRINT' | 'HIGH_CONTRAST' | 'HIPPIE_ERA' | 'ICONIC' | 'JAPANDI_FUSION' | 'JAZZY' | 'LONG_EXPOSURE' | 'MAGAZINE_EDITORIAL' | 'MINIMAL_ILLUSTRATION' | 'MIXED_MEDIA' | 'MONOCHROME' | 'NIGHTLIFE' | 'OIL_PAINTING' | 'OLD_CARTOONS' | 'PAINT_GESTURE' | 'POP_ART' | 'RETRO_ETCHING' | 'RIVIERA_POP' | 'SPOTLIGHT_80S' | 'STYLIZED_RED' | 'SURREAL_COLLAGE' | 'TRAVEL_POSTER' | 'VINTAGE_GEO' | 'VINTAGE_POSTER' | 'WATERCOLOR' | 'WEIRD' | 'WOODBLOCK_PRINT' — A predefined style preset that applies a specific artistic style to the generated image.
  - `color_palette` union — A color palette for generation, must EITHER be specified via one of the presets (name) or explicitly via hexadecimal representations of the color with optional weights (members). Not supported by V_1, V_1_TURBO, V_2A and V_2A_TURBO models.
    - ColorPaletteWithPresetName
      - `name` 'EMBER' | 'FRESH' | 'JUNGLE' | 'MAGIC' | 'MELON' | 'MOSAIC' | 'PASTEL' | 'ULTRAMARINE', required — A color palette preset value.
    - ColorPaletteWithMembers — A color palette represented only via its members. Cannot be used in conjunction with preset name.
      - `members` ColorPaletteMember[], required — A list of ColorPaletteMembers that define the color palette. Each color palette member consists of a required color hex and an optional weight between 0.05 and 1.0 (inclusive). It is recommended that these weights descend from highest to lowest for the color hexes provided.
        - `color_hex` string, required — The hexadecimal representation of the color with an optional chosen weight.
        - `color_weight` number — The weight of the color in the color palette.
  - `style_codes` StyleCode[] — 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.
  - `style_type` 'AUTO' | 'GENERAL' | 'REALISTIC' | 'DESIGN' | 'CUSTOM' | 'FICTION' | 'STYLIZED' — The style type to generate with.
  - `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 — Whether the generated images should be kept private. Omitted or true keeps them private. False publishes them unless the caller's plan always generates 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 remixed images (synchronous requests), or an acknowledgement to poll with `GET /v1/generations/{generation_id}` (`async` requests).

- ToolRemixResponse — Response returned by `POST /v2/image/remix/auto`. Synchronous requests (the default) include the remixed 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 server-assigned value attached to the request; AUTO remixes are not reproducible because the selected model may synthesize an unseeded instruction prompt.
  - `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 remixed 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.
- `404` — A referenced source, reference asset, or saved collection was not found.
- `422` — The prompt did not pass safety checks.
- `429` — Too many requests.
- `500` — Internal server error.
- `503` — The endpoint is temporarily unavailable.

## Changes

- **2026-09-16** `a235a15c0235` — 1 info
  - endpoint added

[Change history](https://skmtc.dev/ideogram/apis/ideogram-openapi-3-0/changes/v2/image/remix/auto/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/a235a15c0235?raw)