Skip to content

Ideogram V3 Character

Integrate

Model id ideogram/character
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/ideogram/character?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "reference_image_urls": [
      "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    ]
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

This request: $0.15 150 API credits Run it on this page

Get API key
Ideogram Image Editing Reference inputs #character-consistency

Ideogram V3 generation that keeps a character consistent using a reference image

Ideogram · Image

Your first result goes here

Build a request below and run it with your API key. Outputs are copied to our storage, kept forever or 7 days for free.

Build a request

Controls are generated from the model schema. The code and the price update as you change them.

•required

Prompt describing the fill for the image's masked region.

•required
Drop a file, or

Character reference images in JPEG, PNG, or WebP format, with a combined limit of 10 MB across all character references. Support is currently limited to 1 image; additional images are ignored.

rendering_speed default BALANCED

Speed setting for rendering.

image_size default square_hd

Resolution to use for the output image.

num_images default 1

Count of images to produce.

Advanced negative_prompt · images · reference_mask_urls · style · seed · expand_prompt · style_codes · color_palette
default

Specify unwanted image content, subject to the main prompt's descriptions taking priority over these negative-prompt descriptions.

image_urls
Drop a file, or

Style reference images in JPEG, PNG or WebP format. Their combined size must not exceed 10 MB.

Drop a file, or

Character-reference masks in JPEG, PNG, or WebP format; the total size across all character references cannot exceed 10 MB. Only 1 mask is currently used, with any additional masks ignored.

style default AUTO

Style type used for generation; mutually exclusive with style_codes.

Seed value for random number generation.

Image-style codes, supplied as hexadecimal strings of 8 characters each; omit both style_reference_images and style when using this list.

Color palette used during generation. Specify either a preset through name or explicit hexadecimal colors through members, optionally including weights.

POST /run/ideogram/character?wait=20 quote → $0.15
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.com/v1/run/ideogram/character?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "reference_image_urls": [
      "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    ]
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.com/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"

Run this request

Your key stays in this browser: it is sent only to the Doitong API and saved (localStorage) only if you tick Remember. Get an API key

About Ideogram V3 Character

Generates images of a character from a `prompt` plus a reference in `reference_image_urls` (only 1 image is used). Optional style references go in `image_urls`, with `style_codes`, `color_palette` and `reference_mask_urls` for more control. `rendering_speed` is TURBO, BALANCED or QUALITY, and `num_images` goes up to 8.

Parameters

Send either the canonical name or the native name, not both. Canonical names

NameType DefaultAllowed Description
image_urlsoptional images
Typeurl[] · image
Style reference images in JPEG, PNG or WebP format. Their combined size must not exceed 10 MB.
rendering_speedoptional
Typeenum
DefaultBALANCED
TURBOBALANCEDQUALITY
Speed setting for rendering.
color_paletteoptional
Typeobject
Color palette used during generation. Specify either a preset through name or explicit hexadecimal colors through members, optionally including weights.
color_palette.membersoptional
Typeobject[]
Palette member list defining the palette's colors.
color_palette.members[].rgbrequired
Typeobject
Palette member's color expressed as RGB.
color_palette.members[].color_weightoptional
Typenumber | null
Default0.5
0.05 – 1
Weight assigned to this color within the palette.
color_palette.nameoptional
Typeenum
EMBERFRESHJUNGLEMAGICMELONMOSAICPASTELULTRAMARINE
Preset selection for the color palette.
style_codesoptional
Typestring[]
Image-style codes, supplied as hexadecimal strings of 8 characters each; omit both style_reference_images and style when using this list.
styleoptional
Typeenum
DefaultAUTO
AUTOREALISTICFICTION
Style type used for generation; mutually exclusive with style_codes.
expand_promptoptional
Typeboolean
Defaulttrue
MagicPrompt usage toggle for request generation.
num_imagesoptional num_outputs
Typeinteger
Default1
1 – 8
Count of images to produce.
seedoptional
Typeinteger | null
Seed value for random number generation.
promptrequired
Typestring
Prompt describing the fill for the image's masked region.
image_sizeoptional
Typeobject
Defaultsquare_hd
square_hdsquareportrait_4_3portrait_16_9landscape_4_3landscape_16_9
Resolution to use for the output image.
negative_promptoptional
Typestring
Default
Specify unwanted image content, subject to the main prompt's descriptions taking priority over these negative-prompt descriptions.
reference_image_urlsrequired
Typeurl[] · image
Character reference images in JPEG, PNG, or WebP format, with a combined limit of 10 MB across all character references. Support is currently limited to 1 image; additional images are ignored.
reference_mask_urlsoptional
Typeurl[] · image
Character-reference masks in JPEG, PNG, or WebP format; the total size across all character references cannot exceed 10 MB. Only 1 mask is currently used, with any additional masks ignored.
required Canonical name, also accepted

File parameters take a public https:// URL, a data: URI up to 10 MB, or the file_url of an upload. Files

Output

GET /requests/req_8k2m4q7x1z9c3v5b6n0p2r4t
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "ideogram/character",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 150,
    "usd": "0.15",
    "charged": 150,
    "refunded": 0
  },
  "input": {
    "prompt": "A red fox trots through fresh snow at sunrise, soft golden light, shallow depth of field",
    "reference_image_urls": [
      "https://content.doitong.com/images/showcase/v3/gen_fox_cartoon.jpg"
    ]
  },
  "output": {
    "images": [
      {
        "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
        "content_type": "image/jpeg",
        "file_name": "0-output.jpeg",
        "file_size": 1843200
      }
    ],
    "seed": 42
  },
  "outputs": [
    {
      "type": "image",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "width": 1024,
      "height": 768,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.com/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
Your files, your choiceEvery outputs[].url is a copy on our storage: kept forever (paid per GB-month) or 7 days for free, by your account setting or ?storage=.
Same shape on every modeltype, url, content_type, width, height and duration, for images, video and audio alike. output is the model’s own result object.
Fields of output
images
array of object {url, content_type, file_name, file_size}
seed
integerSeed value used for random number generation.

More models: Image Editing

For AI agents: this page as Markdown is at https://doitong.com/en-US/developers/models/ideogram/character.md. All models and guides: https://doitong.com/developers/llms.txt