Skip to main content
IdeogramMediumUltra

Ideogram Character

Generate consistent characters from a single reference image. Render the same character in many styles — realistic or fiction — insert them into existing photos with mask inpainting, and rely on Ideogram's signature text rendering for legible signs and typography.

350 credits
per image at Default rendering — Turbo 230, Default 350, Quality 470 credits
Consistent characters from just one reference image
Auto, Fiction, or Realistic character style types
Mask inpainting to add your character to an existing image
Three rendering speeds (Turbo/Default/Quality) with tiered pricing
Ideogram's signature accurate text rendering inside images

Run it right now

Test this model instantly in the Console Playground — no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "ideogram-ai/ideogram-character",
  "input": {
    "prompt": "a close up photo of a woman in a fashion magazine photoshoot",
    "resolution": "None",
    "style_type": "Auto",
    "aspect_ratio": "1:1",
    "magic_prompt_option": "Auto",
    "character_reference_image": "https://example.com/character.webp"
  }
}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringYes-Text prompt for image generation
maskstringNo-A black and white image. Black pixels are inpainted, white pixels are preserved. Resized to match the image size
seedintegerNo-Random seed. Set for reproducible generation
imagestringNo-An image file to use for inpainting. You must also use a mask
resolutionstringNoNoneExact output resolution (e.g. 1024x1024) from ~69 supported presets between 512x1536 and 1536x512. Overrides aspect_ratio; ignored for inpainting
None512x1536576x1408576x1472576x1536640x1344640x1408640x1472640x1536704x1152704x1216704x1280704x1344704x1408704x1472736x1312768x1088768x1216768x1280768x1344800x1280832x960832x1024832x1088832x1152832x1216832x1248864x1152896x960896x1024896x1088896x1120896x1152960x832960x896960x1024960x10881024x8321024x8961024x9601024x10241088x7681088x8321088x8961088x9601120x8961152x7041152x8321152x8641152x8961216x7041216x7681216x8321248x8321280x7041280x7681280x8001312x7361344x6401344x7041344x7681408x5761408x6401408x7041472x5761472x6401472x7041536x5121536x5761536x640
style_typestringNoAutoThe character style type
AutoFictionRealistic
aspect_ratiostringNo1:1Aspect ratio. Ignored if a resolution or inpainting image is given
1:33:11:22:19:1616:910:1616:102:33:23:44:34:55:41:1
rendering_speedstringNoDefaultRendering speed. Turbo is faster and cheaper (300 credits), Quality is higher quality and more expensive (600 credits), Default is balanced (450 credits)
DefaultTurboQuality
magic_prompt_optionstringNoAutoMagic Prompt interprets and optimizes your prompt to maximize variety and quality. Also enables prompts in other languages
AutoOnOff
character_reference_imagestringYes-An image to use as a character reference

How to Provide File Input

There are 3 ways to provide files for the maskimagecharacter_reference_image parameters:

Recommended

Direct Upload (Multipart)

Attach files directly to POST /v1/predictions/upload. No separate upload step needed.

curl -X POST "https://api.core.today/v1/predictions/upload" \
  -H "X-API-Key: cdt_your_api_key" \
  -F "model=ideogram-ai/ideogram-character" \
  -F 'input={"prompt":"your prompt here"}' \
  -F "file:mask=@your_file.png"

Image URL

Pass a publicly accessible URL directly. You can also use file_url from the Storage API.

{
  "model": "ideogram-ai/ideogram-character",
  "input": {
    "prompt": "your prompt here",
    "mask": "https://example.com/image.jpg"
  }
}
See the File Upload docs for more upload methods including Presigned URLs.

Common Parameters

Common parameters used when calling POST /v1/predictions.

ParameterTypeRequiredDefaultDescription
modelstringYes-Model identifier
inputobjectYes-Object containing the model-specific parameters from the table above
output_folderstringNo-Folder path for output files (max 256 chars, '..' not allowed)
webhook_urlstringNo-Webhook URL to call on completion
is_publicbooleanNofalseIf true, output files are also available via permanent public URLs

Examples

Fashion Photoshoot from a Reference

The reference character rendered in a magazine photoshoot setting

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "ideogram-ai/ideogram-character",
  "input": {
    "prompt": "a close up photo of a woman in a fashion magazine photoshoot",
    "resolution": "None",
    "style_type": "Auto",
    "aspect_ratio": "1:1",
    "magic_prompt_option": "Auto",
    "character_reference_image": "https://example.com/character.webp"
  }
}'

Fast Character Iteration with Turbo

Turbo rendering cuts the price to 300 credits per image

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "ideogram-ai/ideogram-character",
  "input": {
    "prompt": "the character as a barista pouring latte art in a cozy cafe, warm lighting",
    "rendering_speed": "Turbo",
    "style_type": "Realistic",
    "aspect_ratio": "3:4",
    "character_reference_image": "https://example.com/character.webp"
  }
}'

Tips & Best Practices

1Iterate with rendering_speed Turbo (300 credits) and switch to Quality (600 credits) only for final renders
2Use a clear, well-lit reference image of the character's face for the strongest consistency
3For inpainting, provide both image and mask — black mask pixels are replaced, white pixels are preserved
4Take advantage of Ideogram's text rendering: put signs, labels, or titles directly in the prompt in quotes
5resolution overrides aspect_ratio; leave it at None unless you need an exact pixel size
6Only use photos of real people as character references with the person's explicit consent

Use Cases

Character sheets showing the same character in varied poses and outfits
Webtoon, comic, and storybook panels with a recurring protagonist
Compositing a character into existing photos via inpainting
Branded mascot imagery with legible embedded text
Marketing visuals featuring a consistent spokesperson or persona

Model Info

ProviderIdeogram
Version-
CategoryImage Generation
Price350 credits

API Endpoint

POST /v1/predictions
Try in ConsoleBack to Docs