WaveSpeedAI APIIdeogram AIIdeogram AI Ideogram Character

Ideogram Ai Ideogram Character

Ideogram Ai Ideogram Character

Playground

Try it on WavespeedAI!

Generate consistent characters from a single reference image. Outputs can be in many styles. You can also use inpainting to add your character to an existing image.

Features

Ideogram Character

Ideogram Character is a character consistency model designed to generate variations of characters using a single reference image. The model maintains visual consistency across different scenes and contexts while preserving the core identity of the subject, working with both real and fictional characters.

Core Functionality

The model operates by taking a single reference photograph and generating variations of the character depicted. It maintains fidelity to the original character while adapting them to new environments, contexts, and artistic styles. Character definition is handled automatically through facial and hair detection algorithms that identify key features defining the character’s identity.

Technical Specifications

Input Requirements

  • Single reference image with clear facial features
  • Text prompts for scene description

Processing Method

The system processes input images by automatically detecting facial features and hair characteristics that form the core identity map. This map is preserved across all generated variations, ensuring character consistency regardless of the new context or style applied.

Applications and Limitations

The model excels at maintaining character consistency across varied scenarios, supporting contextual placement in new environments, artistic style transfers, and scene composition. Performance depends heavily on reference image quality, with clear facial features being essential for optimal results.

Complex poses, extreme viewing angles, or poor image quality may impact consistency. Additionally, aggressive style transfers may sometimes compromise fine detail preservation in favor of stylistic adaptation.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/ideogram-ai/ideogram-character" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "style": "Auto",
    "rendering_speed": "Default",
    "aspect_ratio": "1:1",
    "enable_base64_output": false
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
promptstringYes-The prompt to generate an image from.
imagestringYes-An image to use as a character reference.
stylestringNoAutoAuto, Fiction, RealisticThe character style type. Auto, Fiction, or Realistic.
rendering_speedstringNoDefaultDefault, Turbo, QualityRendering speed. Turbo for faster and cheaper generation, quality for higher quality and more expensive generation, default for balanced.
aspect_ratiostringNo1:11:1, 16:9, 9:16, 4:3, 3:4The aspect ratio of the generated image.
enable_base64_outputbooleanNofalse-If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Query Parameters

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction, the ID of the prediction to get
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2025 WaveSpeedAI. All rights reserved.