Ideogram Character 是 Ideogram AI 推出的最新功能,可确保角色在不同场景、艺术风格和设定中保留面部特征、体型比例和发型等核心特征。无论是基于单张参考图创建角色,还是微调现有角色,Kie.ai 的 Ideogram 角色 API 都能通过其基础(Base)、编辑(Edit)和二创(Remix)操作,为您提供极高的灵活性与精准度。

Model Type:
Pricing: Ideogram Character costs 12 credits ($0.06) Turbo, 18 credits ($0.09) Balanced, 24 credits ($0.12) Quality. High-tier top-ups (+10% bonus) bring effective pricing down to ~$0.055 (Turbo), ~$0.082 (Balanced), and ~$0.109 (Quality).
Input

The prompt to fill the masked part of the image.

0/5000

Click to upload or drag and drop

Supported formats: JPEG, PNG, WEBP Maximum file size: 10MB; Maximum files: 5

A set of images to use as character references. Currently only 1 image is supported, rest will be ignored. (maximum total size 10MB across all character references). The images should be in JPEG, PNG or WebP format

The rendering speed to use. Default value: "BALANCED"

The style type to generate with. Cannot be used with style_codes. Default value: "AUTO"

Determine if MagicPrompt should be used in generating the request or not. Default value: true

Select description

The resolution of the generated image Default value: square_hd

Seed for the random number generator

Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt. Default value: ""

0/5000

A configurable parameter. Defaults to true in the Playground.

There is no guarantee that everything can be filtered out; if you are not satisfied with the results, you will need to make your own arrangements.
Output
output typeimage
Generated output
Examples

Explore different use cases and parameter configurations

README

Complete guide to using ideogram/character

Ideogram 角色 API:确保角色在任意场景下保持完美一致

Original image
Middle image
Left image
Right image
功能特性Ideogram CharacterNano BananaFlux Kontext
Text and Image Upload SupportSupports single reference image uploads with detailed text prompts for scene and style customizationSupports text prompts and image uploads, with integrated editing for precise modificationsSupports both text prompts and image uploads, with advanced inpainting and depth control
Prompt UnderstandingExcels at interpreting detailed prompts for character placement and style transfer, with automated facial/hair detectionHandles complex, multi-step instructions with high accuracy, ideal for precise text-based editsStrong text-to-image capability with reliable fidelity, enhanced by semantic understanding
Style and ConsistencySuperior Ideogram Character Consistency, preserving character identity across scenes and stylesMaintains character and background stability across variations, with strong scene coherenceProvides stable results with flexible outputs, but may struggle with complex scene relationships
Resolution and DetailHigh-fidelity output with precise detail retention for photorealistic character renderingHigh-resolution output with fine detail retention, especially for character restorationMultiple model tiers (e.g., Dev, Pro, Max) balance detail and performance, up to ~4 MP outputs
5.0/ 5
22,110 ratingsLoved by most users
How was your experience?
  • 01
  • 02
  • 03
  • 04
  • Kie.ai Ideogram 角色 API 常见问题解答