Enterprise AI Resource Hub - 302.AI | Pay-as-you-go, Comprehensive AI model API Access, Instant Online App Usage

Character（Character Feature Preservation）

Image Processing Service from Jimeng

2024-12-19

Image Processing

Pricing:

$0.05/call

Bulk order? Contact your manager for exclusive deals

API Overview

Image generation model from Doutiao

General 2.0—Role Feature Retention (formerly known as General 2.0S—Subject Retention) integrates our self-developed subject retention capability, including subject appearance retention and facial feature retention. The subject appearance information covers various types of subjects such as people, animals, and objects. Both subject appearance and facial features work together with the input text during image generation, producing images whose appearance matches the subject in the reference input image while also aligning with the text description.

Introduction: https://www.volcengine.com/docs/6791/1361423

Price: 0.05 PTC per request

API Console

API Reference (1)

API Description	API Endpoint	Request Method	Stability	Parameter Description
Character（Character Feature Preservation）	https://api.302.ai/doubao/drawing/character	POST	Stable	View Details
Document Details Image generation model from SeedEdit The General 2.0 - Character Feature Preservation model (formerly known as General 2.0S - Subject Preservation) integrates proprietary subject preservation technology, which includes both subject appearance preservation and facial feature preservation.The subject appearance information covers a wide range of subjects, including humans, animals, and objects. During the image generation process, both subject appearance and facial features work together with the input text to produce images that not only align with the appearance of the subject in the reference image but also match the textual description. Introduction：https://www.volcengine.com/docs/6791/1361423 Price：0.05 PTC/call Request Parameters Header Parameters Authorizationstring Required Example Value:`Bearer {{YOUR_API_KEY}}` Request Body application/json promptstring Required Prompts for generating images， input in both Chinese and English You can input prompts in either Chinese or English to generate images. To improve the accuracy of the text written in the image, enclose the desired text in quotation marks. For example: “A Christmas poster with the text ‘Merry Christmas’ written on it.” seedinteger Optional Random seed，Used as the basis to determine the initial state of diffusion. The default value is -1 (random). If the random seed is set to the same positive integer and all other parameters remain identical, the generated images are highly likely to be consistent. Default value: -1 scalenumber Optional Influence of Text Description Default value: 3.5 Value range: [1, 10] return_urlboolean Optional Specifies whether the output should include an image link (the link will be valid for 24 hours) logo_infoobject Optional Watermark information add_logoboolean Optional positioninteger Optional The position of the watermark can be set as follows: 0: Bottom right (default) 1: Bottom left 2: Top left 3: Top right languageinteger Optional The language of the watermark can be set as follows: 0: Chinese (AI生成) (default) 1: English (Generated by AI) opacitynumber Optional The opacity of the watermark can be set within the range of 0 to 1, where 1 represents fully opaque. The default value is 0.3 logo_text_contentstring Optional Custom content for visible watermark image_urlsstring Required Image File URL.This algorithm requires a input image ddim_stepsinteger Optional Steps for Image Generation Default Value：9 Value Range：[1, 200] widthinteger Optional Width of Generated Image (Before Upscaling) Default Value：512 Value Range：[256, 768] heightinteger Optional Height of Generated Image (Before Upscaling) Default Value：512 Value Range：[256, 768] cfg_rescalenumber Optional Default Value：0.7 ref_ip_weightnumber Optional Weight of Reference Image’s Subject Appearance The higher the weight, the greater the similarity between the generated result and the subject in the reference image. Default Value：0.7 Value Range：[0, 1] ref_id_weightnumber Optional Weight of facial features from reference image，the higher the weight, the greater the similarity between the generated result and the facial features in the reference image. Default Value: 0.36 Value Range: [0, 1] Recommended Range: [0.2, 0.4] use_srboolean Optional true：Text-to-Image + AIGC Upscaling false：Text-to-Image Default Value：true

API Pricing

$￥円 ₽

Model	Description	302.AI Price