SeedEdit（Image Command Editing）

POST

/doubao/drawing/seededit

Image Editing Model from Doubao
SeedEdit is a diffusion model capable of modifying a given image using any text prompt. Designed specifically for image editing tasks, it has achieved new breakthroughs in generality, controllability, and high quality. By leveraging innovative, multi-scale, and multi-rule data acquisition and filtering schemes, it enables precise editing based on any input instruction.

Core Advantages：
1）High-precision Instruction Comprehension with Support for Chinese, English, and Specialized Terms
2）High-quality Editing Results: Focused Target Editing Without "Over-editing" the Original Image：SeedEdit can flexibly, precisely, and quickly select targets for editing while preserving the integrity of the original image to the greatest extent.
3）Efficient and Innovative Model for Diverse Styles and Natural Aesthetics：Users can easily achieve a wide variety of editing tasks, such as changing backgrounds, altering styles, adding or removing objects, and replacing elements, simply by fine-tuning instructions. This greatly enhances editing efficiency.

Introduction：https://www.volcengine.com/docs/6791/1384311

Price：0.05 PTC/call

Request

Header Params

Authorization

string

required

Example:

Bearer {{YOUR_API_KEY}}

Body Params application/json

prompt

string

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."

image_urls

string

required

Image File URL.This algorithm requires a input image

seed

integer

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

scale

number

optional

Influence of Text Description
Default value: 3.5
Value range: [1, 10]

return_url

boolean

optional

Specifies whether the output should include an image link (the link will be valid for 24 hours)

logo_info

object

optional

Watermark information

add_logo

boolean

optional

position

integer

optional

The position of the watermark can be set as follows:

0: Bottom right (default)

1: Bottom left

2: Top left

3: Top right

language

integer

optional

The language of the watermark can be set as follows:

0: Chinese (AI生成) (default)

1: English (Generated by AI)

opacity

number

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_content

string

optional

Custom content for visible watermark

Example

{
    "image_urls": [
        "https://xxx"
    ],
    "prompt": "让他生气",
    "negative_prompt": "",
    "seed": -1,
    "scale": 0.5,
    "return_url": true,
    "logo_info": {
        "add_logo": false,
        "position": 0,
        "language": 0,
        "logo_text_content": "这里是明水印内容"
    }
}

Request samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location --request POST 'https://api.302.ai/doubao/drawing/seededit' \
--header 'Authorization: Bearer sk-jls4AaVBGoe1GwZD64qZA1qyKTN1MPHa4NmvH1cT68z7K1Zz' \
--header 'Content-Type: application/json' \
--data-raw '{
    "image_urls": [
        "https://xxx"
    ],
    "prompt": "让他生气",
    "negative_prompt": "",
    "seed": -1,
    "scale": 0.5,
    "return_url": true,
    "logo_info": {
        "add_logo": false,
        "position": 0,
        "language": 0,
        "logo_text_content": "这里是明水印内容"
    }
}'

Responses

🟢200OK

application/json

Body

completed_at

string

required

created_at

string

required

error

string

required

string

required

model

string

required

output

string

required

started_at

string

required

status

string

required

Example

{
    "completed_at": "",
    "created_at": "",
    "error": "",
    "id": "",
    "model": "",
    "output": "",
    "started_at": "",
    "status": ""
}

Modified at 2025-01-14 09:36:59

Edit（Image Edition）

Character（Character Feature Preservation）