Seedream 5.0 Lite Edit

curl --request POST \
  --url https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "preserve composition, convert to watercolor style with rich texture and soft shadows",
  "image": [
    "https://example.com/input-1.jpg",
    "https://example.com/input-2.jpg"
  ]
}
'

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    prompt: 'preserve composition, convert to watercolor style with rich texture and soft shadows',
    image: ['https://example.com/input-1.jpg', 'https://example.com/input-2.jpg']
  })
};

fetch('https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit"

payload = {
    "prompt": "preserve composition, convert to watercolor style with rich texture and soft shadows",
    "image": ["https://example.com/input-1.jpg", "https://example.com/input-2.jpg"]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit"

	payload := strings.NewReader("{\n  \"prompt\": \"preserve composition, convert to watercolor style with rich texture and soft shadows\",\n  \"image\": [\n    \"https://example.com/input-1.jpg\",\n    \"https://example.com/input-2.jpg\"\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"prompt\": \"preserve composition, convert to watercolor style with rich texture and soft shadows\",\n  \"image\": [\n    \"https://example.com/input-1.jpg\",\n    \"https://example.com/input-2.jpg\"\n  ]\n}")
  .asString();

const url = 'https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    prompt: 'preserve composition, convert to watercolor style with rich texture and soft shadows',
    image: ['https://example.com/input-1.jpg', 'https://example.com/input-2.jpg']
  })
};

fetch(url, options)
  .then(res => res.json())
  .then(json => console.log(json))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'prompt' => 'preserve composition, convert to watercolor style with rich texture and soft shadows',
    'image' => [
        'https://example.com/input-1.jpg',
        'https://example.com/input-2.jpg'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

require 'uri'
require 'net/http'

url = URI("https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"prompt\": \"preserve composition, convert to watercolor style with rich texture and soft shadows\",\n  \"image\": [\n    \"https://example.com/input-1.jpg\",\n    \"https://example.com/input-2.jpg\"\n  ]\n}"

response = http.request(request)
puts response.read_body

import Foundation

let parameters = [
  "prompt": "preserve composition, convert to watercolor style with rich texture and soft shadows",
  "image": ["https://example.com/input-1.jpg", "https://example.com/input-2.jpg"]
] as [String : Any?]

let postData = try JSONSerialization.data(withJSONObject: parameters, options: [])

let url = URL(string: "https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit")!
var request = URLRequest(url: url)
request.httpMethod = "POST"
request.timeoutInterval = 10
request.allHTTPHeaderFields = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
request.httpBody = postData

let (data, _) = try await URLSession.shared.data(for: request)
print(String(decoding: data, as: UTF8.self))

$headers=@{}
$headers.Add("Authorization", "Bearer <token>")
$headers.Add("Content-Type", "application/json")
$response = Invoke-WebRequest -Uri 'https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit' -Method POST -Headers $headers -ContentType 'application/json' -Body '{
  "prompt": "preserve composition, convert to watercolor style with rich texture and soft shadows",
  "image": [
    "https://example.com/input-1.jpg",
    "https://example.com/input-2.jpg"
  ]
}'

{
  "code": 0,
  "message": "success",
  "data": {
    "status": "pending",
    "task_id": "task-abc123",
    "model_id": "model-123",
    "get_result": {
      "method": "GET",
      "url": "https://api.modellix.ai/api/v1/tasks/task-abc123"
    }
  }
}

Seedream 5.0 Lite Edit

[Core Function] Seedream 5.0 Lite Edit is a reasoning-enhanced, smart image editing model. [Strengths] It features superior cross-modal understanding and reasoning, allowing for highly accurate, interactive multi-turn image editing with real-time knowledge enhancement. [Best For] Highly recommended for: complex image editing tasks, structural modifications, and edits requiring deep semantic understanding. [Limitations] As a ‘Lite’ model, raw visual rendering might not match the 4.5 tier. [Routing] Use this model by default for complex, reasoning-based image editing tasks.

POST

bytedance

seedream-5.0-lite-edit

curl --request POST \
  --url https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "preserve composition, convert to watercolor style with rich texture and soft shadows",
  "image": [
    "https://example.com/input-1.jpg",
    "https://example.com/input-2.jpg"
  ]
}
'

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    prompt: 'preserve composition, convert to watercolor style with rich texture and soft shadows',
    image: ['https://example.com/input-1.jpg', 'https://example.com/input-2.jpg']
  })
};

fetch('https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit"

payload = {
    "prompt": "preserve composition, convert to watercolor style with rich texture and soft shadows",
    "image": ["https://example.com/input-1.jpg", "https://example.com/input-2.jpg"]
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit"

	payload := strings.NewReader("{\n  \"prompt\": \"preserve composition, convert to watercolor style with rich texture and soft shadows\",\n  \"image\": [\n    \"https://example.com/input-1.jpg\",\n    \"https://example.com/input-2.jpg\"\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Authorization", "Bearer <token>")
	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"prompt\": \"preserve composition, convert to watercolor style with rich texture and soft shadows\",\n  \"image\": [\n    \"https://example.com/input-1.jpg\",\n    \"https://example.com/input-2.jpg\"\n  ]\n}")
  .asString();

const url = 'https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit';
const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    prompt: 'preserve composition, convert to watercolor style with rich texture and soft shadows',
    image: ['https://example.com/input-1.jpg', 'https://example.com/input-2.jpg']
  })
};

fetch(url, options)
  .then(res => res.json())
  .then(json => console.log(json))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'prompt' => 'preserve composition, convert to watercolor style with rich texture and soft shadows',
    'image' => [
        'https://example.com/input-1.jpg',
        'https://example.com/input-2.jpg'
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: Bearer <token>",
    "Content-Type: application/json"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

require 'uri'
require 'net/http'

url = URI("https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Authorization"] = 'Bearer <token>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"prompt\": \"preserve composition, convert to watercolor style with rich texture and soft shadows\",\n  \"image\": [\n    \"https://example.com/input-1.jpg\",\n    \"https://example.com/input-2.jpg\"\n  ]\n}"

response = http.request(request)
puts response.read_body

import Foundation

let parameters = [
  "prompt": "preserve composition, convert to watercolor style with rich texture and soft shadows",
  "image": ["https://example.com/input-1.jpg", "https://example.com/input-2.jpg"]
] as [String : Any?]

let postData = try JSONSerialization.data(withJSONObject: parameters, options: [])

let url = URL(string: "https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit")!
var request = URLRequest(url: url)
request.httpMethod = "POST"
request.timeoutInterval = 10
request.allHTTPHeaderFields = [
  "Authorization": "Bearer <token>",
  "Content-Type": "application/json"
]
request.httpBody = postData

let (data, _) = try await URLSession.shared.data(for: request)
print(String(decoding: data, as: UTF8.self))

$headers=@{}
$headers.Add("Authorization", "Bearer <token>")
$headers.Add("Content-Type", "application/json")
$response = Invoke-WebRequest -Uri 'https://api.modellix.ai/api/v1/bytedance/seedream-5.0-lite-edit' -Method POST -Headers $headers -ContentType 'application/json' -Body '{
  "prompt": "preserve composition, convert to watercolor style with rich texture and soft shadows",
  "image": [
    "https://example.com/input-1.jpg",
    "https://example.com/input-2.jpg"
  ]
}'

{
  "code": 0,
  "message": "success",
  "data": {
    "status": "pending",
    "task_id": "task-abc123",
    "model_id": "model-123",
    "get_result": {
      "method": "GET",
      "url": "https://api.modellix.ai/api/v1/tasks/task-abc123"
    }
  }
}

Authorizations

Authorization

string

header

required

API Key authentication. Format: Bearer YOUR_API_KEY.

Body

application/json

prompt

string

required

Image editing instruction, supports Chinese and English. Maximum 10000 characters. We recommend keeping the prompt under 600 words. Excessively long prompts may scatter information, causing the model to overlook details and focus only on major elements, which can result in missing details in the generated image.

Required string length: 1 - 10000

Example:

"Convert this image to a watercolor painting style"

image

string[]

required

Input image array (1-14 images). Each image must be <= 10 MB. Supported formats: JPEG, PNG, WEBP, BMP, TIFF, GIF.

Required array length: 1 - 14 elements

Example:

[
  "https://example.com/input-1.jpg",
  "https://example.com/input-2.jpg"
]

size

string

default:2048x2048

Image size in format 'widthxheight'. Seedream 5.0 Lite supports custom 2K/3K resolutions.

Example:

"2304x1728"

sequential_image_generation

enum<string>

default:disabled

Batch generation mode. 'auto': model-controlled batch generation, 'disabled': generate single image only.

Available options:

auto,

disabled

Example:

"auto"

sequential_image_generation_max_images

integer

default:5

Maximum number of images for batch generation. This value is an upper limit, actual generated count may be less.

Required range: 1 <= x <= 15

Example:

3

optimize_prompt_mode

enum<string>

default:standard

Prompt optimization mode. Only 'standard' mode is supported.

Available options:

standard

Example:

"standard"

output_format

enum<string>

default:jpeg

Output image format. Supported values: 'jpeg' and 'png'.

Available options:

jpeg,

png

Example:

"png"

Response

200 - application/json

Task submitted successfully

code

integer

required

Response code, 0 indicates success

Example:

0

message

string

required

Response message

Example:

"success"

data

object

required

Detailed data about the submitted asynchronous task.

Show child attributes

Media Models

Get Result

File

Else

STT Result Schema

Seedream 5.0 Lite Edit

Authorizations

Body

Response