Image generation

curl --request POST \
  --url https://api.tikway.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "volcengine/doubao-seedream-4.5",
  "prompt": "The scenery of the mountains at sunset, the setting sun reflects the mountains and the sky, the light and shadow are soft, the picture is natural and delicate, and has a cinematic feel.",
  "size": "1024x1024"
}
'

import requests

url = "https://api.tikway.ai/v1/images/generations"

payload = {
    "model": "volcengine/doubao-seedream-4.5",
    "prompt": "The scenery of the mountains at sunset, the setting sun reflects the mountains and the sky, the light and shadow are soft, the picture is natural and delicate, and has a cinematic feel.",
    "size": "1024x1024"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'volcengine/doubao-seedream-4.5',
    prompt: 'The scenery of the mountains at sunset, the setting sun reflects the mountains and the sky, the light and shadow are soft, the picture is natural and delicate, and has a cinematic feel.',
    size: '1024x1024'
  })
};

fetch('https://api.tikway.ai/v1/images/generations', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.tikway.ai/v1/images/generations",
  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([
    'model' => 'volcengine/doubao-seedream-4.5',
    'prompt' => 'The scenery of the mountains at sunset, the setting sun reflects the mountains and the sky, the light and shadow are soft, the picture is natural and delicate, and has a cinematic feel.',
    'size' => '1024x1024'
  ]),
  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;
}

package main

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

func main() {

	url := "https://api.tikway.ai/v1/images/generations"

	payload := strings.NewReader("{\n  \"model\": \"volcengine/doubao-seedream-4.5\",\n  \"prompt\": \"The scenery of the mountains at sunset, the setting sun reflects the mountains and the sky, the light and shadow are soft, the picture is natural and delicate, and has a cinematic feel.\",\n  \"size\": \"1024x1024\"\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.tikway.ai/v1/images/generations")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"volcengine/doubao-seedream-4.5\",\n  \"prompt\": \"The scenery of the mountains at sunset, the setting sun reflects the mountains and the sky, the light and shadow are soft, the picture is natural and delicate, and has a cinematic feel.\",\n  \"size\": \"1024x1024\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.tikway.ai/v1/images/generations")

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  \"model\": \"volcengine/doubao-seedream-4.5\",\n  \"prompt\": \"The scenery of the mountains at sunset, the setting sun reflects the mountains and the sky, the light and shadow are soft, the picture is natural and delicate, and has a cinematic feel.\",\n  \"size\": \"1024x1024\"\n}"

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

{
  "created": 1788920400,
  "data": [
    {
      "index": 0,
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAA..."
    }
  ],
  "model": "volcengine/doubao-seedream-5.0-pro",
  "size": "2048x2048"
}

Seedream

Image generation

Seedream uses /v1/images/generations. model and prompt are required, response_format is optional.

Model	Dimensions	Other parameters
`volcengine/doubao-seedream-5.0-pro`	2K, 3K or compliant `WIDTHxHEIGHT`	`output_format`, `background`, `response_format`, `watermark`, `optimize_prompt_options`
`volcengine/doubao-seedream-4.5`	2K, 4K or compliance `WIDTHxHEIGHT`	`response_format`, `watermark`, `optimize_prompt_options`; transparent background capability is subject to the account upstream

Transparent backgrounds must also be used with output_format=png. The current specification does not expose group diagram control and reference diagram fields.

POST

https://api.tikway.ai

images

generations

Image generation

curl --request POST \
  --url https://api.tikway.ai/v1/images/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "volcengine/doubao-seedream-4.5",
  "prompt": "The scenery of the mountains at sunset, the setting sun reflects the mountains and the sky, the light and shadow are soft, the picture is natural and delicate, and has a cinematic feel.",
  "size": "1024x1024"
}
'

import requests

url = "https://api.tikway.ai/v1/images/generations"

payload = {
    "model": "volcengine/doubao-seedream-4.5",
    "prompt": "The scenery of the mountains at sunset, the setting sun reflects the mountains and the sky, the light and shadow are soft, the picture is natural and delicate, and has a cinematic feel.",
    "size": "1024x1024"
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'volcengine/doubao-seedream-4.5',
    prompt: 'The scenery of the mountains at sunset, the setting sun reflects the mountains and the sky, the light and shadow are soft, the picture is natural and delicate, and has a cinematic feel.',
    size: '1024x1024'
  })
};

fetch('https://api.tikway.ai/v1/images/generations', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://api.tikway.ai/v1/images/generations",
  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([
    'model' => 'volcengine/doubao-seedream-4.5',
    'prompt' => 'The scenery of the mountains at sunset, the setting sun reflects the mountains and the sky, the light and shadow are soft, the picture is natural and delicate, and has a cinematic feel.',
    'size' => '1024x1024'
  ]),
  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;
}

package main

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

func main() {

	url := "https://api.tikway.ai/v1/images/generations"

	payload := strings.NewReader("{\n  \"model\": \"volcengine/doubao-seedream-4.5\",\n  \"prompt\": \"The scenery of the mountains at sunset, the setting sun reflects the mountains and the sky, the light and shadow are soft, the picture is natural and delicate, and has a cinematic feel.\",\n  \"size\": \"1024x1024\"\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.tikway.ai/v1/images/generations")
  .header("Authorization", "Bearer <token>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"volcengine/doubao-seedream-4.5\",\n  \"prompt\": \"The scenery of the mountains at sunset, the setting sun reflects the mountains and the sky, the light and shadow are soft, the picture is natural and delicate, and has a cinematic feel.\",\n  \"size\": \"1024x1024\"\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.tikway.ai/v1/images/generations")

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  \"model\": \"volcengine/doubao-seedream-4.5\",\n  \"prompt\": \"The scenery of the mountains at sunset, the setting sun reflects the mountains and the sky, the light and shadow are soft, the picture is natural and delicate, and has a cinematic feel.\",\n  \"size\": \"1024x1024\"\n}"

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

{
  "created": 1788920400,
  "data": [
    {
      "index": 0,
      "b64_json": "iVBORw0KGgoAAAANSUhEUgAA..."
    }
  ],
  "model": "volcengine/doubao-seedream-5.0-pro",
  "size": "2048x2048"
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Use Doubao Seedream 5.0 Pro to generate images from text.

model

enum<string>

required

Required. Forward exposes the model ID. The gateway forwards to the OFOX OpenAI Images compatible interface according to the doubao/seedream model family.

Available options:

volcengine/doubao-seedream-5.0-pro,

volcengine/doubao-seedream-4.5

prompt

string

required

Pictures generate prompt words. Official recommendations are no more than about 300 Chinese characters or 600 English words.

Minimum string length: 1

Example:

"A future city floating on the sea of clouds, with movie-level light and shadow and rich architectural details at sunrise"

size

doubao-seedream-5.0: Supports 2K, 3K or specified width and height pixel values; default 2048x2048; total pixel range [2560x1440, 3072x3072x1.1025]; aspect ratio range [1/16, 16]. doubao-seedream-4.5: Supports 2K, 4K or specified width and height pixel values; default 2048x2048; total pixel range [2560x1440, 4096x4096]; aspect ratio range [1/16, 16]. doubao-seedream-4.0: Supports 1K, 2K, 4K or specified width and height pixel values; default 2048x2048; total pixel range [1280x720, 4096x4096]; aspect ratio range [1/16, 16].

Available options:

auto,

1K,

1.5K,

2K

output_format

enum<string>

default:jpeg

Output picture format. Transparent backgrounds must use png.

Available options:

png,

jpeg

background

enum<string>

default:opaque

Output background. transparent can only be used with output_format=png.

Available options:

opaque,

transparent

response_format

enum<string>

default:b64_json

Response format. b64_json returns Base64; url returns a temporary image link; the default is b64_json.

Available options:

b64_json,

url

watermark

boolean

default:true

Whether to add a watermark to the generated image.

optimize_prompt_options

object

Volcano engine prompt word optimization settings.

Hide child attributes

optimize_prompt_options.mode

enum<string>

required

Prompt word optimization mode. Standard gives priority to effect, and fast gives priority to speed.

Available options:

standard,

fast

Response

200 - application/json

Doubao Seedream 5.0 Pro image generation successful response.

created

integer<int64>

required

Image creation time, Unix timestamp, unit is seconds.

Required range: x >= 0

data

object[]

required

Generate results. The model returns one image at a time.

Required array length: 1 element

Option 1
Option 2

Hide child attributes

data.b64_json

string

required

Base64 encoded image; returned when response_format=b64_json.

Minimum string length: 1

data.index

integer

Results index.

Required range: x >= 0

data.url

string<uri>

Temporary image link; returned when response_format=url.

model

string

The model ID that actually executes the request.

size

string

actual generated size.

Pattern: ^[1-9][0-9]*x[1-9][0-9]*$

output_format

enum<string>

Actual output format.

Available options:

png,

jpeg

background

enum<string>

The actual background type used.

Available options:

opaque,

transparent

usage

object

The usage information generated this time.

Hide child attributes

usage.input_tokens

integer

Enter the number of tokens.

Required range: x >= 0

usage.input_tokens_details

object

Hide child attributes

usage.input_tokens_details.text_tokens

integer

The number of tokens consumed by the prompt word.

Required range: x >= 0

usage.input_tokens_details.image_tokens

integer

Enter the number of tokens consumed by the image.

Required range: x >= 0

usage.output_tokens

integer

Output the number of tokens.

Required range: x >= 0

usage.total_tokens

integer

Total number of tokens.

Required range: x >= 0

usage.generated_images

integer

Number of images generated.

Required range: x >= 0

Chat completions