Image Generation

Image Generation

curl --request POST \
  --url https://api.gravitex.ai/v1/images/generations \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "prompt": "<string>",
  "response_format": "<string>",
  "contents": [
    {}
  ]
}
'

import requests

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

payload = {
    "model": "<string>",
    "prompt": "<string>",
    "response_format": "<string>",
    "contents": [{}]
}
headers = {
    "Authorization": "<authorization>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<authorization>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    prompt: '<string>',
    response_format: '<string>',
    contents: [{}]
  })
};

fetch('https://api.gravitex.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.gravitex.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' => '<string>',
    'prompt' => '<string>',
    'response_format' => '<string>',
    'contents' => [
        [
                
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <authorization>",
    "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.gravitex.ai/v1/images/generations"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"response_format\": \"<string>\",\n  \"contents\": [\n    {}\n  ]\n}")

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

	req.Header.Add("Authorization", "<authorization>")
	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.gravitex.ai/v1/images/generations")
  .header("Authorization", "<authorization>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"response_format\": \"<string>\",\n  \"contents\": [\n    {}\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

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

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<authorization>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"response_format\": \"<string>\",\n  \"contents\": [\n    {}\n  ]\n}"

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

POST

images

generations

Image Generation

curl --request POST \
  --url https://api.gravitex.ai/v1/images/generations \
  --header 'Authorization: <authorization>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "prompt": "<string>",
  "response_format": "<string>",
  "contents": [
    {}
  ]
}
'

import requests

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

payload = {
    "model": "<string>",
    "prompt": "<string>",
    "response_format": "<string>",
    "contents": [{}]
}
headers = {
    "Authorization": "<authorization>",
    "Content-Type": "application/json"
}

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

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: '<authorization>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    prompt: '<string>',
    response_format: '<string>',
    contents: [{}]
  })
};

fetch('https://api.gravitex.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.gravitex.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' => '<string>',
    'prompt' => '<string>',
    'response_format' => '<string>',
    'contents' => [
        [
                
        ]
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Authorization: <authorization>",
    "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.gravitex.ai/v1/images/generations"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"response_format\": \"<string>\",\n  \"contents\": [\n    {}\n  ]\n}")

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

	req.Header.Add("Authorization", "<authorization>")
	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.gravitex.ai/v1/images/generations")
  .header("Authorization", "<authorization>")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"response_format\": \"<string>\",\n  \"contents\": [\n    {}\n  ]\n}")
  .asString();

require 'uri'
require 'net/http'

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

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

request = Net::HTTP::Post.new(url)
request["Authorization"] = '<authorization>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"model\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"response_format\": \"<string>\",\n  \"contents\": [\n    {}\n  ]\n}"

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

Introduction

The image generation API supports text-to-image, image-to-image, image editing, and more. Through a unified API interface, you can call multiple mainstream image generation models including Gemini, Doubao Seedream, GPT Image, and Tongyi Qianwen.

Authentication

string

required

Bearer Token, e.g. Bearer sk-xxxxxxxxxx

Request Parameters

string

required

Model identifier, supported models include:

Gemini series: gemini-2.5-flash-image (Nano Banana), gemini-3-pro-image-preview (Nano Banana Pro), etc.
Doubao Seedream series: dola-seedream-5-0-pro-260628 (Seedream 5.0 Pro), doubao-seedream-3-0-t2i-250415, doubao-seedream-4-0-250828, doubao-seedream-4-5-251128, doubao-seededit-3-0-i2i-250628, etc.
GPT Image series: gpt-image-2, etc.
Tongyi Qianwen series: qwen-image-plus, qwen-image-edit-plus, etc.

string

Text prompt for text-to-image generation

string

default:"url"

Response format: b64_json or urlNote: Different models have different support for response_format:

Gemini series: Only supports b64_json format, always returns base64-encoded image data regardless of the value passed
Doubao Seedream series: Usually returns URL links, response_format parameter may not take effect
GPT Image series: Only supports b64_json format, forces base64-encoded image data
Tongyi Qianwen series: Supports both b64_json and url, returns the corresponding format based on the parameter value (b64_json will download from URL and convert to base64)

array

Multi-turn content for image-to-image or contextual conversation

Basic Examples

Gemini
Doubao Seedream
GPT Image
Tongyi Qianwen

Text-to-Image
Image-to-Image
Multi-Image Fusion

curl -X POST "https://api.gravitex.ai/v1/images/generations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash-image",
    "prompt": "A cute orange kitten sitting in a garden, sunny day, high quality photography",
    "size": "16:9",
    "quality": "high",
    "n": 1,
    "temperature": 1.1,
    "top_p": 0.95,
    "response_format": "b64_json",
    "image_size": "2K",
    "mime_type": "image/png",
    "response_modalities": "image"
  }'

curl -X POST "https://api.gravitex.ai/v1/images/generations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash-image",
    "size": "16:9",
    "quality": "high",
    "image_size": "3K",
    "temperature": 1.1,
    "top_p": 0.95,
    "response_format": "b64_json",
    "contents": [
      {
        "role": "user",
        "parts": [
          {"text": "Generate an aerial view of Canton Tower based on this image"},
          {"image": "data:image/png;base64,iVBORw0KGgoAAxxxx..."}
        ]
      }
    ]
  }'

curl -X POST "https://api.gravitex.ai/v1/images/generations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-2.5-flash-image",
    "size": "16:9",
    "image_size": "3K",
    "temperature": 1.1,
    "top_p": 0.95,
    "response_format": "b64_json",
    "contents": [
      {
        "role": "user",
        "parts": [
          {"text": "Apply the oil painting style from the first image to the content of the second image"},
          {"image": "https://example.com/style.jpg"},
          {"image": "https://example.com/content.jpg"}
        ]
      }
    ]
  }'

curl -X POST "https://api.gravitex.ai/v1/images/generations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dola-seedream-5-0-pro-260628",
    "prompt": "Futuristic city nightscape, movie poster style",
    "size": "1024x1024",
    "n": 1,
    "watermark": false
  }'

For image-to-image / multi-image fusion, pass an images URL array. See Seedream 5.0 Pro.

curl -X POST "https://api.gravitex.ai/v1/images/generations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-4-0-250828",
    "prompt": "A cute orange kitten sitting in a garden, sunny day, high quality photography",
    "size": "2048x2048",
    "watermark": false,
    "seed": 12345,
    "optimize_prompt_options": {
      "mode": "standard"
    }
  }'

curl -X POST "https://api.gravitex.ai/v1/images/generations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-4-0-250828",
    "prompt": "Change this image to oil painting style",
    "size": "2048x2048",
    "watermark": false,
    "seed": 12345,
    "contents": [
      {
        "role": "user",
        "parts": [
          {"image": "data:image/png;base64,iVBORw0KGgoAAxxxx..."},
          {"text": "Change this image to oil painting style"}
        ]
      }
    ]
  }'

curl -X POST "https://api.gravitex.ai/v1/images/generations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-4-0-250828",
    "prompt": "A cute orange kitten sitting in a garden, sunny day, high quality photography",
    "size": "2048x2048",
    "watermark": false,
    "sequential_image_generation": "auto",
    "sequential_image_generation_options": {
      "max_images": 4
    },
    "optimize_prompt_options": {
      "mode": "standard"
    }
  }'

curl -X POST "https://api.gravitex.ai/v1/images/generations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seededit-3-0-i2i-250628",
    "prompt": "Change this image to oil painting style",
    "watermark": false,
    "guidance_scale": 2.5,
    "seed": 12345,
    "contents": [
      {
        "role": "user",
        "parts": [
          {"image": "data:image/png;base64,iVBORw0KGgoAAxxxx..."},
          {"text": "Change this image to oil painting style"}
        ]
      }
    ]
  }'

curl -X POST "https://api.gravitex.ai/v1/images/generations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-3-0-t2i-250415",
    "prompt": "A cute orange kitten sitting in a garden, sunny day, high quality photography",
    "size": "1024x1024",
    "watermark": false,
    "guidance_scale": 7.5,
    "seed": 12345
  }'

# Standard mode
curl -X POST "https://api.gravitex.ai/v1/images/generations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-4-5-251128",
    "prompt": "A cute kitten",
    "size": "2048x2048",
    "watermark": false,
    "optimize_prompt_options": {
      "mode": "standard"
    }
  }'

# fast mode
curl -X POST "https://api.gravitex.ai/v1/images/generations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-4-0-250828",
    "prompt": "A cute kitten",
    "size": "2048x2048",
    "watermark": false,
    "optimize_prompt_options": {
      "mode": "fast"
    }
  }'

Text-to-Image
Image-to-Image
Multi-Image Fusion

curl -X POST "https://api.gravitex.ai/v1/images/generations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "A cute orange kitten sitting in a garden, sunny day, high quality photography",
    "size": "1024x1024",
    "quality": "high",
    "n": 1
  }'

curl -X POST "https://api.gravitex.ai/v1/images/generations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "Change this image to oil painting style",
    "size": "1024x1024",
    "quality": "high",
    "input_fidelity": "medium",
    "n": 1,
    "image": "data:image/png;base64,iVBORw0KGgoAAxxxx..."
  }'

curl -X POST "https://api.gravitex.ai/v1/images/generations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-image-2",
    "prompt": "Apply the style from the first image to the content of the second image",
    "size": "1024x1024",
    "quality": "high",
    "input_fidelity": "high",
    "n": 2,
    "images": [
      "data:image/png;base64,iVBORw0KGgoAAxxxx...",
      "data:image/png;base64,iVBORw0KGgoAAyyyy..."
    ]
  }'

Text-to-Image
Image Editing

curl -X POST "https://api.gravitex.ai/v1/images/generations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-image-plus",
    "input": {
      "messages": [
        {
          "role": "user",
          "content": [
            {
              "text": "一副典雅庄重的对联悬挂于厅堂之中，房间是个安静古典的中式布置，桌子上放着一些青花瓷，对联上左书“义本生知人机同道善思新”，右书“通云赋智乾坤启数高志远”， 横批“智启通义”，字体飘逸，在中间挂着一幅中国风的画作，内容是岳阳楼。"
            }
          ]
        }
      ]
    },
    "parameters": {
      "negative_prompt": "1",
      "prompt_extend": true,
      "seed": "4",
      "watermark": true
    }
  }'

curl -X POST "https://api.gravitex.ai/v1/images/generations" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-image-edit-plus",
    "input": {
      "messages": [
        {
          "role": "user",
          "content": [
            {
              "image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250925/fpakfo/image36.webp"
            },
            {
              "text": "Generate an image that matches the depth map. Description: a red, worn-out bicycle parked on a muddy path, with a dense primeval forest in the background."
            }
          ]
        }
      ]
    },
    "parameters": {
      "n": 2,
      "negative_prompt": "low quality",
      "watermark": true,
      "size": "2048*2048",
      "seed": 1
    }
  }'

Model-Specific Parameters

Different models support different parameters. Below are detailed parameter descriptions for each model:

Doubao Seedream
GPT Image
Gemini
Tongyi Qianwen

string

doubao-seedream-3-0-t2i-250415 does not support this parameter for input images. Supports URL or Base64 encoding. Among them, doubao-seedream-4.5 and doubao-seedream-4.0 support single-image or multi-image input (see the Multi-Image Fusion example), while doubao-seededit-3.0-i2i only supports single-image input.

string

Image size, supported sizes depend on model version:

doubao-seedream-3.0: 1024x1024, 1152x864, 864x1152, 1280x720, 720x1280, 1248x832, 832x1248, 1512x648
doubao-seedream-4.0/4.5: 2048x2048, 2304x1728, 1728x2304, 2560x1440, 1440x2560, 2496x1664, 1664x2496, 3024x1296 (2K) or 4096x4096, 4704x3520, 3520x4704, 5504x3040, 3040x5504, 4992x3328, 3328x4992, 6240x2656 (4K)

boolean

default:"false"

Whether to add watermark

integer

Random seed for controlling the randomness of generation results. Same seed produces similar results. Range: 0 to 2147483647

number

Guidance scale, controls how closely the generated image matches the prompt. Higher values are stricter, lower values are more free. Recommended range: 1.0-10.0, default: 2.5. Only supported by doubao-seedream-3.0-t2i-250415 and doubao-seededit-3.0-i2i-250628

string

Sequential image generation toggle, only supported by doubao-seedream-4.0 and doubao-seedream-4.5:

"auto": Enable sequential image generation
"disabled": Disable sequential image generation (default)

object

Sequential image generation configuration options, only effective when sequential_image_generation is "auto":

max_images (integer): Maximum number of images, range 1-4, default 4

object

Only doubao-seedream-4.5 (currently only supports standard mode) and doubao-seedream-4.0 support this parameter.

mode (string): Optimization mode
- "standard": Standard mode, higher quality but longer time (default, supported by both 4.0 and 4.5)
- "fast": Fast mode, shorter time but average quality (only 4.0)

string

Image size, supports: 1024x1024, 1024x1536, 1536x1024. Default: 1024x1024

string

default:"high"

Image quality:

"low": Fastest generation speed, lowest cost
"medium": Balance between quality and speed
"high": Highest quality, most detailed (gpt-image-2 default)

integer

default:"1"

Number of images to generate, range: 1-10. Each generation consumes corresponding quota

string

Input fidelity, only effective in image-to-image mode:

"low": More creative freedom, larger differences from original image
"medium": Balance between fidelity and creativity
"high": Preserve original image features, smaller changes
"auto": Automatically select appropriate fidelity

string

Single input image, supports URL or Base64 format (data:image/...;base64,...)

array

Array of multiple input images, supports up to 10 images. Each image supports URL or Base64 format

string

Image aspect ratio, supports: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9. Can also use pixel dimensions (e.g., 1024x1024), and the system will automatically convert them to the corresponding ratio.

string

Image quality, maps to imageSize parameter:

"hd", "high", "2K": Maps to 2K resolution
"standard", "medium", "low", "auto", "1K": Maps to 1K resolution (default)

integer

default:"1"

Number of images to generate (corresponds to sample_count parameter)

string

Aspect ratio, same function as size parameter

string

default:"allow_adult"

Person generation control, default: "allow_adult"

integer

default:"32768"

Output token limit, default: 32768

number

default:"0.95"

Top-P sampling value, range: 0.0-1.0, default: 0.95

string

Image size, supports: 1K (default), 2K, 4K

string

default:"image/png"

Output format, supports: image/png (default), image/jpeg

string

default:"image"

Response modality, supports: image (default), image-text

object

required

Generation parameters object, contains the following fields:

role (string, required): Message sender role, must be set to user.
image (string): Only for qwen-image-edit-plus models. URL or Base64-encoded image data. Supports 1-3 input images. When multiple images are provided, image order is defined by array order, and the output aspect ratio is based on the last image.
n (integer, required): Number of output images, default is 1. For qwen-image-edit-plus series models, you can choose to output 1-6 images. For qwen-image-edit, only 1 image is supported.
negative_prompt (string): Negative prompt, used to exclude unwanted elements
prompt_extend (boolean, default: true): Whether to enable prompt extension. Recommended for short prompts, and recommended to disable for detailed prompts. Only supported by qwen-image-edit-plus series models.
watermark (boolean, default: true): Whether to add watermark
seed (integer): Random seed, range 0-2147483647

Response Format

{
  "code": 200,
  "msg": "Success",
  "data": {
    "data": [
      {
        "url": "",
        "b64_json": "iVBORw0KGgoAAAANSUhEUgAABAAAAAQA...",
        "revised_prompt": ""
      }
    ],
    "created": 1757320007
  }
}

Supported Models

Gemini Series

Model Name: gemini-2.5-flash-image (Nano Banana) Core Capabilities:

✅ Text-to-image (pure text description generates images)
✅ Image-to-image (single image + text generates new image)
✅ Multi-image-to-one (2-5 images fusion generation)
✅ Multi-turn conversational image generation (contextual continuous modification)

Supported Aspect Ratios: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 Image Input: Supports URL and Base64 format, max 7MB Model Name: gemini-3-pro-image-preview (Nano Banana Pro) Core Capabilities:

✅ Text-to-image (pure text description generates images)
✅ Image-to-image (single image + text generates new image)
✅ Multi-image-to-one (2-5 images fusion generation)
✅ Multi-turn conversational image generation (contextual continuous modification)
✅ Higher quality output

Supported Aspect Ratios: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 Image Input: Supports URL and Base64 format, max 7MB

Doubao Seedream Series

Model Name: dola-seedream-5-0-pro-260628 (Seedream 5.0 Pro page) Core Capabilities:

✅ Text-to-image
✅ Image-to-image (single image + text)
✅ Multi-image reference / fusion
✅ Synchronous OpenAI-compatible /v1/images/generations
✅ Supports 1K / 2K or custom WIDTHxHEIGHT
⚠️ Currently returns 1 image per request (images are inputs, not output count)

Reference field: images (URL array) Model Name: doubao-seedream-3-0-t2i-250415 Core Capabilities:

✅ Text-to-image (pure text description generates images)
✅ Supports guidance scale adjustment
✅ Supports random seed control
❌ Does not support image-to-image

Supported Sizes: 1024×1024, 1152×864, 864×1152, 1280×720, 720×1280, 1248×832, 832×1248, 1512×648 Model Name: doubao-seedream-4-0-250828 Core Capabilities:

✅ Text-to-image (pure text description generates images)
✅ Image-to-image (single image + text generates new image)
✅ Multi-image fusion (2-5 images fusion generation)
✅ Sequential image generation
✅ Supports 2K/4K resolution
✅ Supports multiple image formats

Supported Sizes:

2K: 2048×2048, 2304×1728, 1728×2304, 2560×1440, 1440×2560, 2496×1664, 1664×2496, 3024×1296
4K: 4096×4096, 4704×3520, 3520×4704, 5504×3040, 3040×5504, 4992×3328, 3328×4992, 6240×2656

Image Input: Supports JPEG, PNG, WEBP, BMP, TIFF, GIF formats, max 10MB Limitation: Maximum input plus output 15 images, but not recommended to output too many (e.g., 15 text-to-image or 1 input image output 14 images), as more output images take longer time. Model Name: doubao-seedream-4-5-251128 Core Capabilities:

✅ Text-to-image (pure text description generates images)
✅ Image-to-image (single image + text generates new image)
✅ Multi-image fusion (2-5 images fusion generation)
✅ Sequential image generation
✅ Supports 2K/4K resolution
✅ Supports prompt optimization options
✅ Supports multiple image formats

Supported Sizes: Same as doubao-seedream-4-0 Image Input: Supports JPEG, PNG, WEBP, BMP, TIFF, GIF formats, max 10MB Limitation: Maximum input plus output 15 images, but not recommended to output too many (e.g., 15 text-to-image or 1 input image output 14 images), as more output images take longer time. Model Name: doubao-seededit-3-0-i2i-250628 Core Capabilities:

✅ Image editing (single image + text editing)
✅ Supports guidance scale adjustment
✅ Supports random seed control
✅ Image editing (content modification, style transfer, etc.)
❌ Does not support pure text-to-image

Supported Sizes: Adaptive (automatically adjusts based on input image size) Image Input: Supports JPEG, PNG formats, max 10MB, single image

GPT Image Generation Series

Model Name: gpt-image-2 Core Capabilities:

✅ Text-to-image (pure text description generates images)
✅ Image-to-image (up to 10 images + text)
✅ Supports image quality selection
✅ Supports input fidelity adjustment
✅ Multi-image fusion generation

Supported Sizes: 1024×1024, 1024×1536, 1536×1024 Image Quality: low, medium, high Generation Count: Can generate 1-10 images per request Image Input: Supports JPEG, PNG, GIF, WEBP formats, max 10MB, up to 10 images

Tongyi Qianwen Series

Model Name: qwen-image-plus Core Capabilities:

✅ Text-to-image (pure text description generates images)
✅ Chinese and English text rendering (excels at generating complex text in images)
✅ Multiple artistic styles
✅ Intelligent prompt extension
❌ Does not support image-to-image

Supported Sizes: 1328×1328, 1664×928, 928×1664, 1472×1140, 1140×1472 Billing Method: Per image (¥0.18/image) Model Name: qwen-image-edit-plus Core Capabilities:

✅ Image editing (input one image, output up to 6 images)
✅ Modify text in images
✅ Add/remove/move objects
✅ Transfer image styles
✅ Enhance image details

Image Input: Supports JPEG, JPG, PNG, BMP, TIFF, WEBP formats, max 10MB Output Description: Actual output count is affected by image content and editing complexity, can generate up to 6 images

Best Practices

Prompt Optimization Tips

Gemini (Nano Banana)
Doubao Seedream
GPT Image
Tongyi Qianwen

Specify aspect ratio needs: Describe composition direction in the prompt
- Landscape: Use “horizontal composition”, “widescreen view”
- Portrait: Use “vertical composition”, “vertical view”
High-quality keywords:
- “high quality”, “HD”, “professional photography”
- “8k resolution”, “rich details”
Multi-image fusion techniques:
- Clearly describe the role of each image
- Specify fusion method (style transfer, element combination, etc.)

Specify style needs:
- Realistic style: Add “photorealistic”, “ultra-realistic”
- Artistic style: Add “oil painting style”, “watercolor”, “sketch”
- Anime style: Add “anime style”, “2D”, “cartoon”
High-quality keywords:
- “4K resolution”, “8K quality”, “ultra-high details”
- “professional photography”, “cinematic lighting”
Sequential image generation techniques (doubao-seedream-4.x):
- Maintain prompt style consistency
- Use sequential_image_generation parameter to enable sequential mode
- Control max_images parameter to set number of images (1-4 images)
Prompt optimization (doubao-seedream-4.5):
- Use optimize_prompt_options parameter to optimize prompts
- Optional modes: standard (standard), creative (creative), precise (precise)

Specify image quality:
- Use quality parameter to control quality: low, medium, high
- For high-quality images, add descriptive words: “professional photography”, “high detail”, “8K”
Multi-image input techniques:
- Supports up to 10 images input
- Use input_fidelity parameter to control input image fidelity: low, medium, high, auto
- Clearly describe the role of each reference image
Prompt optimization:
- Describe desired image content in detail
- Specify artistic style, lighting conditions, composition method
- Add negative descriptions to exclude unwanted content
Image count control:
- Use n parameter to control generation count (1-10 images)
- For complex scenes, recommend generating multiple images to select the best result

Text rendering techniques:
- Clearly mark text content in quotes in the prompt
- Example: “A poster with title “Summer Sale""
Prompt extension:
- Short prompts: Enable prompt_extend: true
- Detailed prompts: Disable prompt_extend: false
Negative prompts:
- Exclude unwanted elements: “blurry, low quality, watermark”
- Text rendering: “blurry text, typos”

Size Selection Tips

Social Media
Design Purposes

FAQ

General Questions
Gemini (Nano Banana)
Doubao Seedream
GPT Image
Tongyi Qianwen

What image formats are supported?

Different models support different formats:

Gemini: PNG, JPEG, JPG, WEBP, max 7MB
Doubao Seedream 3.0/4.0: JPEG, PNG, max 10MB
Doubao Seedream 4.5: JPEG, PNG, WEBP, BMP, TIFF, GIF, max 10MB
GPT Image: JPEG, PNG, GIF, WEBP, max 10MB
Tongyi Qianwen: JPEG, JPG, PNG, BMP, TIFF, WEBP, max 10MB

How long are generated images valid?

Image URLs are valid for approximately 24 hours. It is recommended to download and save immediately after receiving the response, or upload to your own storage service.

Can I generate multiple images at once?

Tongyi Qianwen series generates 1 image per request. For multiple images, please make multiple concurrent requests.

How to maintain the same aspect ratio in conversation?

In the contents conversation array, each request must include the size parameter, and the system will apply the specified aspect ratio to the current request.

What are the requirements for using URL images?

URLs must be publicly accessible HTTP/HTTPS addresses, supporting formats include PNG, JPEG, JPG, WEBP, max 7MB.

How many images does multi-image fusion support?

Supports 2-5 images input simultaneously, 2-3 images recommended for best results.

Does doubao-seedream-3.0 support image-to-image?

No. doubao-seedream-3-0-t2i-250415 is a pure text-to-image model, only supports generating images through text description.

What image formats does doubao-seedream-4.x support?

doubao-seedream-4.0 and 4.5 support JPEG, PNG, WEBP, BMP, TIFF, GIF formats, max 10MB.

How to use sequential image generation?

Use the sequential_image_generation parameter to enable sequential mode, set to auto. You can control the number of images (1-4 images) through max_images.

What does prompt optimization option do?

doubao-seedream-4.5 supports the optimize_prompt_options parameter, with optional modes: standard (standard), creative (creative), precise (precise), used to optimize prompt effects.

What editing features does doubao-seededit support?

doubao-seededit-3-0-i2i-250628 supports image editing, including content modification, style transfer, detail enhancement, etc., requires input of one image and editing instruction.

What image formats does GPT Image support?

Supports JPEG, PNG, GIF, WEBP formats, max 10MB.

How many images can be input at most?

gpt-image-2 supports up to 10 images input.

How to choose image quality parameter?

quality parameter options: low, medium, high:

low: Fastest generation speed, lowest cost
medium: Balance between quality and speed
high: Highest quality, most detailed

What does input fidelity do?

input_fidelity parameter controls the fidelity of input images, options: low, medium, high, auto:

low: More creative freedom, larger differences from original image
high: Preserve original image features, smaller changes
auto: Automatically select appropriate fidelity

Can I generate multiple images at once?

Yes, use the n parameter to control generation count (1-10 images), each image consumes corresponding quota.

Video Generation

View video generation API documentation

Model List

View all supported model information

API documentation

Chat & text

Safety & audio

Image Series

Video Series

Completions & Embeddings

Interface module

Introduction

Authentication

Request Parameters

Basic Examples

Model-Specific Parameters

Response Format

Supported Models

Gemini Series

Doubao Seedream Series

GPT Image Generation Series

Tongyi Qianwen Series

Best Practices

Prompt Optimization Tips

Size Selection Tips

FAQ

Video Generation

Model List

​Introduction

​Authentication

​Request Parameters

​Basic Examples

​Model-Specific Parameters

​Response Format

​Supported Models

​Gemini Series

​Doubao Seedream Series

​GPT Image Generation Series

​Tongyi Qianwen Series

​Best Practices

​Prompt Optimization Tips

​Size Selection Tips

​FAQ

​Related Resources

Video Generation

Model List

Introduction

Authentication

Request Parameters

Basic Examples

Model-Specific Parameters

Response Format

Supported Models

Gemini Series

Doubao Seedream Series

GPT Image Generation Series

Tongyi Qianwen Series

Best Practices

Prompt Optimization Tips

Size Selection Tips

FAQ

Related Resources