SJinn
GPT-Image-2

GPT-Image-2

Generate and edit high-quality images using OpenAI's GPT-Image-2 model with support for reference images and aspect ratio control

Tool Overview

The GPT-Image-2 tool provides access to OpenAI's latest image generation model. It supports text-to-image generation and image editing with reference pictures, delivering high-quality results across a variety of aspect ratios.

Tool Identifier

gpt-image-2-api

Parameters

Required Parameters

prompt

  • Type: string (required)
  • Description: Text description of the image to generate or edit
  • Validation: Must be a non-empty string
  • Example: "A futuristic city skyline at dusk with glowing neon lights"

Optional Parameters

image_list

  • Type: string[] (optional)
  • Default: [] (empty array, text-to-image mode)
  • Format: Array of complete HTTP/HTTPS URLs (e.g., ["https://cdn.sjinn.ai/uploads/image.jpg"])
  • Validation: If provided, must be an array with non-empty string elements

aspect_ratio

  • Type: string (optional)
  • Default: "auto"
  • Supported Values:
    • "auto" - Automatically select the optimal aspect ratio
    • "1:1" - Square format
    • "16:9" - Widescreen landscape
    • "9:16" - Portrait mobile
    • "3:2" - Classic landscape
    • "2:3" - Classic portrait
  • Validation: If an unsupported value is provided, defaults to "auto"

Pricing

  • 100 credits per task

Request Examples

Text-to-Image

curl -X POST https://sjinn.ai/api/un-api/create_tool_task \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "tool_type": "gpt-image-2-api",
    "input": {
      "prompt": "A futuristic city skyline at dusk with glowing neon lights",
      "aspect_ratio": "16:9"
    }
  }'

Image Editing with Reference

curl -X POST https://sjinn.ai/api/un-api/create_tool_task \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "tool_type": "gpt-image-2-api",
    "input": {
      "prompt": "Make the background a snowy mountain landscape",
      "image_list": ["https://cdn.sjinn.ai/uploads/photo.jpg"],
      "aspect_ratio": "3:2"
    }
  }'

Using JavaScript

const response = await fetch('https://sjinn.ai/api/un-api/create_tool_task', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    tool_type: 'gpt-image-2-api',
    input: {
      prompt: 'A futuristic city skyline at dusk with glowing neon lights',
      aspect_ratio: '16:9',
    },
  }),
});

const result = await response.json();
console.log('Task ID:', result.data.task_id);

Using Python

import requests

url = 'https://sjinn.ai/api/un-api/create_tool_task'
headers = {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
}
data = {
    'tool_type': 'gpt-image-2-api',
    'input': {
        'prompt': 'A futuristic city skyline at dusk with glowing neon lights',
        'image_list': ['https://cdn.sjinn.ai/uploads/reference.jpg'],
        'aspect_ratio': '16:9'
    }
}

response = requests.post(url, json=data, headers=headers)
result = response.json()
print('Task ID:', result['data']['task_id'])

Response Examples

Success Response

{
  "success": true,
  "errorMsg": "",
  "error_code": 0,
  "data": {
    "task_id": "550e8400-e29b-41d4-a716-446655440000"
  }
}

Error Response (Invalid Parameters)

{
  "success": false,
  "errorMsg": "prompt is required",
  "error_code": 400
}

Best Practices

  1. Prompt Optimization:

    • Use detailed, descriptive prompts for best results
    • Include style, lighting, and mood descriptions
    • Specify camera angle or perspective if needed (e.g., "aerial view", "close-up portrait")

  2. Reference Image Usage:

    • Provide high-quality, publicly accessible image URLs
    • Use reference images to guide style or subject consistency
    • Multiple reference images can be combined for complex edits

  3. Aspect Ratio Selection:

    • Use "1:1" for social media square posts
    • Use "16:9" for banners and widescreen content
    • Use "9:16" for mobile/story format
    • Leave as "auto" to let the model decide based on the prompt

Related Links