Midjourney 6.1 - Image Variator

Create variations of existing images using Midjourney's latest 6.1 model. This advanced model offers improved image understanding and generation capabilities with support for character and style references.

Endpoint

POSThttps://api.1min.ai/api/features

Request Body

The request must include the following parameters:

Parameter	Type	Required	Description
type	string	Yes	Feature type identifier. Must be IMAGE_VARIATOR
model	string	Yes	AI model identifier. Must be midjourney_6_1
promptObject	object	Yes	Feature-specific parameters

Prompt Object Parameters

Parameter	Type	Required	Description
imageUrl	string	Yes	Path to the image for variation
aspect_width	number	No	Width aspect ratio (default: 1)
aspect_height	number	No	Height aspect ratio (default: 1)
no	string	No	Negative prompt - elements to exclude from the image
image_weight	number	No	Image prompt weight (0.5-2, default: 1)
seed	number	No	Random seed for reproducible results
tile	boolean	No	Create seamless patterns
stylize	number	No	Stylization strength (0-1000, default: 100)
chaos	number	No	Variation amount (0-100, default: 0)
weird	number	No	Unconventional aesthetics level (0-3000, default: 0)
character_reference	array	No	Array of image URLs for character consistency
style_reference	array	No	Array of image URLs for style consistency

Example Request

JavaScript

fetch('https://api.1min.ai/api/features', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'API-KEY': 'YOUR_API_KEY'
  },
  body: JSON.stringify({
    type: 'IMAGE_VARIATOR',
    model: 'midjourney_6_1',
    promptObject: {
      imageUrl: 'development/images/2025_02_14_17_41_01_211_images.jpeg',
      aspect_width: 16,
      aspect_height: 9,
      stylize: 250,
      chaos: 30,
      character_reference: ['path/to/character_ref.jpg'],
      style_reference: ['path/to/style_ref.jpg']
    }
  })
})

cURL

curl --location 'https://api.1min.ai/api/features' \
--header 'API-KEY: <api-key>' \
--header 'Content-Type: application/json' \
--data '{
"type": "IMAGE_VARIATOR",
"model": "midjourney_6_1",
"promptObject": {
  "imageUrl": "development/images/2025_02_14_17_41_01_211_images.jpeg",
  "aspect_width": 16,
  "aspect_height": 9,
  "stylize": 250,
  "chaos": 30,
  "character_reference": ["path/to/character_ref.jpg"],
  "style_reference": ["path/to/style_ref.jpg"]
}
}'

Python

import requests

url = "https://api.1min.ai/api/features"
headers = {
  "Content-Type": "application/json",
  "API-KEY": "YOUR_API_KEY"
}

data = {
  "type": "IMAGE_VARIATOR",
  "model": "midjourney_6_1",
  "promptObject": {
      "imageUrl": "development/images/2025_02_14_17_41_01_211_images.jpeg",
      "aspect_width": 16,
      "aspect_height": 9,
      "stylize": 250,
      "chaos": 30,
      "character_reference": ["path/to/character_ref.jpg"],
      "style_reference": ["path/to/style_ref.jpg"]
  }
}

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

Responses

Success Response (200)

Successful response contains the generated image variation data. The service will:

1. Analyze your input image to extract a detailed description
2. Apply any character or style references if provided
3. Generate 4 high-quality image variations
4. Return the variation images

{
"success": true,
"data": {
  "resultObject": [
    "path/to/variation1.png",
    "path/to/variation2.png",
    "path/to/variation3.png",
    "path/to/variation4.png"
  ]
}
}

Features & Improvements

Key Differences from v5.2

• Enhanced Image Understanding: Better recognition of subjects, styles, and compositions
• Character References: Maintain consistent characters across variations
• Style References: Apply specific artistic styles consistently
• Improved Quality: Higher resolution and better detail preservation
• Better Prompt Adherence: More accurate interpretation of image descriptions

Advanced Parameters

• Character Reference (character_reference): Upload reference images to maintain character consistency across variations
• Style Reference (style_reference): Apply specific artistic styles from reference images
• Combined References: Use both character and style references for maximum control

Notes

• Midjourney 6.1 automatically generates 4 variations per request
• Character references help maintain consistent facial features and character details
• Style references apply artistic styles while preserving the original subject
• The model offers better photorealism and artistic control compared to v5.2
• Higher stylize values create more artistic and creative interpretations
• Use chaos for more diverse variations between generated images