​

Image Models Overview

​

Available Models

​

DALL-E Models (OpenAI)

• DALL-E 3: Latest model with improved quality and prompt adherence
• DALL-E 2: Reliable image generation with good quality

​

Flux Models (Black Forest Labs)

• Flux Pro: Professional-grade image generation
• Flux Dev: Development version with fast iteration
• Flux Schnell: Ultra-fast image generation

​

Stable Diffusion Models

• Stable Diffusion 3.5: Latest open-source model
• Stable Diffusion XL: High-resolution image generation
• Stable Diffusion Turbo: Fast generation with fewer steps

​

Midjourney

• Midjourney v6: Artistic and creative image generation
• Midjourney Niji: Anime and illustration focused

​

Model Capabilities

​

Image Generation API

POST /v1/images/generations

​

Basic Example

curl -X POST "https://api.anyapi.ai/v1/images/generations" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dall-e-3",
    "prompt": "A serene mountain landscape at sunset",
    "size": "1024x1024",
    "quality": "hd",
    "n": 1
  }'

​

Response Format

{
  "created": 1589478378,
  "data": [
    {
      "url": "https://cdn.anyapi.ai/images/generated/abc123.png",
      "revised_prompt": "A detailed mountain landscape at sunset with dramatic lighting and cloud formations"
    }
  ]
}

​

Image Editing API

POST /v1/images/edits

​

Example: Inpainting

import requests

# Upload image file
files = {
    'image': open('original.png', 'rb'),
    'mask': open('mask.png', 'rb')
}

data = {
    'model': 'dall-e-2',
    'prompt': 'Add a rainbow in the sky',
    'size': '1024x1024',
    'n': 1
}

response = requests.post(
    "https://api.anyapi.ai/v1/images/edits",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    files=files,
    data=data
)

​

Image Variations API

POST /v1/images/variations

import requests

files = {'image': open('original.png', 'rb')}

data = {
    'model': 'dall-e-2',
    'n': 3,
    'size': '1024x1024'
}

response = requests.post(
    "https://api.anyapi.ai/v1/images/variations",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    files=files,
    data=data
)

​

Model Comparison

​

Advanced Features

​

Style Control

{
  "prompt": "A cat in the style of Van Gogh's Starry Night",
  "style": "vivid",
  "quality": "hd"
}

​

Aspect Ratios

• Square: 1024x1024, 1536x1536
• Portrait: 1024x1792, 1536x2048
• Landscape: 1792x1024, 2048x1536

​

Quality Settings

• Standard: Default quality, faster generation
• HD: Higher quality, more detailed images

​

Prompt Engineering

​

Best Practices

1. Be specific: Include details about style, lighting, composition
2. Use descriptive adjectives: “vibrant”, “moody”, “minimalist”
3. Specify camera settings: “shot with 85mm lens”, “shallow depth of field”
4. Include style references: “in the style of…”, “photorealistic”

​

Example Prompts

​

Pricing

​

Rate Limits

​

Content Policy

• No harmful, offensive, or inappropriate content
• Respect copyright and intellectual property
• No generation of real people without consent
• Commercial use allowed with proper licensing

​

Common Use Cases

​

Image Formats

• Input: PNG, JPEG, WebP (for editing/variations)
• Output: PNG (default), JPEG available for some models
• Maximum file size: 20MB for uploads
• Recommended: PNG for best quality

​

Getting Started