How to Use Our API

The Visual AI API allows you to generate images programmatically using both standard visual styles and custom-trained models. This guide will walk you through everything you need to know to get started.

To use the API, you first need to generate an API key from your dashboard.

1. Log in to your Visual AI account
2. Navigate to **Settings** → **API Keys** tab
3. Click on **Generate New Key** button
4. Enter a name for your API key (e.g., 'Production API', 'Development Key')
5. Click **Generate** and copy your API key immediately

All image generation requests should be sent to the following endpoint:

The API uses Bearer token authentication. Include your API key in the Authorization header of every request.

Send a JSON payload in the request body with the following parameters:

Choose from our pre-built visual styles for different use cases:

You can use your own trained models by specifying the model name. Custom models use your training data to generate images that match your brand style.

1. Train a custom model in the **Train Model** section of your dashboard
2. Upload training pairs (text prompts + reference images)
3. Wait for training to complete
4. Use your custom model name in the API request
5. The API will automatically detect and use your custom model's style

Here are complete examples of API requests:

curl -X POST https://yourapp.com/api/v1/generate \
  -H "Authorization: Bearer vsk_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A beautiful sunset over mountains",
    "model": "infographic"
  }'

curl -X POST https://yourapp.com/api/v1/generate \
  -H "Authorization: Bearer vsk_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Create a product launch banner",
    "model": "jayakannan-test"
  }'

const response = await fetch('https://yourapp.com/api/v1/generate', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer vsk_your_api_key_here',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    prompt: 'A futuristic city at night',
    model: 'photo'
  })
});

const data = await response.json();
console.log(data.imageUrl);

The API returns a JSON response with the generated image details:

{
  "success": true,
  "imageUrl": "https://supabase-url.com/storage/v1/object/public/visuals/workspace-12/api-visual-123.jpeg",
  "visualId": 456,
  "prompt": "A beautiful sunset over mountains",
  "enhancedPrompt": "A stunning visual representation of a beautiful sunset...",
  "style": "infographic",
  "createdAt": "2025-01-08T12:45:30.123Z",
  "isCustomModel": false,
  "customModelName": null,
  "trainingPairsCount": 0
}

{
  "success": true,
  "imageUrl": "https://supabase-url.com/storage/v1/object/public/visuals/workspace-12/api-visual-789.jpeg",
  "visualId": 789,
  "prompt": "Create a product launch banner",
  "enhancedPrompt": "Enhanced prompt using custom model training data...",
  "style": "custom_jayakannan-test",
  "createdAt": "2025-01-08T12:50:15.456Z",
  "isCustomModel": true,
  "customModelName": "jayakannan-test",
  "trainingPairsCount": 5
}

If something goes wrong, the API will return an error response:

{
  "error": "Missing or invalid Authorization header"
}

{
  "error": "Invalid API key"
}

{
  "error": "API key is inactive"
}

{
  "error": "Both 'prompt' and 'model' are required in the request body"
}

{
  "error": "Failed to generate image",
  "errorType": "generation_error"
}

Follow these best practices for optimal API usage:

API usage is tracked and logged for each request:

• All API calls are logged with timestamps, response times, and status codes
• Check your usage statistics in the Settings → API Keys section
• Each API key is workspace-specific
• Inactive API keys cannot be used for generation
• Rate limits may apply based on your subscription plan

Need help? Here are additional resources: