Image Variation API (/images/variations)

Generate creative variations of existing images using TrueFoundry AI Gateway

Provider capabilities

The table below summarizes gateway support for this endpoint by provider.

Legend:

• ✅ Supported by Provider and Truefoundry
• Provided by provider, but not by Truefoundry
• Provider does not support this feature

Provider	Variation
OpenAI	✅
Azure OpenAI
Bedrock	✅
Vertex
Anthropic
Cohere
Gemini
Groq
Together-AI
xAI
DeepInfra

For every gateway endpoint and provider, see Supported APIs.

TrueFoundry AI Gateway supports image variation capabilities that allow you to generate new versions of existing images while preserving the core visual elements and style. This feature is perfect for creating artistic variations, exploring different compositions, or generating multiple options from a single source image.

Supported Providers

• OpenAI: Supports dall-e-2 model
• AWS Bedrock: Supports amazon-nova-canvas model

Requirements

Provider	Model	Format	Size Limit	Image Count	Image Requirements
OpenAI	dall-e-2	Square PNG	< 4MB	1 image only	Must be square
AWS Bedrock	amazon-nova-canvas	PNG, JPEG	-	Upto 5 images	-

Example Usage

The meaning of the parameters are present in the OpenAI API documentation. The AWS Bedrock specfic parameters are explained here

OpenAI

from openai import OpenAI

BASE_URL = "{GATEWAY_BASE_URL}"
API_KEY = "your-truefoundry-api-key"

# Configure OpenAI client with TrueFoundry settings
client = OpenAI(
    api_key=API_KEY,
    base_url=BASE_URL,
)

response = client.images.create_variation(
    model="openai-main/dall-e-2",
    image=open("source_image.png", "rb"),  # Source image for variation
    n=3,  # Number of variations to generate
    size="1024x1024"
)

print(response)

Response Format

The API returns an ImagesResponse object containing:

{
  "created": 1589478378,
  "data": [
    {
      "url": "https://..."
    },
    {
      "url": "https://..."
    },
    {
      "url": "https://..."
    }
  ]
}