Skip to content

Images API

Generate images with AWS Bedrock image models like Stability AI and Amazon Nova Canvas through an OpenAI-compatible interface.

Why Choose Image Generation?

  • Quality Output
    Generate photorealistic images, digital art, and illustrations.

  • Real-Time Streaming
    Progressive generation shows partial previews as the model works for interactive applications.

  • Flexible Control
    Choose dimensions, quality levels, and styles. From quick drafts to high-resolution finals.

  • Scalable Infrastructure
    Generate images at scale with AWS Bedrock infrastructure. No GPU management required.

Quick Start: Available Endpoint

Endpoint Method What It Does Powered By
/v1/images/generations POST Generate images from text prompts AWS Bedrock Image Models

Feature Compatibility

Feature Status Notes
Generation
Text-to-image (/generations) Generate images from prompts
Parameters
prompt Text description for generation
n (number of images) Generate multiple images per request
size (WIDTHxHEIGHT) Supported dimensions vary by model; some may approximate requested sizes
quality low, medium, high + model specific quality levels
style Some models support style parameters
output_compression Supported on all input formats
background Only opaque is supported
moderation Only auto is supported
Extra model-specific params Extra model-specific parameters not supported by the OpenAI API
Output
URL response format Temporary URLs to generated images
Base64 JSON format Inline base64-encoded images
PNG format Lossless image output
JPEG format Compressed image output
WebP format Modern compressed format
Streaming
SSE streaming Real-time generation updates
Partial images Progressive previews when available
Usage tracking
Input text tokens Estimated for reference
Output image tokens Image count (billing unit)
Other
user Logged

Legend:

  • Supported — Fully compatible with OpenAI API
  • Available on Select Models — Check your model's capabilities
  • Partial — Supported with limitations
  • Unsupported — Not available in this implementation
  • Extra Feature — Enhanced capability beyond OpenAI API

Configuration Required

You must configure the AWS_S3_BUCKET environment variable with a bucket to use the URL response format.

Performance Optimization

For faster image downloads, especially for high-resolution images or globally distributed users, enable S3 Transfer Acceleration by setting AWS_S3_ACCELERATE=true. This uses CloudFront edge locations to accelerate file downloads, providing 50-500% faster speeds for users far from your S3 bucket region. See S3 Transfer Acceleration configuration for setup details.

Advanced Features

Provider-Specific Parameters

Unlock advanced image generation capabilities by passing provider-specific parameters directly in your requests. These parameters are forwarded to AWS Bedrock and allow you to access features unique to each image model provider.

Documentation: Bedrock Image Model Parameters

How It Works:

Add provider-specific fields at the top level of your request body alongside standard OpenAI parameters. The API automatically forwards these to the appropriate model provider via AWS Bedrock.

Examples:

Stability AI - Negative Prompts: 

{
  "model": "stability.stable-image-core-v1:0",
  "prompt": "A serene mountain landscape at sunset",
  "negative_prompt": "blurry, distorted, low quality, watermark"
}

Amazon Nova Canvas - Negative Prompts: 

{
  "model": "amazon.nova-canvas-v1:0",
  "prompt": "An abstract watercolor painting",
  "textToImageParams": {"negativeText": "blurry, distorted, low quality, watermark"},
}

Configuration Options:

Option 1: Per-Request

Add provider-specific parameters directly in your request body (as shown in examples above).

Option 2: Server-Wide Defaults

Configure default parameters for specific models via the DEFAULT_MODEL_PARAMS environment variable:

export DEFAULT_MODEL_PARAMS='{
  "stability.stable-image-core-v1:0": {
    "negative_prompt": "blurry, low quality, watermark"
  }
}'

Note: Per-request parameters override server-wide defaults.

Behavior:

  • ✅ Compatible parameters: Forwarded to the model and applied
  • ⚠️ Unsupported parameters: Return HTTP 400 with an error message

Try It Now

Generate image (URL response):

curl -X POST "$BASE/v1/images/generations" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A serene mountain landscape at sunset, photorealistic",
    "model": "amazon.nova-canvas-v1:0",
    "size": "1024x1024",
    "quality": "high",
    "response_format": "url"
  }'

Generate with base64 encoding:

curl -X POST "$BASE/v1/images/generations" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A futuristic cityscape with flying cars, digital art style",
    "model": "amazon.nova-canvas-v1:0",
    "response_format": "b64_json"
  }'

Stream generation with partial previews:

curl -N -X POST "$BASE/v1/images/generations" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "An abstract watercolor painting of emotions",
    "model": "amazon.nova-canvas-v1:0",
    "stream": true,
    "partial_images": 3
  }'

Unleash your creativity! Explore available image models in the Models API.