Skip to content
QuantCDN

Generate images with Amazon Nova Canvas

POST
/api/v3/organizations/{organisation}/ai/image-generation

Generates images using Amazon Nova Canvas image generation model. * * Region Restriction: Nova Canvas is ONLY available in: * - us-east-1 (US East, N. Virginia) * - ap-northeast-1 (Asia Pacific, Tokyo) * - eu-west-1 (Europe, Ireland) * ❌ NOT available in ap-southeast-2 (Sydney) * * Supported Task Types: * - TEXT_IMAGE: Basic text-to-image generation * - TEXT_IMAGE with Conditioning: Layout-guided generation using edge detection or segmentation * - COLOR_GUIDED_GENERATION: Generate images with specific color palettes * - IMAGE_VARIATION: Create variations of existing images * - INPAINTING: Fill masked areas in images * - OUTPAINTING: Extend images beyond their borders * - BACKGROUND_REMOVAL: Remove backgrounds from images * - VIRTUAL_TRY_ON: Try on garments/objects on people * * Quality Options: * - standard: Faster generation, lower cost * - premium: Higher quality, slower generation * * Timeout: Image generation can take up to 5 minutes

Authorizations

Parameters

Path Parameters

organisation
required
string

The organisation ID

Request Body required

Image generation request

object
modelId

Model to use for image generation

string
default: amazon.nova-canvas-v1:0
taskType
required

Type of image generation task

string
Allowed values: TEXT_IMAGE COLOR_GUIDED_GENERATION IMAGE_VARIATION INPAINTING OUTPAINTING BACKGROUND_REMOVAL VIRTUAL_TRY_ON
textToImageParams

Parameters for TEXT_IMAGE task

object
text

Text prompt

string
>= 1 characters <= 1024 characters
negativeText

What NOT to include

string
>= 1 characters <= 1024 characters
style
string
Allowed values: 3D_ANIMATED_FAMILY_FILM DESIGN_SKETCH FLAT_VECTOR_ILLUSTRATION GRAPHIC_NOVEL_ILLUSTRATION MAXIMALISM MIDCENTURY_RETRO PHOTOREALISM SOFT_DIGITAL_PAINTING
conditionImage

Base64-encoded conditioning image

string format: byte
controlMode
string
default: CANNY_EDGE
Allowed values: CANNY_EDGE SEGMENTATION
controlStrength
number format: float
default: 0.7 <= 1
colorGuidedGenerationParams

Parameters for COLOR_GUIDED_GENERATION task

object
colors
Array<string>
>= 1 items <= 10 items
referenceImage
string format: byte
text
string
>= 1 characters <= 1024 characters
negativeText
string
>= 1 characters <= 1024 characters
imageVariationParams

Parameters for IMAGE_VARIATION task

object
images
Array<string>
>= 1 items <= 5 items
similarityStrength
number format: float
>= 0.2 <= 1
text
string
>= 1 characters <= 1024 characters
negativeText
string
>= 1 characters <= 1024 characters
inPaintingParams

Parameters for INPAINTING task

object
image
string format: byte
maskImage
string format: byte
maskPrompt
string
text
string
>= 1 characters <= 1024 characters
negativeText
string
outPaintingParams

Parameters for OUTPAINTING task

object
image
string format: byte
maskImage
string format: byte
maskPrompt
string
outPaintingMode
string
default: DEFAULT
Allowed values: PRECISE DEFAULT
text
string
negativeText
string
backgroundRemovalParams

Parameters for BACKGROUND_REMOVAL task

object
image
string format: byte
virtualTryOnParams

Parameters for VIRTUAL_TRY_ON task

object
imageGenerationConfig

General image generation configuration

object
width
integer
1024
height
integer
1024
quality
string
default: standard
Allowed values: standard premium
cfgScale
number format: float
default: 6.5 >= 1.1 <= 10
seed
integer
<= 2147483646
numberOfImages
integer
default: 1 >= 1 <= 5
region

AWS region for Nova Canvas

string
default: us-east-1
Allowed values: us-east-1 ap-northeast-1 eu-west-1
Example
{
  "taskType": "TEXT_IMAGE",
  "textToImageParams": {
    "text": "A serene mountain landscape at sunset with snow-capped peaks",
    "negativeText": "blurry, low quality, distorted",
    "style": "PHOTOREALISM"
  },
  "imageGenerationConfig": {
    "width": 1024,
    "height": 1024,
    "quality": "premium",
    "numberOfImages": 1,
    "cfgScale": 7
  },
  "region": "us-east-1"
}

Responses

200

Image(s) generated successfully

object
images
required

Array of base64-encoded generated images

Array<string>
maskImage

Base64-encoded mask image (for virtual try-on)

string format: byte
error

Error message if any images were blocked by content moderation

string

400

Invalid request parameters

403

Access denied

500

Failed to generate images