Foundation model available in N. Virginia. Direct inference without cross-region routing.
Provider: All Amazon models | AWS Bedrock
Inference regions: us-east-1
https://bedrock-runtime.us-east-1.amazonaws.com| Parameter | Type | Description |
|---|---|---|
| taskType | enum | Type of image generation task. |
| width | integer | Output image width in pixels. (320–4096) |
| height | integer | Output image height in pixels. (320–4096) |
| quality | enum | Output quality. Default: standard. |
| numberOfImages | integer | Number of images to generate. (1–5) Default: 1. |
| cfgScale | float | How closely the image follows the prompt. (1.1–10) Default: 6.5. |
| seed | integer | Seed for reproducible generation. (0–858993459) |
Default mode. Pay per token with no upfront commitment.
Nova Canvas supports multiple image generation tasks including text-to-image, inpainting, and background removal.