← Back to all generators
topazlabs/image-upscale
Official
View on Replicate →
Professional-grade image upscaling, from Topaz Labs
Capabilities
Reference Images
Cost
Community model (estimated from hardware time)
Input Parameters
| Name | Type | Description | Default | Constraints |
|---|---|---|---|---|
image * | string (uri) | Image to enhance | — | — |
enhance_model | string | Model to use: Standard V2 (general purpose), Low Resolution V2 (for low-res images), CGI (for digital art), High Fidelity V2 (preserves details), Text Refine (optimized for text) | "Standard V2" | Standard V2 Low Resolution V2 CGI High Fidelity V2 Text Refine |
face_enhancement | boolean | Enhance faces in the image | false | — |
face_enhancement_creativity | number | Choose the level of creativity for face enhancement from 0 to 1. Defaults to 0, and is ignored if face_enhancement is false. | 0 | min: 0, max: 1 |
face_enhancement_strength | number | Control how sharp the enhanced faces are relative to the background from 0 to 1. Defaults to 0.8, and is ignored if face_enhancement is false. | 0.8 | min: 0, max: 1 |
output_format | string | Output format | "jpg" | jpg png |
subject_detection | string | Subject detection | "None" | None All Foreground Background |
upscale_factor | string | How much to upscale the image | "None" | None 2x 4x 6x |
image required string Image to enhance
enhance_model string Model to use: Standard V2 (general purpose), Low Resolution V2 (for low-res images), CGI (for digital art), High Fidelity V2 (preserves details), Text Refine (optimized for text)
Default:
"Standard V2" Standard V2 Low Resolution V2 CGI High Fidelity V2 Text Refine
face_enhancement boolean Enhance faces in the image
Default:
false face_enhancement_creativity number Choose the level of creativity for face enhancement from 0 to 1. Defaults to 0, and is ignored if face_enhancement is false.
Default:
0 min: 0, max: 1 face_enhancement_strength number Control how sharp the enhanced faces are relative to the background from 0 to 1. Defaults to 0.8, and is ignored if face_enhancement is false.
Default:
0.8 min: 0, max: 1 output_format string Output format
Default:
"jpg" jpg png
subject_detection string Subject detection
Default:
"None" None All Foreground Background
upscale_factor string How much to upscale the image
Default:
"None" None 2x 4x 6x
Version:
2fdc3b86a01d Updated: 2/26/2026 1.4M runs
cinemasetfree.com