Topaz Image Upscale

AI Image Editing Model

Professional-grade image upscaler from Topaz Labs offering five specialized models (Standard, Low Resolution, CGI, High Fidelity, Text Refine) with optional face enhancement

topaz-image API OpenAI-compatible

Base URL
https://api.lumenfall.ai/openai/v1
Model
topaz-image-upscale

Code Examples

Upscale

/v1/images/edits
curl -X POST \
  https://api.lumenfall.ai/openai/v1/images/edits \
  -H "Authorization: Bearer $LUMENFALL_API_KEY" \
  -F "model=topaz-image-upscale" \
  -F "[email protected]" \
  -F "prompt=Add a starry night sky to this image" \
  -F "size=1024x1024"
# Response:
# { "created": 1234567890, "data": [{ "url": "https://...", "revised_prompt": "..." }] }

Parameter Reference

Required Supported Not available

Media Inputs

Parameter Type Description Modes
image file Required. Input image to upscale
Single image per request.
Upscale
scale_factor number Required. Factor by which to upscale the image
2x 4x 6x None
Upscale

Output & Format

Parameter Type Description Modes
response_format string How to return the image
url b64_json
Default: "url"
Upscale
output_format string Output image format
png jpeg gif webp avif
Gateway converts to requested format if provider doesn't support it natively.
Upscale
output_compression integer Compression level for lossy formats (JPEG, WebP, AVIF)
Upscale
n integer Number of images to generate
Default: 1
Gateway generates multiple images in parallel even if provider only supports 1.
Upscale

Additional Parameters

Provider-specific passthrough fields, available only when the request is routed to the listed provider.

Parameter Type Description Modes
Universal
face_enhancement boolean Enable face enhancement
Upscale
face_enhancement_strength number Strength of face enhancement (0-1)
Upscale
subject_detection string Subject detection mode
All Background Foreground None
Upscale
fal
crop_to_fill boolean Crop to fill output dimensions
Upscale
model string Enhancement model to use
CGI High Fidelity V2 Low Resolution V2 Standard V2 Text Refine
Upscale
replicate
enhance_model string Enhancement model to use
CGI High Fidelity V2 Low Resolution V2 Standard V2 Text Refine
Upscale
face_enhancement_creativity number Creativity for face enhancement (0-1)
Upscale

Parameter Normalization

How we handle parameters across different providers

Not every provider speaks the same language. When you send a parameter, we handle it in one of four ways depending on what the model supports:

Behavior What happens Example
passthrough Sent as-is to the provider style, quality
renamed Same value, mapped to the field name the provider expects prompt
converted Transformed to the provider's native format size
emulated Works even if the provider has no concept of it n, response_format

Parameters we don't recognize pass straight through to the upstream API, so provider-specific options still work.