Skip to main content
Endpoint: POST https://fal.run/fal-ai/topaz/upscale/image Endpoint ID: fal-ai/topaz/upscale/image

Try it in the Playground

Run this model interactively with your own prompts.

​
Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/topaz/upscale/image",
    arguments={
        "image_url": "https://storage.googleapis.com/falserverless/model_tests/codeformer/codeformer_poor_1.jpeg"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

​
Input Schema

​
model
ModelEnum
default:"Standard V2"
Model to use for image enhancement. Default value: "Standard V2"Possible values: Low Resolution V2, Standard V2, CGI, High Fidelity V2, Text Refine, Recovery, Redefine, Recovery V2, Standard MAX, Wonder
​
upscale_factor
float
default:"2"
Factor to upscale the image by (e.g. 2.0 doubles width and height) Default value: 2Range: 1 to 4
​
crop_to_fill
boolean
default:"false"
​
image_url
string
required
Url of the image to be upscaled
​
output_format
OutputFormatEnum
default:"jpeg"
Output format of the upscaled image. Default value: "jpeg"Possible values: jpeg, png
​
subject_detection
SubjectDetectionEnum
default:"All"
Subject detection mode for the image enhancement. Applies to standard enhance and Recovery V2 models. Default value: "All"Possible values: All, Foreground, Background
​
face_enhancement
boolean
default:"true"
Whether to apply face enhancement to the image. Applies to standard enhance and Recovery V2 models. Default value: true
​
face_enhancement_creativity
float
default:"0"
Creativity level for face enhancement. 0.0 means no creativity, 1.0 means maximum creativity. Ignored if face enhancement is disabled.Range: 0 to 1
​
face_enhancement_strength
float
default:"0.8"
Strength of the face enhancement. 0.0 means no enhancement, 1.0 means maximum enhancement. Ignored if face enhancement is disabled. Default value: 0.8Range: 0 to 1
​
sharpen
float
Sharpening level (0.0-1.0). Applies to Standard V2, Low Resolution V2, CGI, High Fidelity V2, Text Refine, and Redefine models.Range: 0 to 1
​
denoise
float
Denoising level (0.0-1.0). Applies to Standard V2, Low Resolution V2, CGI, High Fidelity V2, Text Refine, and Redefine models.Range: 0 to 1
​
fix_compression
float
Compression artifact removal level (0.0-1.0). Applies to Standard V2, Low Resolution V2, High Fidelity V2, and Text Refine models.Range: 0 to 1
​
strength
float
Enhancement strength (0.01-1.0). Applies to Text Refine model only.Range: 0.01 to 1
​
creativity
integer
Creativity level for generative upscaling (1-6). Higher values produce more creative/hallucinated details. Applies to Redefine model only.Range: 1 to 6
​
texture
integer
Texture detail level for generative upscaling (1-5). Applies to Redefine model only.Range: 1 to 5
​
prompt
string
Text prompt to guide generative upscaling (max 1024 chars). Applies to Redefine model only.
​
autoprompt
boolean
Enable automatic prompt generation for generative upscaling. Applies to Redefine model only.
​
detail
float
Detail recovery level (0.0-1.0). Applies to Recovery V2 model only.Range: 0 to 1

​
Output Schema

​
image
File
required
The upscaled image.

​
Input Example

{
  "model": "Standard V2",
  "upscale_factor": 2,
  "crop_to_fill": false,
  "image_url": "https://storage.googleapis.com/falserverless/model_tests/codeformer/codeformer_poor_1.jpeg",
  "output_format": "jpeg",
  "subject_detection": "All",
  "face_enhancement": true,
  "face_enhancement_creativity": 0,
  "face_enhancement_strength": 0.8
}

​
Output Example

{
  "image": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019
  }
}

​
Limitations

  • upscale_factor range: 1 to 4
  • output_format restricted to: jpeg, png
  • subject_detection restricted to: All, Foreground, Background
  • face_enhancement_creativity range: 0 to 1
  • face_enhancement_strength range: 0 to 1
  • sharpen range: 0 to 1
  • denoise range: 0 to 1
  • fix_compression range: 0 to 1
  • strength range: 0.01 to 1
  • creativity range: 1 to 6
  • texture range: 1 to 5
  • detail range: 0 to 1