Browse ModelsTopazTopaz Image Enhance

Topaz Image Enhance

Topaz Image Enhance

Playground

Try it on WavespeedAI!

Topaz Image Enhance improves images by removing noise, sharpening, and upscaling while preserving the details including faces of important subjects. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Topaz Image Enhance

Topaz Image Enhance is a professional-grade AI upscaling model powered by Topaz Labs’ technology. Upload your image, set target dimensions, and let AI intelligently upscale while adding detail and clarity — perfect for enlarging photos for print, display, or production use.


Why Choose This?

  • AI-powered upscaling Intelligently enlarges images while adding realistic detail, not just interpolation.

  • Multiple specialized models 5 models optimized for different image types — photos, low-res sources, CGI, high-fidelity, and text.

  • Custom output sizing Set exact width and height for your target dimensions.

  • Crop to fill option Optionally crop the image to exactly fill the specified dimensions.

  • Professional quality Powered by Topaz Labs’ AI, trusted by professional photographers and studios worldwide.


Parameters

ParameterRequiredDescription
imageYesSource image to enhance (upload or URL)
widthNoOutput width in pixels (default: 1080)
heightNoOutput height in pixels (default: 1080)
modelNoEnhancement model to use (default: Standard V2)
output_formatNoOutput format: jpeg, jpg, or png
crop_to_fillNoCrop the image to fill the exact dimensions

Model Options

ModelBest For
Standard V2General-purpose upscaling for most photos (default)
Low Resolution V2Upscaling very low-resolution or small images
CGIComputer-generated images, renders, and digital art
High Fidelity V2Maximum detail preservation for high-quality sources
Text RefineImages containing text, documents, screenshots

Output Format Options

  • jpeg / jpg — Compressed format, smaller file size
  • png — Lossless format, supports transparency

How to Use

  1. Upload your image — drag and drop or paste a URL.
  2. Set output size — specify target width and height.
  3. Select model — choose based on your image type.
  4. Enable crop to fill (optional) — check if you need exact dimensions.
  5. Choose output format — select based on your quality needs.
  6. Run — submit and download the enhanced image.

Pricing

ItemCost
Per image$0.07

Simple flat-rate pricing regardless of image size or model selected.


Best Use Cases

  • Print Enlargement — Upscale photos for large format printing.
  • Low-Res Recovery — Enhance old or small images to usable sizes.
  • CGI and Renders — Upscale 3D renders and digital artwork.
  • Document Enhancement — Improve readability of scanned documents with text.
  • Social Media — Upscale images for high-resolution display requirements.

Pro Tips

  • Use Low Resolution V2 for very small or heavily compressed source images.
  • Use CGI model for game screenshots, renders, and digital illustrations.
  • Use Text Refine when your image contains important text or documents.
  • High Fidelity V2 works best on already high-quality source images.
  • Enable crop_to_fill when you need exact dimensions for a specific layout.

Notes

  • Larger upscaling ratios may take longer to process.
  • For best results, start with the highest quality source available.
  • Different models are optimized for different content — experiment to find the best match.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result


# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/topaz/image/enhance" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "size": "1080*1080",
    "model": "Standard V2",
    "output_format": "jpeg",
    "crop_to_fill": false,
    "enable_base64_output": false
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"

Parameters

Task Submission Parameters

Request Parameters

ParameterTypeRequiredDefaultRangeDescription
imagestringNo-The positive prompt for the generation.The image file to be processed. Supported formats (png jpg jpeg)
sizestringNo1080*10801 ~ 32000 per dimensionSpecify the width and height pixel values of the generated image.Total pixel value range: [2560*1440, 4096*4096]
modelstringNoStandard V2Standard V2, Low Resolution V2, CGI, High Fidelity V2, Text RefineThe sharpen model to use.
output_formatstringNojpegjpeg, jpg, pngThe format of the output image.
crop_to_fillbooleanNofalse-Crop the image to fill the dimensions.
enable_base64_outputbooleanNofalse-If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.

Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
data.idstringUnique identifier for the prediction, Task Id
data.modelstringModel ID used for the prediction
data.outputsarrayArray of URLs to the generated content (empty when status is not completed)
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.has_nsfw_contentsarrayArray of boolean values indicating NSFW detection for each output
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds

Result Request Parameters

ParameterTypeRequiredDefaultDescription
idstringYes-Task ID

Result Response Parameters

ParameterTypeDescription
codeintegerHTTP status code (e.g., 200 for success)
messagestringStatus message (e.g., “success”)
dataobjectThe prediction data object containing all details
data.idstringUnique identifier for the prediction, the ID of the prediction to get
data.modelstringModel ID used for the prediction
data.outputsstringArray of URLs to the generated content (empty when status is not completed).
data.urlsobjectObject containing related API endpoints
data.urls.getstringURL to retrieve the prediction result
data.statusstringStatus of the task: created, processing, completed, or failed
data.created_atstringISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”)
data.errorstringError message (empty if no error occurred)
data.timingsobjectObject containing timing details
data.timings.inferenceintegerInference time in milliseconds
© 2025 WaveSpeedAI. All rights reserved.