Browse ModelsTopazTopaz Image Sharpen

Topaz Image Sharpen

Topaz Image Sharpen

Playground

Try it on WavespeedAI!

Topaz Image Sharpen brings clarity and crisp definition to soft or out-of-focus images. Perfect for fixing lens blur, motion blur, and general softness. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Topaz Image Sharpen

Topaz Image Sharpen is a professional-grade image sharpening model powered by Topaz Labs’ industry-leading AI technology. Upload your image and select from multiple specialized sharpening models — each optimized for different scenarios like portraits, wildlife, motion blur recovery, and more.


Why Choose This?

  • Multiple sharpening models 9 specialized models optimized for different use cases — from general sharpening to specific scenarios like portraits, wildlife, and motion blur.

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

  • Blur recovery Specialized models for lens blur and motion blur can recover detail from out-of-focus or motion-blurred images.

  • Multiple output formats Export as JPEG, PNG, or TIFF based on your workflow needs.


Parameters

ParameterRequiredDescription
imageYesSource image to sharpen (upload or URL)
modelNoSharpening model to use (default: Standard)
output_formatNoOutput format: jpeg, jpg, png, tiff, or tif

Model Options

ModelBest For
StandardGeneral-purpose sharpening (default)
StrongMore aggressive sharpening for soft images
Lens BlurRecovering detail from out-of-focus images
Lens Blur V2Improved lens blur recovery with better edge handling
Motion BlurRecovering detail from motion-blurred images
NaturalSubtle, natural-looking sharpening
RefocusBringing soft areas back into focus
WildlifeOptimized for animal fur, feathers, and textures
PortraitOptimized for skin, hair, and facial features

Output Format Options

  • jpeg / jpg — Compressed format, smaller file size
  • png — Lossless format, supports transparency
  • tiff / tif — Professional format, highest quality preservation

How to Use

  1. Upload your image — drag and drop or paste a URL.
  2. Select model — choose the sharpening model that matches your image type.
  3. Choose output format — select based on your quality and file size needs.
  4. Run — submit and download the sharpened image.

Pricing

ItemCost
Per image$0.07

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


Best Use Cases

  • Photo Enhancement — Sharpen photos for print or digital display.
  • Blur Recovery — Recover detail from slightly out-of-focus shots.
  • Wildlife Photography — Enhance fur, feathers, and fine textures.
  • Portrait Retouching — Sharpen facial features while maintaining natural skin.
  • Motion Blur Correction — Improve images affected by camera shake or subject movement.

Pro Tips

  • Start with Standard model for general use, switch to specialized models for specific content.
  • Use Portrait mode for headshots to avoid over-sharpening skin texture.
  • Use Wildlife mode for animals to enhance fur and feather details.
  • Lens Blur V2 often produces better results than the original Lens Blur.
  • Use PNG or TIFF for maximum quality preservation in professional workflows.

Notes

  • Different models are optimized for different content types — experiment to find the best match.
  • For best results, use high-resolution source images.
  • Over-sharpening can introduce artifacts — start with Standard or Natural for subtle enhancement.

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/sharpen" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "model": "Standard",
    "output_format": "jpeg",
    "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 image file to be processed. Supported formats (png jpg jpeg tiff tif)
modelstringNoStandardStandard, Strong, Lens Blur, Lens Blur V2, Motion Blur, Natural, Refocus, Wildlife, PortraitThe sharpen model to use. Standard: Balanced sharpening. Strong: Aggressive sharpening. Lens Blur: Fix lens blur. Lens Blur V2: Enhanced lens blur correction. Motion Blur: Reduce motion blur. Natural: Natural-looking sharpness. Refocus: Bring back focus. Wildlife: Optimized for wildlife. Portrait: Optimized for portraits.
output_formatstringNojpegjpeg, jpg, png, tiff, tifThe format of the output image.
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.