Browse ModelsClarity AIClarity AI Pro Upscaler

Clarity Ai Pro Upscaler

Clarity Ai Pro Upscaler

Playground

Try it on WavespeedAI!

Clarity Pro Upscaler is a photorealistic image upscaler from Clarity AI with identity preservation, creative detail control, and up to 16x scaling. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Clarity AI Pro Upscaler

Clarity AI Pro Upscaler is a photorealistic image upscaler built for high-quality enhancement while preserving identity, structure, and natural detail. It is well suited for photos, AI-generated images, product shots, artwork, and other visual assets that need clean high-resolution output.


Why Choose This?

  • Photorealistic upscaling Enhance images with sharper detail while keeping the result natural and visually consistent.

  • Strong identity preservation Preserve important structure, subject identity, and core composition during enhancement.

  • Simple control surface Use just a few settings to balance faithful restoration against stronger detail generation.

  • Predictable output tiers Choose from 2k, 4k, or 8k target resolution presets for consistent output sizing.

  • Fast workflow Upload one image, set the resolution and creativity level, and generate an enhanced result quickly.

  • Production-ready API Suitable for image enhancement pipelines, creative tooling, commercial asset preparation, and high-resolution delivery workflows.


Parameters

ParameterRequiredDescription
imageYesInput image to upscale.
target_resolutionNoOutput resolution tier: 2k, 4k (default), or 8k. Higher tiers create larger and more detailed images.
creativityNoControls how much new detail is added. Negative values stay stricter to the source, while positive values add more creative detail. Range: -10 to 10. Default: 0.

How to Use

  1. Upload your image — provide the source image you want to enhance.
  2. Choose target resolution — select 2k, 4k, or 8k depending on your quality and cost needs.
  3. Adjust creativity (optional) — keep it near 0 for faithful results, lower it for stricter preservation, or raise it for stronger detail generation.
  4. Submit — run the model and download the enhanced image.

Example Use Case

Upscale a product photo for high-resolution marketing use while preserving edges, material texture, and overall realism.


Pricing

Pricing is based on the selected target_resolution.

Target ResolutionCost
2k$0.05
4k$0.10
8k$0.20

Billing Rules

  • 2k costs $0.05 per image
  • 4k costs $0.10 per image
  • 8k costs $0.20 per image
  • Pricing depends on target_resolution
  • creativity does not affect pricing

Best Use Cases

  • Photo enhancement — Improve resolution and detail for real-world photography.
  • AI image cleanup — Refine generated images into cleaner, higher-resolution outputs.
  • Product visuals — Prepare sharper product shots for listings, ads, and brand materials.
  • Artwork upscaling — Increase image size for presentation, delivery, and print workflows.
  • Commercial asset preparation — Produce cleaner high-resolution images for campaigns, websites, and design systems.
  • Faithful restoration workflows — Preserve identity and structure while improving clarity.

Pro Tips

  • Start with 4k for most common enhancement tasks.
  • Keep creativity near 0 when you want natural, source-faithful results.
  • Use negative creativity values when preserving the original structure matters more than adding detail.
  • Increase creativity carefully if you want stronger generated texture or sharper enhancement.
  • Use the cleanest source image available for better detail recovery.
  • Test 8k only when you truly need the larger output size, since higher tiers cost more.

Notes

  • image is the only required field.
  • Supported target resolutions are 2k, 4k, and 8k.
  • target_resolution defaults to 4k.
  • creativity ranges from -10 to 10.
  • The input image is resized internally to match the selected target resolution before upscaling.
  • Pricing depends only on the selected resolution tier.

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/clarity-ai/pro-upscaler" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "target_resolution": "4k",
    "creativity": 0
}'

# 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
imagestringYes-Input image to upscale.
target_resolutionstringNo4k2k, 4k, 8kTarget output resolution tier. Higher tiers create larger, more detailed images.
creativitynumberNo--10.0 ~ 10.0Negative values stay stricter to the source; positive values add more detail.

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.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.