Browse ModelsClarity AIClarity AI Crystal Video Upscaler

Clarity Ai Crystal Video Upscaler

Clarity Ai Crystal Video Upscaler

Playground

Try it on WavespeedAI!

Clarity AI Crystal Video Upscaler is a fast AI video super-resolution model that increases video resolution with target megapixel control and Clarity AI crystal-video processing. Ready-to-use REST inference API for enhancing low-resolution videos, restoring details, improving visual clarity, upscaling creative clips, product videos, social media content, and professional video enhancement workflows with simple integration, no coldstarts, and affordable pricing.

Features

Clarity AI Crystal Video Upscaler

Clarity AI Crystal Video Upscaler enhances and enlarges video content with a simple megapixel-based target control. Upload a source video, choose the desired target megapixels, and generate a cleaner, sharper upscaled result for higher-quality delivery, presentation, or archival workflows.


Why Choose This?

  • Video upscaling workflow Improve the visual quality of existing video content with a simple upload-and-upscale process.

  • Megapixel-based output control Use target_megapixels to choose the intended output size more directly.

  • Simple pricing logic Cost scales with both target megapixels and video duration, with a minimum charge for very small jobs.

  • Suitable for restoration and delivery Useful for sharpening low-resolution clips for presentations, publishing, or asset reuse.

  • Production-ready API Suitable for enhancement pipelines, archival cleanup, and commercial video preparation workflows.


Parameters

ParameterRequiredDescription
videoYesInput video to upscale.
target_megapixelsNoTarget output size in megapixels. Higher values produce larger and more detailed upscaled frames.

How to Use

  1. Upload your video — provide the source video you want to enhance.
  2. Choose target megapixels — set the desired output size based on your delivery needs.
  3. Submit — run the model and download the upscaled video.

Example Use Case

Upscale a low-resolution talk-show or interview clip to a cleaner, sharper version for reuse in presentations, publishing, or social distribution.


Pricing

Pricing is based on video duration and target_megapixels.

Billing Rules

  • Base price is $0.10
  • Standard rate is $0.10 × target_megapixels × video duration (seconds)
  • The final charge is the greater of:
    • $0.10 minimum
    • $0.10 × target_megapixels × duration

Example Costs

Target Megapixels1s5s10s
1 MP$0.10$0.50$1.00
2 MP$0.20$1.00$2.00
4 MP$0.40$2.00$4.00
8 MP$0.80$4.00$8.00

Best Use Cases

  • Low-resolution video enhancement — Improve the clarity of older or compressed video clips.
  • Presentation and publishing prep — Generate cleaner upscaled outputs for decks, demos, and public distribution.
  • Archival restoration workflows — Prepare sharper versions of legacy footage for reuse.
  • Commercial asset improvement — Upgrade visual quality for marketing, social, and branded content.
  • General video cleanup — Increase perceived quality for clips that need a higher-resolution presentation.

Pro Tips

  • Start with a lower target_megapixels value first to validate cost and output quality.
  • Use clean source video whenever possible for better enhancement results.
  • Higher megapixel targets can increase cost quickly on longer clips.
  • Short clips are a good way to test the workflow before processing longer footage.

Notes

  • video is required.
  • Pricing depends on both target_megapixels and source video duration.
  • A minimum charge of $0.10 applies.
  • Longer videos and larger target sizes increase cost proportionally.

  • Other Clarity AI upscaling and enhancement models may be useful when you need image-first workflows or different restoration trade-offs.

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/crystal-video-upscaler" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "target_megapixels": 2
}'

# 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
videostringYes-Input video to upscale.
target_megapixelsnumberNo21 ~ 200Requested output size in megapixels. Range: 1-200 MP.

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.