Choose Auto, TokenLab Verified, or Official for each request, with prices shown up front. See what's new

Pruna AI: P-Image-Upscale

P-Image Upscale is an image upscaling model from Pruna that increases resolution using AI with a configurable target from 1 to 8 megapixels. It includes optional detail enhancement and realism enhancement controls for improving output quality, particularly effective on AI-generated images. It supports JPEG and PNG output formats with both synchronous and asynchronous processing.
Compare models
p-image-upscale
AvailablePruna AIImageSync
Price
From $0.005
Modalities
Image

About P-Image-Upscale

P-Image-Upscale is Pruna AI's image upscaler: it raises the resolution of a supplied image to a target size in megapixels. Optional detail enhancement and realism enhancement controls refine texture, and Pruna says it works particularly well on AI-generated images. Output can be JPEG or PNG, and requests run synchronously or asynchronously.

Where it works well

  • The target size is set in megapixels rather than a fixed multiplier, so the result lands at a known size.
  • A detail option sharpens fine textures and small features.
  • A realism option helps AI-generated images look less synthetic.
  • It is designed to improve quality without changing the composition.

When to choose another model

  • Enhancement options can introduce small variations from the original, so exact pixel fidelity is not guaranteed.
  • It enlarges and refines only; it cannot fix a bad composition or add missing content.

Getting started

  1. Create API key

    Create a key in Console, then use it with every model on the platform.

  2. Send your first request

    Copy the example for your language and run it against the endpoint.

    Image editingTokenLab endpoint
    POST/v1/images/generations
    curl -X POST "https://api.tokenlab.sh/v1/images/generations" \
      -H "Authorization: Bearer sk-xxx" \
      -H "Content-Type: application/json" \
      -d '{
      "operation": "image-to-image",
      "model": "p-image-upscale",
      "prompt": "A minimalist product photo of matte black headphones on a soft blue background.",
      "image_url": "https://example.com/source.png"
    }'

Parameters

Image editing

ParameterValues and limitsDefaultNotes
imageNot providedNot providedAlias of the combined images input. See input_limits.images for the total input image count.
image_urlNot providedNot providedAlias of the combined images input. See input_limits.images for the total input image count.
image_urlsNot providedNot providedAlias of the combined images input. See input_limits.images for the total input image count.
imagesInputs: ≥ 1, ≤ 1Not providedLimits apply when this input is supplied. Image aliases are combined into one input image list; the limit applies to the combined list.
operationNot providedNot providedNot provided
output_formatjpeg, png, webpNot providedDefault encoding is shared by these equivalent values: jpg, jpeg.

Fields outside this contract are rejected.

Pricing

The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.

Image editing

per image
Official price
$0.005
Verified price
—
Discount
—

Usage & activity

Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.

Usage & availability

Last 24 hours
Requests
Success rate
P95 latency
Total tokens
Model performance
Metrics appear once privacy and data volume thresholds are met.

Data is based on aggregate user requests, excluding status checks.

Open in Console

Open P-Image-Upscale in Console with a prompt ready to edit or send.

Help me create an image with p-image-upscale using image-edit at /v1/images/edits. Show the result, cost, and any limits I should know.

Use cases

  • Finishing generated images

    Take a good draft from a fast text-to-image model and produce the delivery version.

  • Print preparation

    Enlarge a web-sized picture to a size that holds up on posters or packaging.

  • Catalogue clean-up

    Raise low-resolution product photos to a consistent size for a storefront. Consistent sizing helps grid layouts look tidy.

Prompt examples

Input: a 1024 px AI portrait. Target: 4 megapixels, realism enhancement on, detail enhancement on.

Input: a compressed product photo of a leather bag. Target: 8 megapixels, detail enhancement only.

Input: a logo mock-up with small lettering. Target: 4 megapixels, PNG output.

FAQ

What does P-Image-Upscale do?

It increases the resolution of an image with AI, to a target you give in megapixels. Optional enhancement settings improve fine detail and realism. The result is a larger file of the same picture.

Which output formats are supported?

JPEG and PNG on this catalog entry, and Pruna's own guide also lists WebP. Quality can be tuned for lossy formats. PNG suits graphics with sharp edges.

Are there enhancement options?

Yes: detail enhancement for textures and small features, and realism enhancement, which Pruna recommends especially for AI-generated pictures. Both can alter fine details slightly. Detail and realism can each be switched on separately.

Can I call it asynchronously?

Yes. Requests are asynchronous by default, with a synchronous mode through a request header for immediate results. Use async for large targets and batches. Pick the mode that fits your pipeline.

Is it a text-to-image model?

No. It needs an input image. Pair it with P-Image or another generator: create the picture first, then upscale the version you keep. Upscaling is the last step, not the first.

How much does P-Image-Upscale cost?

On TokenLab, P-Image-Upscale costs $0.005 per image. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

Which endpoint should P-Image-Upscale use?

Use https://api.tokenlab.sh/v1/images/edits for P-Image-Upscale. The request example below shows the matching code shape.

Which operations does P-Image-Upscale support?

P-Image-Upscale supports Image editing. Select an operation above to see its endpoint and request example.

Compare P-Image-Upscale

Guides that use P-Image-Upscale

Sources

Reviewed Oct 2, 2026

More from Pruna AI

Related models