PL Log inCreate account
Launching in October 2026. Accounts, model catalog, calculator and docs are live. Studio is available in preview; generation is awaiting activation.

Video upscaling - prepare and check your source

Prepare a source clip for AI upscaling. Check file length and the cost reserve, then compare fine detail and motion before replacing your original.

Upscaling does not automatically repair incorrect motion, a blurred face or a distorted logo. It may also emphasize compression artifacts. Before processing a full clip, select a short representative passage containing the movement and detail that matter to the project.

Prepare the shot

  • Keep the original and create a test copy without another lossy encode when possible.
  • Check clip duration because input-billed tools reserve funds according to source length.
  • Supply the source through the supported Studio field and review the Reserve message.
  • Compare the same frame at 100 percent scale, rather than only using a small preview.
  • Watch at normal speed for flickering lines, textures and text.
  • Replace the edit source only after approval; keep the original available.

Review before publication

  • Detail is stable between frames.
  • Edges do not develop bright halos.
  • The result helps at the intended display size.

Model and cost

Use Topaz Video Upscaler. Its current unit price is $0.11 per second. Check the pricing page and calculator for your settings. Credits never expire, there is no subscription and failed generations are free. A successful output is billable even if you choose not to publish it.

FAQ

Why does Studio show a reserve rather than a final amount?

An input-billed tool depends on the source file length. Review the reserve together with duration before submitting.

Can I check the request before a paid run?

Yes. Check the model schema and the cost shown in Studio. Local demo API tests validate request handling but do not prove the visual or audio quality of the real model.

Where are the supported parameters?

Model details and the generation API guide list the supported inputs. Preview mode does not provide a real generated result.