Shotcraft
Upscaling and restoration

Topaz Gigapixel

Still-image upscaler used in video pipelines for stills, plates, matte paintings and frame grabs.

An upscaling and restoration tool by Topaz Labs · read 2026-08-14 · sourcing high

Weights
Not released
API
Yes
Commercial use
Permitted subject to conditions

Supports upscaling up to 16x with nine models covering Standard, Standard Max, High Fidelity, Low Resolution, Text & Shapes, Art & CG, Recover, Redefine and Face Recovery, plus generative Wonder 2 and Wonder 3 models (Wonder 1 via cloud). Runs locally with unlimited renders, or in the cloud on subscription.

Commercial use — Permitted subject to conditions

Full commercial use is a Pro-tier entitlement; Personal tier commercial use is limited per the Topaz pricing page.

  • Depends on your plan tier. Full commercial use is a Pro-tier entitlement; Personal tier commercial use is limited per the Topaz pricing page

The conditions above were extracted from the licence notes recorded during research, and each one shows the sentence it came from so you can check the reading. Read the licence before you rely on any of this. Nothing on this page is legal advice, and this site does not tell you a model is cleared for commercial use.

Specification

Vendor figures, read 2026-08-14Read from Topaz Labs's own documentation on 2026-08-14. Vendors change these between model versions without announcing it, so check theirs before you commit a shot to a number. Sourcing for this entry is strong: the figures came from pages we retrieved and read. Check the vendor's current documentation

What it takes in
image, text
What it makes
image
Maximum resolution
not established
Aspect ratios
not established
Controls
upscale-factor, denoise, face-recovery
Weights
Not released
API
Yes
Pricing
Seat subscription: Personal $149/yr, $19/mo on annual commitment or $29/mo no commitment. Pro $499/yr or $54/mo on annual commitment, including full commercial use. Also bundled in Topaz Studio $399/yr. API credits: 1 credit up to 24MP output, 2 credits at 32MP, 10 credits at 256MP, 16 credits at 512MP.
Released or updated
not established

Maximum resolution and supported aspect ratios are not established here. That means no page we could retrieve stated them, not that the model lacks them.

Strengths

  • Published 16x upscale ceiling and a large model roster including dedicated face recovery
  • Unlimited local rendering with no per-image cost
  • API credit table is explicit about megapixel-to-credit mapping

Weaknesses

  • Stills only, so it does not solve moving-image temporal consistency
  • Generative Wonder/Redefine models can invent detail that will not match adjacent frames
  • Desktop app maximum output megapixels not published (30,000px limit applies only to the Photoshop plugin)

Best for

Where the sources disagree

Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.

What to understand before using it

Explainers naming the mechanisms this model's own documentation mentions.

MCP servers that front Topaz Labs

Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.

See it from the vendor

Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.

Nearby in the directory

Topaz Astra

Browser-based cloud video enhancement app that runs Topaz's heavier diffusion models in two modes: Creative (Astra 1, Astra 2) for stylised enhancemen

Upscaling and restoration

Topaz Bloom

Web-based creative image upscaler aimed at digital art and AI-generated images. Scales images up to 8x while generating new detail and texture, with a

Upscaling and restoration

Topaz Project Starlight

Diffusion-based video restoration model that upscales, denoises, de-aliases and sharpens footage in one pass with no sliders, analysing hundreds of su

Upscaling and restoration

Sources

Read on 2026-08-14. A source that has changed since then will not be reflected here until the next pass.