OverviewTopaz Precision
Vidu Upscale Pro enhances uploaded or generated videos to 1080p, 2K, 4K, or 8K.
Upload or choose a source video in Models or Generate, or start from a completed video's TaskCard.
Model guideWhy choose Topaz Precision
Key strengths
- Rebuilds real detail from the source rather than sharpening what is already there.
- Six engines tuned for different source problems: compression, noise, or CG flatness.
- Timing, framing, and grade all survive the pass untouched.
Good fit for
- Taking an approved 1080p cut up to a 4K delivery master.
- Rescuing archival or heavily compressed footage before an edit.
- Finishing generated video at a resolution the model could not produce directly.
EnginesEngines in Topaz Precision
This model is a price tier: every engine below costs the same, so the choice is about the source, not the budget. Pick one in Generate under the model; leaving it unset uses the first.
- Proteus - Topaz's general-purpose model, with the widest manual control set. The right default when the source has no single dominant problem.
- Artemis High Quality - For clean, lightly compressed footage that mainly needs resolution rather than repair.
- Artemis Medium Quality - For footage carrying visible compression artifacts - streamed or re-encoded sources.
- Artemis Low Quality - For heavily degraded footage where blocking and banding dominate.
- Gaia High Quality - Built for rendered and CG footage, where photographic models over-sharpen synthetic edges.
- Gaia Computer Graphics - For flat-shaded CG, motion graphics, and screen recordings with hard geometric edges.
Supported on MachGenInputs and output settings
Upscaling is live in Models, Generate, and on a completed generation's TaskCard.
| Mode | Required input | Available settings |
|---|
| Upscaling | Uploaded or generated source video in Models or Generate; completed videos can also be selected from a TaskCard | Resolution: 1080p, 2K, 4K, 8K |
WorkflowHow to upscale a video
- Upload a source video or choose one from Assets in Models or Generate. You can also start from a completed video's TaskCard.
- Select 1080p, 2K, 4K, or 8K above the source resolution.
- Review the estimate, then submit the job.
- Inspect the enhanced video when processing completes.
Best resultsHow to get better Topaz Precision results
- Match the engine to the source: Artemis for compressed footage, Gaia for CG and rendered content, Proteus when unsure.
- Start from the cleanest source available - upscaling cannot recover detail that compression already destroyed.
- Longer clips are capped at the higher resolutions; split a long source before going to 8K.
- Judge the result in motion, not on a paused frame.
LimitsLimits and availability
- Choose a target above the source resolution: 1080p, 2K, 4K, 8K.
- Maximum source length is 300 seconds, and shorter at the highest targets.
- Any frame rate is accepted. Billing is per delivered frame, so a 60 FPS source costs twice a 30 FPS one of the same length.
- Direct uploads are limited to 256 MiB; generated MachGen videos can be selected from Assets or a completed TaskCard.
- Current rates come from the live MachGen pricebook.
- Topaz Precision is pass-through. MachGen sends the request through its upstream provider integration and returns the generated asset.
Learn moreLearn more
For model background, technical details, and architecture, see the official Topaz video model documentation.
Use the MachGen Playground to upload or choose a source video. You can also open a completed video's TaskCard and choose Upscale.
Official documentation may describe capabilities or parameters that are not currently exposed by MachGen. Use the Inputs and output settings section above as the source of truth for this page.
PricingTopaz Precision pricing
See Pricing for currently published MachGen rates. Models, Generate, and the completed video's TaskCard show the current estimate before an Upscale job is submitted.
On MachGenTopaz Precision on MachGen
Deployment: Pass-through. Topaz Precision is pass-through. MachGen sends the request through its upstream provider integration and returns the generated asset.
Upload or choose a source in Models or Generate, or open a completed MachGen generation's TaskCard and choose Upscale.