Video Samples

Every Processing Option changes the output in a different way. Compare them side-by-side before you spend render time on your own video.

Enhance — GFPGAN on vs. off

GFPGAN face restoration runs on every frame for a sharper result, at the cost of extra render time.

0:00
Enhance off — default look

Without GFPGAN

Faster rendering, slightly softer facial detail.

0:00
Enhance on — sharper

With GFPGAN

Each frame is passed through face restoration. Noticeably crisper.

0:00
Enhance off — second example

Without GFPGAN (avatar 2)

Another avatar showing baseline output without face restoration.

0:00
Enhance on — second example

With GFPGAN (avatar 2)

The same avatar with GFPGAN — sharper skin texture and eye detail.

Upscale — 512 px vs. 1024 px

Upscaling adds clarity after rendering without re-running the model. 512 px is the recommended sweet spot for most uses.

0:00
Upscale: 512 px — recommended

512 px upscale

Good balance of quality and file size. Recommended for most uses.

0:00
Upscale: 1024 px — sharpest

1024 px upscale

Maximum clarity, larger file. Best for presentations and high-res exports.

Still mode — on vs. off

Still mode keeps the head stable with minimal drift — good for presentation-style videos.

0:00
Still mode on — stable

Still mode on

Head stays mostly fixed. Ideal for explainers and slides.

0:00
Still mode off — natural drift

Still mode off

More natural head motion. Better for conversational avatars.

Expression scale — 0.7 vs. 1.2

Controls how animated the face is. The default of 1.0 is the most natural — lower values are subtler, higher values are more dramatic.

0:00
Expression 0.7 — subtle

Expression scale 0.7

More restrained movement. Good for calm, measured delivery. The default of 1.0 sits between these two and is the most natural-looking.

0:00
Expression 1.2 — expressive

Expression scale 1.2

More pronounced mouth movement. Works well for energetic or enthusiastic speech.