---
title: "Topaz Upscale Video Precision"
description: "Topaz precision (non-generative) video upscaling, faithful to the source. Rhea for talking heads and people, Iris to recover faces, Proteus for most real footage, Proteus Natural for a softer look. Up to 4x. Billed per output second at the resolution tier of the output (720p, 1080p, 4K); the listed price is the 4K ceiling."
updated: 2026-09-29
---

# Topaz Upscale Video Precision

**Node type:** `video:topaz_upscale_video_precision`  
**Category:** `video`

## Description

Topaz precision (non-generative) video upscaling, faithful to the source. Rhea for talking heads and people, Iris to recover faces, Proteus for most real footage, Proteus Natural for a softer look. Up to 4x. Billed per output second at the resolution tier of the output (720p, 1080p, 4K); the listed price is the 4K ceiling.

## Pricing

- **Cost:** ~10 credits per seconds
- **Per-second rate:** The figure is the rate at a 5-second reference run. Our margin is progressive and steepest on the smallest runs, so a clip shorter than that can cost more per second, and a model priced with a flat multiplier is exact at every length. The charge is always computed from the real duration.

## Canvas ports

These appear as port handles on the left side of the node.

| ID          | Label     | Details              |
| ----------- | --------- | -------------------- |
| `video_url` | **Video** | `VIDEO` _(required)_ |

## Sidebar config

These render as form fields in the right-side config panel when the node is selected.

| ID               | Label                            | Details                                                                                                                                                                                                                                                                                                         |
| ---------------- | -------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `upscale_factor` | **Upscale Factor**               | `NUMBER` · `1…4`                                                                                                                                                                                                                                                                                                |
| `model`          | **Model**                        | `TEXT` · options: `Proteus`, `Proteus Natural`, `Iris`, `Iris Low Quality`, `Rhea`, +16 — Rhea: talking heads and people. Iris: face recovery. Proteus: most real footage. Proteus Natural: softer (2x only). Dione: interlaced sources. Artemis: denoise and sharpen degraded footage. Gaia 2: animation (2x). |
| `recover_detail` | **Recover Detail**               | `NUMBER` · `0…1` — How much original detail to keep (0 to 1). Leave empty for the model default.                                                                                                                                                                                                                |
| `noise`          | **Noise Reduction**              | `NUMBER` · `0…1` — 0 to 1. Leave empty for the model default.                                                                                                                                                                                                                                                   |
| `compression`    | **Compression Artifact Removal** | `NUMBER` · `0…1` — 0 to 1. Leave empty for the model default.                                                                                                                                                                                                                                                   |
| `halo`           | **Halo Reduction**               | `NUMBER` · `0…1` — 0 to 1. Leave empty for the model default.                                                                                                                                                                                                                                                   |
| `grain`          | **Film Grain**                   | `NUMBER` · `0…0.1` — 0 to 0.1. Leave empty for the model default.                                                                                                                                                                                                                                               |
| `H264_output`    | **H.264 Output**                 | `BOOLEAN`                                                                                                                                                                                                                                                                                                       |

## Outputs

| ID      | Label              | Type    |
| ------- | ------------------ | ------- |
| `video` | **Upscaled Video** | `VIDEO` |

---

_Auto-generated from the Wireflow node registry._

---

Documentation index: fetch https://www.wireflow.ai/llms.txt for the full list of Wireflow docs.