Rhea

High-fidelity 4× upscaling for fine detail

Model Overview

Rhea is a high fidelity enhancement model designed for 4× upscaling of organic textures and fine detail, delivering clean, controlled sharpness while preserving natural structure.

Rhea blends the general enhancement strengths of Proteus with the facial recovery capabilities of Iris to recover fine detail and faces from lower resolution sources such as 480p footage. It operates natively at a 4× scale and is best suited for workflows where maximum detail preservation is prioritized over render speed.

Key Capabilities

• Optimized for high quality 4× upscaling of organic textures and fine detail

• Preserves faces, text, and small structures with natural looking sharpness

• Best suited for clean or lower resolution sources where fidelity is prioritized over speed

Pricing

Duration	720p	1080p	4K
1s	1	1	1
5s	1	1	3
10s	1	2	6
1m	4	8	31
5m	17	38	151
10m	34	76	302

The above credit costs are all estimates calculated at 30fps. For more accurate pricing, we recommend checking out our Credit Calculator.

Getting Started

Endpoint

• https://api.topazlabs.com/video/

  • model — "rhea-1"

Model-Specific Parameters

• video_type — "Progressive", "Interlaced", or "ProgressiveInterlaced"

• auto — "Auto", "Manual", or "Relative"

• field_order — "TopFirst", "BottomFirst", or "Auto"

• focus_fix_level — "None", "Normal", or "Strong"

• compression — decimal between -1 and 1

• details — decimal between -1 and 1

• prenoise — decimal between 0 and 0.1

• noise — decimal between -1 and 1

• halo — decimal between -1 and 1

• preblur — decimal between -1 and 1

• blur — decimal between -1 and 1

• grain — decimal between 0 and 0.1

• grain_sigma — decimal between 0 and 1

• grain_size — decimal between 0 and 5

• grain_type — "silver_rich", "gaussian", or "grey"

• recover_original_detail_value — decimal between 0 and 1

Examples

Click to view

Click to view