Iris

Face recovery for degraded footage

Model Overview

Iris is a face focused enhancement model designed to recover facial detail in low to medium quality footage. It is optimized for footage where faces are degraded due to noise, compression, or interlacing.

Iris performs best on challenging sources such as archival material, broadcast footage, or heavily compressed video.

Key Capabilities

• Specialized face recovery for older or degraded footage

• Works with both progressive and interlaced sources

• This model has been specifically trained for low quality (LQ) and mid quality (MQ) input videos.

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 —

    • "iris-3" (Iris Low Quality)

    • "iris-2" (Iris Medium Quality)

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 Iris LQ

Click to view Iris MQ