Topaz Labs

Topaz Video Upscale

This family is a toolbox, not a quality ladder: Proteus and Artemis are general-purpose choices, Dione targets interlaced sources, Iris emphasizes faces, Gaia targets clean animation or CGI, and Starlight or Astra variants use generative reconstruction for more difficult or creative material. Choosing the model by source type and defect is more important than choosing the newest name.

How to use this model

  1. 1

    Identify the source first: progressive camera footage, interlaced video, animation/CGI, archival material, compressed web video, or generated video.

  2. 2

    Choose a matching model: Dione for deinterlacing, Iris for damaged faces, Gaia for clean animation, Proteus or Artemis for general footage, or a diffusion model for reconstruction.

  3. 3

    Set the output resolution conservatively and process a short section containing faces, motion, texture, and text.

  4. 4

    Compare at 100% scale for invented detail, halos, unstable texture, warped lettering, and changes to the source style.

  5. 5

    Use a second pass only when the first pass solves a distinct defect; avoid stacking strong enhancement without an intermediate review.

ArtemisAvailable

Artemis

Artemis is a general enhancement model that balances detail enhancement with noise and artifact reduction. It is designed to handle low, medium, and high quality footage with a range of common issues, including haloing, aliasing, and compression artifacts.

Try now

Properties

  • Supports Video Upscale workflows.

Best for

  • General purpose denoise and sharpen model
  • Offers multiple tuned variants for different footage conditions
  • Available variants include High Quality, Medium Quality, Low Quality, Medium Halo, Strong Halo, and Aliasing or Moire

Tips

  • Balanced denoise and sharpening

How to use this model

  1. 1

    Upload the source media at the best quality available.

  2. 2

    Choose the restoration or enhancement variant that matches the defect.

  3. 3

    Compare the output at full size and reduce strength if natural detail is lost.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 15 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Video Type

video_type
Optional

Frame or field type of the source video.

  • Progressive

  • Interlaced

  • ProgressiveInterlaced

Parameter Mode

auto
Optional

Parameter mode for the selected model.

  • Auto

  • Manual

  • Relative

Field Order

field_order
Optional

Optional field order for interlaced input videos.

  • TopFirst

  • BottomFirst

  • Auto

Focus Fix Level

focus_fix_level
Optional

Downscale input for stronger correction of blurred subjects.

  • None

  • Normal

  • Strong

Compression

compression
Optional

Compression recovery strength.

Range: -1 – 1

Details

details
Optional

Detail reconstruction amount.

Range: -1 – 1

Prenoise

prenoise
Optional

Noise added before processing to reduce smoothing.

Range: 0 – 0.1

Noise

noise
Optional

Noise reduction amount.

Range: -1 – 1

Halo

halo
Optional

Halo reduction amount.

Range: -1 – 1

Preblur

preblur
Optional

Anti-aliasing and deblurring strength.

Range: -1 – 1

Blur

blur
Optional

Sharpness amount.

Range: -1 – 1

Grain

grain
Optional

Grain added after processing.

Range: 0 – 0.1

Grain Size

grain_size
Optional

Generated grain size.

Range: 0 – 5

Recover Original Detail

recover_original_detail_value
Optional

Amount of source detail to reintroduce into the output.

Range: 0 – 1

Model

model
Optional

Artemis model variant.

Default: Low Quality

  • Aliasing / Moire

  • Low Quality

  • Medium Quality

  • High Quality

  • Medium Halo

  • Strong Halo

slc-1Available

Astra 1

Astra 1 is a creative diffusion-based upscaling model designed specifically for GenAI video. It transforms AI-generated footage to 4K by adding new, dynamic detail and texture, producing expressive and stylized results beyond traditional enhancement. Astra 1 allows creators to control the level of creative transformation, from subtle refinement to bold, highly stylized output. It enhances clarity, richness, and visual complexity by adding new detail and texture to GenAI video. Due to its scale and creative flexibility, Astra 1 is a cloud-only model optimized for high-capacity processing.

Try now

Properties

  • Supports Video Creative Upscale workflows.

Best for

  • Creative diffusion-based upscaling for GenAI video at 4K
  • Adds new detail and texture with adjustable creative intensity
  • Cloud-optimized model for expressive, stylized enhancement workflows

Tips

  • Transform GenAI video to 4K with creative upscaling that generates dynamic new texture and detail

How to use this model

  1. 1

    Upload the source media at the best quality available.

  2. 2

    Choose the restoration or enhancement variant that matches the defect.

  3. 3

    Compare the output at full size and reduce strength if natural detail is lost.

Examples

Creative video enhancement preview from Topaz Astra.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 15 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Creativity

creativity
Required

Creative enhancement strength.

  • low

  • middle

  • high

ast-2Available

Astra 2

Astra 2 is an advancement in creative diffusion-based upscaling for GenAI video, building on Astra 1 with expanded control over detail generation and stylization. It transforms AI-generated footage by adding new, dynamic detail and texture, with adjustable creativity and sharpness controls and prompt-based guidance for more precise creative direction. Astra 2 performs best on stylized and GenAI sources, as well as wide shots and large-scale scenes where additional detail can be creatively inferred. It enhances clarity, richness, and visual complexity, and is optimized for expressive, stylized workflows.

Try now

Properties

  • Supports Video Creative Upscale workflows.

Best for

  • Creatively transform GenAI sources with new detail and textures
  • Expanded control with adjustable creativity and sharpness levels, plus prompt-based guidance
  • Strong performance on stylized content, wide shots, and detail-sparse scenes

Tips

  • Enhanced creative upscaling for GenAI video with advanced control over detail and style

How to use this model

  1. 1

    Upload the source media at the best quality available.

  2. 2

    Choose the restoration or enhancement variant that matches the defect.

  3. 3

    Compare the output at full size and reduce strength if natural detail is lost.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 15 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Creativity

creativity
Required

Creative enhancement strength.

  • low

  • middle

  • high

DioneAvailable

Dione

Dione is intended for true interlaced sources rather than ordinary progressive footage. Correct field order is essential: the wrong order produces reversed or stuttering motion even if individual frames look sharp.

Try now

Properties

  • Purpose: deinterlacing combined with enhancement/upscaling.
  • Best matched to interlaced source video with known field order.

Best for

  • Purpose built for interlaced video workflows
  • Includes specialized variants tuned for different source types
  • Available variants include Dione DV for digital video, Dione TV for analog broadcast sources, and Dione Dehalo for reducing edge artifacts and fringing

Tips

  • Deinterlacing and legacy video conversion

How to use this model

  1. 1

    Confirm that the source is interlaced and identify its field order.

  2. 2

    Choose the matching field order and a conservative output scale.

  3. 3

    Process a motion-heavy test section before the whole clip.

  4. 4

    Check diagonals and motion cadence for combing, stutter, or doubled edges.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 15 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Video Type

video_type
Optional

Frame or field type of the source video.

  • Progressive

  • Interlaced

  • ProgressiveInterlaced

Parameter Mode

auto
Optional

Parameter mode for the selected model.

  • Auto

  • Manual

  • Relative

Field Order

field_order
Optional

Optional field order for interlaced input videos.

  • TopFirst

  • BottomFirst

  • Auto

Focus Fix Level

focus_fix_level
Optional

Downscale input for stronger correction of blurred subjects.

  • None

  • Normal

  • Strong

Compression

compression
Optional

Compression recovery strength.

Range: -1 – 1

Details

details
Optional

Detail reconstruction amount.

Range: -1 – 1

Prenoise

prenoise
Optional

Noise added before processing to reduce smoothing.

Range: 0 – 0.1

Noise

noise
Optional

Noise reduction amount.

Range: -1 – 1

Halo

halo
Optional

Halo reduction amount.

Range: -1 – 1

Preblur

preblur
Optional

Anti-aliasing and deblurring strength.

Range: -1 – 1

Blur

blur
Optional

Sharpness amount.

Range: -1 – 1

Grain

grain
Optional

Grain added after processing.

Range: 0 – 0.1

Grain Size

grain_size
Optional

Generated grain size.

Range: 0 – 5

Recover Original Detail

recover_original_detail_value
Optional

Amount of source detail to reintroduce into the output.

Range: 0 – 1

Model

model
Optional

Dione model variant.

Default: DV

  • DV

  • TV

  • Robust

  • Dehalo

  • Robust Dehalo

GaiaAvailable

Gaia

Gaia is designed to upscale and refine high quality CGI and animation sources. It assumes the input footage is already clean and well rendered, focusing on subtle refinement rather than heavy artifact removal. Gaia is not intended for heavily compressed or damaged footage and is best used as a final step to increase resolution while preserving the original source characteristics.

Try now

Properties

  • Supports Video Upscale workflows.

Best for

  • Optimized for high fidelity CGI and animation content
  • Gaia High Quality improves fine detail and aliased edges in already clean sources
  • Gaia Computer Generated is well suited for animation, linework, and stylized imagery

Tips

  • Refinement for high-quality CGI and animation

How to use this model

  1. 1

    Upload the source media at the best quality available.

  2. 2

    Choose the restoration or enhancement variant that matches the defect.

  3. 3

    Compare the output at full size and reduce strength if natural detail is lost.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 15 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Video Type

video_type
Optional

Frame or field type of the source video.

  • Progressive

  • Interlaced

  • ProgressiveInterlaced

Parameter Mode

auto
Optional

Parameter mode for the selected model.

  • Auto

  • Manual

  • Relative

Field Order

field_order
Optional

Optional field order for interlaced input videos.

  • TopFirst

  • BottomFirst

  • Auto

Focus Fix Level

focus_fix_level
Optional

Downscale input for stronger correction of blurred subjects.

  • None

  • Normal

  • Strong

Compression

compression
Optional

Compression recovery strength.

Range: -1 – 1

Details

details
Optional

Detail reconstruction amount.

Range: -1 – 1

Prenoise

prenoise
Optional

Noise added before processing to reduce smoothing.

Range: 0 – 0.1

Noise

noise
Optional

Noise reduction amount.

Range: -1 – 1

Halo

halo
Optional

Halo reduction amount.

Range: -1 – 1

Preblur

preblur
Optional

Anti-aliasing and deblurring strength.

Range: -1 – 1

Blur

blur
Optional

Sharpness amount.

Range: -1 – 1

Grain

grain
Optional

Grain added after processing.

Range: 0 – 0.1

Grain Size

grain_size
Optional

Generated grain size.

Range: 0 – 5

Recover Original Detail

recover_original_detail_value
Optional

Amount of source detail to reintroduce into the output.

Range: 0 – 1

Model

model
Optional

Gaia model variant.

Default: CG

  • CG

  • High Quality

  • 2 Animation

IrisAvailable

Iris

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.

Try now

Properties

  • Supports Video Upscale workflows.

Best for

  • Specialized face recovery for older or degraded footage
  • Works with both progressive and interlaced sources
  • This model has been specifically trained for low quality and mid quality input videos.

Tips

  • Face recovery for degraded footage

How to use this model

  1. 1

    Upload the source media at the best quality available.

  2. 2

    Choose the restoration or enhancement variant that matches the defect.

  3. 3

    Compare the output at full size and reduce strength if natural detail is lost.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 15 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Video Type

video_type
Optional

Frame or field type of the source video.

  • Progressive

  • Interlaced

  • ProgressiveInterlaced

Parameter Mode

auto
Optional

Parameter mode for the selected model.

  • Auto

  • Manual

  • Relative

Field Order

field_order
Optional

Optional field order for interlaced input videos.

  • TopFirst

  • BottomFirst

  • Auto

Focus Fix Level

focus_fix_level
Optional

Downscale input for stronger correction of blurred subjects.

  • None

  • Normal

  • Strong

Compression

compression
Optional

Compression recovery strength.

Range: -1 – 1

Details

details
Optional

Detail reconstruction amount.

Range: -1 – 1

Prenoise

prenoise
Optional

Noise added before processing to reduce smoothing.

Range: 0 – 0.1

Noise

noise
Optional

Noise reduction amount.

Range: -1 – 1

Halo

halo
Optional

Halo reduction amount.

Range: -1 – 1

Preblur

preblur
Optional

Anti-aliasing and deblurring strength.

Range: -1 – 1

Blur

blur
Optional

Sharpness amount.

Range: -1 – 1

Grain

grain
Optional

Grain added after processing.

Range: 0 – 0.1

Grain Size

grain_size
Optional

Generated grain size.

Range: 0 – 5

Recover Original Detail

recover_original_detail_value
Optional

Amount of source detail to reintroduce into the output.

Range: 0 – 1

Model

model
Optional

Iris model variant.

Default: Low Quality

  • Low Quality

  • Medium Quality

pnat-1Available

Proteus Natural

Proteus Natural is an update to the popular Proteus model, designed to eliminate over sharpening and over enhancement that can occasionally occur during upscaling. This next generation refinement delivers a more natural, softer output while preserving texture and source character. Proteus Natural reduces sharpening halos, aliasing, and background distortion, producing clean, stable upscales across a wide range of video sources and supporting both local and cloud workflows.

Try now

Properties

  • Supports Video Upscale workflows.

Best for

  • Designed for a more natural, restrained enhancement compared to the original Proteus model.
  • Reduces halos, aliasing, and facial distortion, especially in small details and background faces.
  • Avoids over sharpening or texture exaggeration and integrates well into multi-step enhancement workflows

Tips

  • Next-generation natural enhancement

How to use this model

  1. 1

    Upload the source media at the best quality available.

  2. 2

    Choose the restoration or enhancement variant that matches the defect.

  3. 3

    Compare the output at full size and reduce strength if natural detail is lost.

Examples

A reviewed video output created with Proteus Natural in Omnipix.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 15 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Video Type

video_type
Optional

Frame or field type of the source video.

  • Progressive

  • Interlaced

  • ProgressiveInterlaced

Parameter Mode

auto
Optional

Parameter mode for the selected model.

  • Auto

  • Manual

  • Relative

Field Order

field_order
Optional

Optional field order for interlaced input videos.

  • TopFirst

  • BottomFirst

  • Auto

Focus Fix Level

focus_fix_level
Optional

Downscale input for stronger correction of blurred subjects.

  • None

  • Normal

  • Strong

Compression

compression
Optional

Compression recovery strength.

Range: -1 – 1

Details

details
Optional

Detail reconstruction amount.

Range: -1 – 1

Prenoise

prenoise
Optional

Noise added before processing to reduce smoothing.

Range: 0 – 0.1

Noise

noise
Optional

Noise reduction amount.

Range: -1 – 1

Halo

halo
Optional

Halo reduction amount.

Range: -1 – 1

Preblur

preblur
Optional

Anti-aliasing and deblurring strength.

Range: -1 – 1

Blur

blur
Optional

Sharpness amount.

Range: -1 – 1

Grain

grain
Optional

Grain added after processing.

Range: 0 – 0.1

Grain Size

grain_size
Optional

Generated grain size.

Range: 0 – 5

Recover Original Detail

recover_original_detail_value
Optional

Amount of source detail to reintroduce into the output.

Range: 0 – 1
rhea-1Available

Rhea

Rhea is a high fidelity enhancement model designed for 4x 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 4x scale and is best suited for workflows where maximum detail preservation is prioritized over render speed.

Try now

Properties

  • Supports Video Upscale workflows.

Best for

  • Optimized for high quality 4x 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

Tips

  • High-fidelity 4x upscaling for fine detail

How to use this model

  1. 1

    Upload the source media at the best quality available.

  2. 2

    Choose the restoration or enhancement variant that matches the defect.

  3. 3

    Compare the output at full size and reduce strength if natural detail is lost.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 15 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Video Type

video_type
Optional

Frame or field type of the source video.

  • Progressive

  • Interlaced

  • ProgressiveInterlaced

Parameter Mode

auto
Optional

Parameter mode for the selected model.

  • Auto

  • Manual

  • Relative

Field Order

field_order
Optional

Optional field order for interlaced input videos.

  • TopFirst

  • BottomFirst

  • Auto

Focus Fix Level

focus_fix_level
Optional

Downscale input for stronger correction of blurred subjects.

  • None

  • Normal

  • Strong

Compression

compression
Optional

Compression recovery strength.

Range: -1 – 1

Details

details
Optional

Detail reconstruction amount.

Range: -1 – 1

Prenoise

prenoise
Optional

Noise added before processing to reduce smoothing.

Range: 0 – 0.1

Noise

noise
Optional

Noise reduction amount.

Range: -1 – 1

Halo

halo
Optional

Halo reduction amount.

Range: -1 – 1

Preblur

preblur
Optional

Anti-aliasing and deblurring strength.

Range: -1 – 1

Blur

blur
Optional

Sharpness amount.

Range: -1 – 1

Grain

grain
Optional

Grain added after processing.

Range: 0 – 0.1

Grain Size

grain_size
Optional

Generated grain size.

Range: 0 – 5

Recover Original Detail

recover_original_detail_value
Optional

Amount of source detail to reintroduce into the output.

Range: 0 – 1
slf-1Available

Starlight Fast 1

Starlight Fast 1 is the first generation diffusion video enhancement model optimized for speed. It delivers fast results and is intended for workflows where performance and turnaround time are prioritized over maximum quality. Fast 1 provides automatic enhancement with sharper detail than traditional upscalers, making it well suited for rapid iteration or time sensitive processing that still require stunning results.

Try now

Properties

  • Supports Video Upscale workflows.

Best for

  • First generation fast diffusion model optimized for quick results
  • Prioritizes speed over maximum quality and realism

Tips

  • First generation generative upscaling for speed

How to use this model

  1. 1

    Upload the source media at the best quality available.

  2. 2

    Choose the restoration or enhancement variant that matches the defect.

  3. 3

    Compare the output at full size and reduce strength if natural detail is lost.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 15 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Start Frame Index

start_idx
Optional

First source frame index to process.

Range: 0 – +∞

End Frame Index

end_idx
Optional

Last source frame index to process.

Upscaling Factor

upscaling_factor
Optional

Upscaling factor for Starlight processing.

Low Sharpness

low_sharpness
Optional

Use lower sharpness in Starlight processing.

Keep Original

keep_original
Optional

Preserve more of the original source detail.

FFmpeg Encoding

ffmpeg_encoding
Optional

Optional FFmpeg encoding override.

Watermark Path

wm_path
Optional

Optional watermark path.

FFmpeg Preprocessing Filters

ffmpeg_preproc_filters
Optional

Optional FFmpeg preprocessing filters.

slf-2Available

Starlight Fast 2

Starlight Fast 2 is a second generation diffusion-based video enhancement model designed for improved speed and quality. It delivers significantly faster results than Fast 1 while producing more realistic outputs and sharper details. Fast 2 balances performance and quality, making it well suited for high volume processing, rapid turnaround workflows, and scenarios where speed is critical but visual fidelity still matters.

Try now

Properties

  • Supports Video Upscale workflows.

Best for

  • Up to 2x faster performance compared to Starlight Fast 1
  • Produces more realistic results and sharper detail than previous model
  • Ideal for high volume and time sensitive workflows that require speed with improved quality

Tips

  • 2x faster diffusion upscaling with higher fidelity

How to use this model

  1. 1

    Upload the source media at the best quality available.

  2. 2

    Choose the restoration or enhancement variant that matches the defect.

  3. 3

    Compare the output at full size and reduce strength if natural detail is lost.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 15 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Start Frame Index

start_idx
Optional

First source frame index to process.

Range: 0 – +∞

End Frame Index

end_idx
Optional

Last source frame index to process.

Upscaling Factor

upscaling_factor
Optional

Upscaling factor for Starlight processing.

Low Sharpness

low_sharpness
Optional

Use lower sharpness in Starlight processing.

Keep Original

keep_original
Optional

Preserve more of the original source detail.

FFmpeg Encoding

ffmpeg_encoding
Optional

Optional FFmpeg encoding override.

Watermark Path

wm_path
Optional

Optional watermark path.

FFmpeg Preprocessing Filters

ffmpeg_preproc_filters
Optional

Optional FFmpeg preprocessing filters.

slhq-1Available

Starlight HQ

Starlight HQ is a high quality enhancement model designed for modern, high resolution video sources. It delivers a strong balance of detail and sharpness while preserving the visual intent of the original footage. Unlike restoration focused models such as Starlight Mini, HQ is optimized for clean progressive video and larger source resolutions. It supports inputs from 480p through 4K and can render native 4K outputs, making it well suited for modern digital camera footage and high resolution finishing. Starlight HQ can run locally in Topaz Video or in the cloud via API. For local processing, the model uses a larger architecture that prioritizes visual fidelity over speed and requires an NVIDIA GPU with at least 10GB of VRAM, with 12GB or more recommended.

Try now

Properties

  • Supports Video Upscale workflows.

Best for

  • High fidelity diffusion enhancement for modern digital camera sources
  • Supports larger inputs up to 4K with native 4K output
  • Ideal for high resolution workflows where maximum visual quality is the priority

Tips

  • Maximum quality generative enhancement for modern high-resolution video

How to use this model

  1. 1

    Upload the source media at the best quality available.

  2. 2

    Choose the restoration or enhancement variant that matches the defect.

  3. 3

    Compare the output at full size and reduce strength if natural detail is lost.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 15 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Start Frame Index

start_idx
Optional

First source frame index to process.

Range: 0 – +∞

End Frame Index

end_idx
Optional

Last source frame index to process.

Upscaling Factor

upscaling_factor
Optional

Upscaling factor for Starlight processing.

Low Sharpness

low_sharpness
Optional

Use lower sharpness in Starlight processing.

Keep Original

keep_original
Optional

Preserve more of the original source detail.

FFmpeg Encoding

ffmpeg_encoding
Optional

Optional FFmpeg encoding override.

Watermark Path

wm_path
Optional

Optional watermark path.

FFmpeg Preprocessing Filters

ffmpeg_preproc_filters
Optional

Optional FFmpeg preprocessing filters.

slm-1Available

Starlight Mini

Starlight Mini is the first local diffusion model for video enhancement, delivering the core strengths of Starlight technology, optimized for desktop workflows. It enables diffusion based restoration and enhancement without relying on cloud processing. Mini is currently the most powerful diffusion-based video enhancement available for local desktop use. Starlight Mini is well suited for degraded and archival sources, including 8mm and 16mm film, MiniDV, and standard definition video with automatic deinterlacing. Its output emphasizes natural texture and motion consistency, helping reduce flicker, banding, and overly harsh detail.

Try now

Properties

  • Supports Video Upscale workflows.

Best for

  • First and most powerful diffusion based video enhancement model available for local desktop processing
  • Ideal for restoring degraded, archival, and low resolution footage that challenges traditional models
  • Produces natural, stable results with reduced flicker, banding, and background artifacts

Tips

  • Powerful local diffusion restoration for archival and interlaced footage

How to use this model

  1. 1

    Upload the source media at the best quality available.

  2. 2

    Choose the restoration or enhancement variant that matches the defect.

  3. 3

    Compare the output at full size and reduce strength if natural detail is lost.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 15 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Start Frame Index

start_idx
Optional

First source frame index to process.

Range: 0 – +∞

End Frame Index

end_idx
Optional

Last source frame index to process.

Upscaling Factor

upscaling_factor
Optional

Upscaling factor for Starlight processing.

Low Sharpness

low_sharpness
Optional

Use lower sharpness in Starlight processing.

Keep Original

keep_original
Optional

Preserve more of the original source detail.

FFmpeg Encoding

ffmpeg_encoding
Optional

Optional FFmpeg encoding override.

Watermark Path

wm_path
Optional

Optional watermark path.

FFmpeg Preprocessing Filters

ffmpeg_preproc_filters
Optional

Optional FFmpeg preprocessing filters.

sl-1Available

Starlight Precise 1

Starlight Precise 1 is the original diffusion-based video enhancement model and the first of its kind designed specifically for video. Originally developed as Project Starlight, it was created to enhance footage previously considered impossible to restore, including degraded film and low resolution GenAI video. Precise 1 is a generative diffusion model that intelligently improves detail, temporal consistency, and structure while preserving artistic intent, performing all enhancement automatically without manual controls.

Try now

Properties

  • Supports Video Upscale workflows.

Best for

  • First ever diffusion model purpose built for video enhancement
  • Transforms degraded, low resolution footage into clean, consistent HD or 4K results
  • High quality, automatic enhancement with no sliders or manual tuning required

Tips

  • Restore footage once considered impossible with fully automatic diffusion enhancement

How to use this model

  1. 1

    Upload the source media at the best quality available.

  2. 2

    Choose the restoration or enhancement variant that matches the defect.

  3. 3

    Compare the output at full size and reduce strength if natural detail is lost.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 15 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Start Frame Index

start_idx
Optional

First source frame index to process.

Range: 0 – +∞

End Frame Index

end_idx
Optional

Last source frame index to process.

Upscaling Factor

upscaling_factor
Optional

Upscaling factor for Starlight processing.

Low Sharpness

low_sharpness
Optional

Use lower sharpness in Starlight processing.

Keep Original

keep_original
Optional

Preserve more of the original source detail.

FFmpeg Encoding

ffmpeg_encoding
Optional

Optional FFmpeg encoding override.

Watermark Path

wm_path
Optional

Optional watermark path.

FFmpeg Preprocessing Filters

ffmpeg_preproc_filters
Optional

Optional FFmpeg preprocessing filters.

slp-2Available

Starlight Precise 2

Starlight Precise 2 is a second generation diffusion video model designed to deliver more natural faces and skin tones for native GenAI video sources. It prioritizes realism and quality while preserving artistic intent. Precise 2 intelligently refines facial detail, skin texture, and structure. Using a single frame diffusion architecture, it reduces ghosting and instability in fast moving, inconsistent, or heavily compressed footage, resulting in improved clarity and temporal consistency.

Try now

Properties

  • Supports Video Upscale workflows.

Best for

  • Restores natural facial detail and skin tones while minimizing synthetic or plastic artifacts
  • Best choice for enhancing GenAI video while preserving creative intent and visual structure
  • Delivers improved stability and detail recovery for difficult or inconsistent footage

Tips

  • Bring realism to GenAI video with natural faces, skin tones, and stable motion

How to use this model

  1. 1

    Upload the source media at the best quality available.

  2. 2

    Choose the restoration or enhancement variant that matches the defect.

  3. 3

    Compare the output at full size and reduce strength if natural detail is lost.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 15 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Start Frame Index

start_idx
Optional

First source frame index to process.

Range: 0 – +∞

End Frame Index

end_idx
Optional

Last source frame index to process.

Upscaling Factor

upscaling_factor
Optional

Upscaling factor for Starlight processing.

Low Sharpness

low_sharpness
Optional

Use lower sharpness in Starlight processing.

Keep Original

keep_original
Optional

Preserve more of the original source detail.

FFmpeg Encoding

ffmpeg_encoding
Optional

Optional FFmpeg encoding override.

Watermark Path

wm_path
Optional

Optional watermark path.

FFmpeg Preprocessing Filters

ffmpeg_preproc_filters
Optional

Optional FFmpeg preprocessing filters.

slp-2.5Available

Starlight Precise 2.5

Starlight Precise 2.5 is a diffusion video enhancement model designed to improve realism in AI-generated video by reducing plastic or artificial artifacts. Building on Precise 2, it enhances facial detail while improving fabrics, materials, and the clarity of text, labels, and logos. Precise 2.5 is well suited to upscale and enhance AI-generated footage that already has strong composition and structure but appears soft or slightly artificial. It also performs well on archival content where sufficient visual information exists, such as digital video footage from the 2000s onward.

Try now

Properties

  • Supports Video Upscale workflows.

Best for

  • Improved realism for AI-generated video with more natural faces, materials, and textures
  • Enhanced rendering of text, labels, and fine detail for higher fidelity results
  • Broad applicability across GenAI and modern archival footage with consistent, stable outputs

Tips

  • Improved realism for AI-generated video with enhanced faces, texture detail, and text clarity

How to use this model

  1. 1

    Upload the source media at the best quality available.

  2. 2

    Choose the restoration or enhancement variant that matches the defect.

  3. 3

    Compare the output at full size and reduce strength if natural detail is lost.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 15 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Start Frame Index

start_idx
Optional

First source frame index to process.

Range: 0 – +∞

End Frame Index

end_idx
Optional

Last source frame index to process.

Upscaling Factor

upscaling_factor
Optional

Upscaling factor for Starlight processing.

Low Sharpness

low_sharpness
Optional

Use lower sharpness in Starlight processing.

Keep Original

keep_original
Optional

Preserve more of the original source detail.

FFmpeg Encoding

ffmpeg_encoding
Optional

Optional FFmpeg encoding override.

Watermark Path

wm_path
Optional

Optional watermark path.

FFmpeg Preprocessing Filters

ffmpeg_preproc_filters
Optional

Optional FFmpeg preprocessing filters.

wonder-1Available

Starlight Sharp

Starlight Sharp is a diffusion-based video enhancement model optimized for local or cloud processing. It is designed to sharpen low-res blurry videos and improve clarity on small faces. Starlight Sharp is used for restoration, detail recovery and compression cleanup. Unlike Mini, Starlight Sharp assumes a progressive input and does not perform automatic deinterlacing.

Try now

Properties

  • Supports Video Upscale workflows.

Best for

  • Local first diffusion-based restoration optimized for speed and sharp detail
  • Restores clarity in degraded or low resolution footage
  • Best suited for progressive or pre-deinterlaced sources in local desktop workflow

Tips

  • Fast local restoration with sharper detail for clean, progressive video

How to use this model

  1. 1

    Upload the source media at the best quality available.

  2. 2

    Choose the restoration or enhancement variant that matches the defect.

  3. 3

    Compare the output at full size and reduce strength if natural detail is lost.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 15 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Start Frame Index

start_idx
Optional

First source frame index to process.

Range: 0 – +∞

End Frame Index

end_idx
Optional

Last source frame index to process.

Upscaling Factor

upscaling_factor
Optional

Upscaling factor for Starlight processing.

Low Sharpness

low_sharpness
Optional

Use lower sharpness in Starlight processing.

Keep Original

keep_original
Optional

Preserve more of the original source detail.

FFmpeg Encoding

ffmpeg_encoding
Optional

Optional FFmpeg encoding override.

Watermark Path

wm_path
Optional

Optional watermark path.

FFmpeg Preprocessing Filters

ffmpeg_preproc_filters
Optional

Optional FFmpeg preprocessing filters.

TheiaAvailable

Theia

Theia is a clarity focused enhancement model designed to sharpen and enhance detail in video footage while controlling noise. It is well suited for situations where additional detail is needed and a hands on approach to tuning results is preferred. Theia provides granular manual control through three adjustable parameters and includes two fine tuning modes. Fine Tune Fidelity prioritizes stable, consistent detail with reduced artifacts, while Fine Tune Detail aggressively enhances detail on a per frame basis and may introduce subtle variation between frames.

Try now

Properties

  • Supports Video Upscale workflows.

Best for

  • Clarity focused sharpening and detail enhancement with noise control
  • Granular manual adjustment using three core parameters
  • Fine Tune Fidelity for stable results and Fine Tune Detail for aggressive detail extraction

Tips

  • Manual clarity and detail control

How to use this model

  1. 1

    Upload the source media at the best quality available.

  2. 2

    Choose the restoration or enhancement variant that matches the defect.

  3. 3

    Compare the output at full size and reduce strength if natural detail is lost.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 15 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Video Type

video_type
Optional

Frame or field type of the source video.

  • Progressive

  • Interlaced

  • ProgressiveInterlaced

Parameter Mode

auto
Optional

Parameter mode for the selected model.

  • Auto

  • Manual

  • Relative

Field Order

field_order
Optional

Optional field order for interlaced input videos.

  • TopFirst

  • BottomFirst

  • Auto

Focus Fix Level

focus_fix_level
Optional

Downscale input for stronger correction of blurred subjects.

  • None

  • Normal

  • Strong

Compression

compression
Optional

Compression recovery strength.

Range: -1 – 1

Details

details
Optional

Detail reconstruction amount.

Range: -1 – 1

Prenoise

prenoise
Optional

Noise added before processing to reduce smoothing.

Range: 0 – 0.1

Noise

noise
Optional

Noise reduction amount.

Range: -1 – 1

Halo

halo
Optional

Halo reduction amount.

Range: -1 – 1

Preblur

preblur
Optional

Anti-aliasing and deblurring strength.

Range: -1 – 1

Blur

blur
Optional

Sharpness amount.

Range: -1 – 1

Grain

grain
Optional

Grain added after processing.

Range: 0 – 0.1

Grain Size

grain_size
Optional

Generated grain size.

Range: 0 – 5

Recover Original Detail

recover_original_detail_value
Optional

Amount of source detail to reintroduce into the output.

Range: 0 – 1

Model

model
Optional

Theia model variant.

Default: Fine Tune Detail

  • Fine Tune Detail

  • Fine Tune Fidelity

prob-4Retired

Proteus

Proteus delivers high quality results across a wide range of sources and is recommended as the default model for most common video upscaling projects. A versatile, general purpose enhancement model for upscaling, denoising, and sharpening a wide range of low to medium quality video sources. Proteus performs especially well on low to medium quality footage, including old, grainy, or heavily compressed video.

Properties

  • Supports Video Upscale workflows.

Best for

  • General purpose and most recommended video enhancement model
  • Effective on both progressive and interlaced footage, commonly used to upscale legacy low resolution content to 4K
  • Offers modifiable parameters for fine tuning results, including controls for compression recovery, detail enhancement, sharpening, noise reduction, dehalo, and anti aliasing or deblur

Tips

  • The default choice for video enhancement

How to use this model

  1. 1

    Upload the source media at the best quality available.

  2. 2

    Choose the restoration or enhancement variant that matches the defect.

  3. 3

    Compare the output at full size and reduce strength if natural detail is lost.

Parameters

Video

video
Required

Source video URL

Resolution

resolution
Optional

Desired output video resolution.

Default: 1080p

  • 720p

  • 1080p

  • 4k

Frame Rate

frame_rate
Optional

Desired output frame rate.

Default: 30Range: 1 – 240

Output Container

output_container
Optional

Desired output container.

Default: mp4

  • mp4

  • mov

  • mkv

Audio Transfer

audio_transfer
Optional

How to transfer audio to the output video.

Default: Copy

  • Copy

  • Convert

  • None

Audio Codec

audio_codec
Optional

Audio codec to use when audio is copied or converted.

Default: AAC

  • AAC

  • AC3

  • PCM

Video Encoder

video_encoder
Optional

Video encoder for the output video.

Default: H265

  • AV1

  • H264

  • H265

  • VP9

Dynamic Compression Level

dynamic_compression_level
Optional

Automatic compression level for output encoding.

Default: High

  • Low

  • Mid

  • High

Crop To Fit

crop_to_fit
Optional

Center crop the output to fit the requested dimensions.

Video Type

video_type
Optional

Frame or field type of the source video.

  • Progressive

  • Interlaced

  • ProgressiveInterlaced

Parameter Mode

auto
Optional

Parameter mode for the selected model.

  • Auto

  • Manual

  • Relative

Field Order

field_order
Optional

Optional field order for interlaced input videos.

  • TopFirst

  • BottomFirst

  • Auto

Focus Fix Level

focus_fix_level
Optional

Downscale input for stronger correction of blurred subjects.

  • None

  • Normal

  • Strong

Compression

compression
Optional

Compression recovery strength.

Range: -1 – 1

Details

details
Optional

Detail reconstruction amount.

Range: -1 – 1

Prenoise

prenoise
Optional

Noise added before processing to reduce smoothing.

Range: 0 – 0.1

Noise

noise
Optional

Noise reduction amount.

Range: -1 – 1

Halo

halo
Optional

Halo reduction amount.

Range: -1 – 1

Preblur

preblur
Optional

Anti-aliasing and deblurring strength.

Range: -1 – 1

Blur

blur
Optional

Sharpness amount.

Range: -1 – 1

Grain

grain
Optional

Grain added after processing.

Range: 0 – 0.1

Grain Size

grain_size
Optional

Generated grain size.

Range: 0 – 5

Recover Original Detail

recover_original_detail_value
Optional

Amount of source detail to reintroduce into the output.

Range: 0 – 1