Video Upscale Models - Parameters Reference

This page is auto-generated from model configurations. Last updated: 2026-03-13.

This reference lists all available video upscale models and their parameters. Use these parameter names when calling the Generation API.

Models

Upscale your videos using FlashVSR with the fastest speeds!

Model ID: model_flash-vsr-video-upscale

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_flash-vsr-video-upscale/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`video`	file	Yes	-	-	-	-	Video to upscale
`upscaleFactor`	number	No	`2`	2	4	-	How much to upscale the image
`acceleration`	string	No	`regular`	-	-	`regular`, `high`, `full`	Acceleration mode for VAE decoding. Options: regular (best quality), high (balanced), full (fastest). More acceleration means longer duration videos can be processed too.
`colorFix`	boolean	No	`true`	-	-	-	Color correction enabled.
`quality`	number	No	`70`	0	100	-	Quality level for tile blending. Higher values (80-100) provide better quality with more tile overlap, lower values (0-40) prioritize speed. Recommended: 60-80 for balanced results.
`preserveAudio`	boolean	No	`false`	-	-	-	Preserve the audio of the input video.
`outputQuality`	string	No	`high`	-	-	`low`, `medium`, `high`, `maximum`	The quality of the output video
`outputWriteMode`	string	No	`balanced`	-	-	`fast`, `balanced`, `small`	The write mode of the output video

SeedVR2 Upscale Image is a model that can upscale images.

Model ID: model_seedvr-2-upscale-video

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_seedvr-2-upscale-video/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`video`	file	Yes	-	-	-	-	Video to upscale
`upscaleMode`	string	No	`factor`	-	-	`factor`, `target`	The mode to use for the upscale. If 'target', the upscale factor will be calculated based on the target resolution. If 'factor', the upscale factor will be used directly.
`upscaleFactor`	number	No	`2`	2	10	-	How much to upscale the image
`targetResolution`	string	No	`1080p`	-	-	`720p`, `1080p`, `1440p`, `2160p`	The target resolution to upscale to when Upscale Mode is target.
`noiseScale`	number	No	`0.1`	0	1	-	The noise scale to use for the generation process.
`outputQuality`	string	No	`high`	-	-	`low`, `medium`, `high`, `maximum`	The quality of the output video
`outputWriteMode`	string	No	`balanced`	-	-	`fast`, `balanced`, `small`	The write mode of the output video
`seed`	number	No	-	-	-	-	Random seed for reproducibility. If None, a random seed is chosen.

High-precision video upscaler optimized for portraits, faces and products.

Model ID: model_crystal-video-upscaler

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_crystal-video-upscaler/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`video`	file	Yes	-	-	-	-	An input video for upscaling
`scaleFactor`	number	No	`2`	1	200	-	Scale factor for upscaling (will be capped if output will exceed 4K)

Upscale videos by 4x, up to a maximum of 4k

Model ID: model_runway-upscale-v1

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_runway-upscale-v1/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`video`	file	Yes	-	-	-	-	Video file to upscale. Videos must be shorter than 40s and less than 4096px per side.

Topazlabs Video Upscale is a tool for enhancing video quality using advanced AI techniques.

Model ID: model_topazlabs-video-upscale

Capabilities: video2video

LLM Markdown: https://app.scenario.com/api/models/model_topazlabs-video-upscale/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`video`	file	Yes	-	-	-	-	Video file to upscale
`resolution`	string	No	`1080p`	-	-	`720p`, `1080p`, `4k`	Target resolution
`fps`	number	No	`60`	15	60	-	Target Frame-Per-Second