TopazVideoEnhanceV2 - ComfyUI Built-in Node Documentation

The Topaz Video Enhance V2 node allows you to upscale and enhance video using Topaz Labs’ AI models. It can increase resolution, adjust frame rate through interpolation, and apply creative or realistic enhancements to breathe new life into your video footage.

Inputs

Parameter	Description	Data Type	Required	Range
`video`	The input video to be processed. Must be in MP4 container format.	VIDEO	Yes	-
`upscaler_model`	The AI model used for upscaling the video. Selecting “Disabled” means no upscaling will be applied.	COMBO	Yes	`"Astra 2"` `"Starlight (Astra) Fast"` `"Starlight (Astra) Creative"` `"Starlight Precise 2.5"` `"Disabled"`
`upscaler_model.upscaler_resolution`	The target output resolution for the upscaler. This parameter is required when an upscaler model is selected (not “Disabled”).	COMBO	Conditional	`"FullHD (1080p)"` `"4K (2160p)"`
`upscaler_model.creativity`	Creative strength of the upscale. Available only for “Astra 2” and “Starlight (Astra) Creative” models. For Astra 2, it’s a slider (default: 0.5). For Starlight Creative, it’s a combo (default: “low”).	FLOAT / COMBO	Conditional	Astra 2: 0.0 to 1.0 (step 0.1) Starlight Creative: `"low"` `"middle"` `"high"`
`upscaler_model.prompt`	Optional descriptive (not instructive) scene prompt. Only available for the “Astra 2” model. Capped at 450 input frames (~15s @ 30fps) when set. Default: empty.	STRING	No	-
`upscaler_model.sharp`	Pre-enhance sharpness: 0.0=Gaussian blur, 0.5=passthrough (default), 1.0=USM sharpening. Only available for the “Astra 2” model. Default: 0.5.	FLOAT	No	0.0 to 1.0 (step 0.01)
`upscaler_model.realism`	Pulls output toward photographic realism. Leave at 0 for the model default. Only available for the “Astra 2” model. Default: 0.0.	FLOAT	No	0.0 to 1.0 (step 0.01)
`interpolation_model`	The AI model used for frame interpolation. Selecting “Disabled” means no interpolation will be applied.	COMBO	Yes	`"Disabled"` `"apo-8"`
`interpolation_model.interpolation_frame_rate`	Output frame rate. Required when interpolation model is “apo-8”. Default: 60.	INT	Conditional	15 to 240
`interpolation_model.interpolation_slowmo`	Slow-motion factor applied to the input video. For example, 2 makes the output twice as slow and doubles the duration. Default: 1.	INT	No	1 to 16
`interpolation_model.interpolation_duplicate`	Analyze the input for duplicate frames and remove them. Default: False.	BOOLEAN	No	True/False
`interpolation_model.interpolation_duplicate_threshold`	Detection sensitivity for duplicate frames. Default: 0.01.	FLOAT	No	0.001 to 0.1 (step 0.001)
`dynamic_compression_level`	CQP level for video compression. Default: “Low”.	COMBO	No	`"Low"` `"Mid"` `"High"`

Important Constraints:

At least one of upscaler_model or interpolation_model must be enabled (not “Disabled”), otherwise an error is raised.
The input video must be in MP4 container format.
The “Astra 2” model with a prompt is limited to 450 input frames (~15 seconds at 30fps). Without a prompt, it is limited to 9000 input frames.
When upscaler_model is not “Disabled”, the upscaler_resolution sub-parameter is required.
When interpolation_model is not “Disabled”, the interpolation_frame_rate sub-parameter is required.

Outputs

Output Name	Description	Data Type
`video`	The enhanced video output after applying the selected upscaling and/or interpolation filters.	VIDEO

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

Source fingerprint (SHA-256): d955e5bae683fa4d7e09e23f7cd06bc077ec5e4ab0b5c4f6d712b8358027998c

​Inputs

​Outputs

Inputs

Outputs