SelectVAEDevice - ComfyUI Built-in Node Documentation

Overview

This node allows you to manually select which GPU device the VAE model should be placed on. By default, the VAE is placed on the device assigned by the model loader, but you can pin it to a specific GPU (e.g., gpu:0, gpu:1). If the selected device is not available on your machine, the node will pass the VAE through unchanged and log a message instead of failing.

Inputs

Parameter	Description	Data Type	Required	Range
`vae`	The VAE model to assign to a specific device.	VAE	Yes
`device`	The target device for the VAE. `"default"` restores the device assigned by the loader. `"gpu:N"` pins the VAE to the Nth available GPU. CPU is not a supported choice and will be ignored if provided. (default: `"default"`)	COMBO	Yes	`"default"` `"gpu:0"` `"gpu:1"` `"gpu:2"` `"gpu:3"` `"gpu:4"` `"gpu:5"` `"gpu:6"` `"gpu:7"`

Outputs

Output Name	Description	Data Type
`vae`	The VAE model, now assigned to the selected device. If the requested device is unavailable or invalid, the VAE is passed through unchanged.	VAE

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): 011154043fc02f930b0074de656bb24baf4dfe74bcfd2e89ea76284f0a5b7d8e

SelectModelDevice - ComfyUI Built-in Node Documentation

GeminiNodeV2 - ComfyUI Built-in Node Documentation

​Overview

​Inputs

​Outputs

Overview

Inputs

Outputs