ModelComputeDtype - ComfyUI Built-in Node Documentation

The ModelComputeDtype node changes the computational data type (precision) used by a model during processing. It creates a copy of the input model and applies the selected precision setting, which can help optimize memory usage and performance depending on your hardware. This is useful for debugging and testing different precision configurations.

Inputs

Parameter	Description	Data Type	Required	Range
`model`	The input model to modify with a new compute data type	MODEL	Yes	-
`dtype`	The computational data type to apply to the model (default: “default”)	STRING	Yes	”default" "fp32" "fp16" "bf16”

Outputs

Output Name	Description	Data Type
`model`	The modified model with the new compute data type applied	MODEL

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): bc65f1e452d0122ad175a8b95f38a36503253c9908157037c516496e65c828e6

LazyCache - ComfyUI Built-in Node Documentation

CFGNorm - ComfyUI Built-in Node Documentation

​Inputs

​Outputs

Inputs

Outputs