Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.comfy.org/llms.txt

Use this file to discover all available pages before exploring further.

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

ParameterData TypeRequiredRangeDescription
modelMODELYes-The input model to modify with a new compute data type
dtypeSTRINGYes”default"
"fp32"
"fp16"
"bf16”
The computational data type to apply to the model (default: “default”)

Outputs

Output NameData TypeDescription
modelMODELThe modified model with the new compute data type applied

Source fingerprint (SHA-256): bc65f1e452d0122ad175a8b95f38a36503253c9908157037c516496e65c828e6