This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHubThe 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 | Data Type | Required | Range | Description |
|---|---|---|---|---|
model | MODEL | Yes | - | The input model to modify with a new compute data type |
dtype | STRING | Yes | ”default" "fp32" "fp16" "bf16” | The computational data type to apply to the model (default: “default”) |
Outputs
| Output Name | Data Type | Description |
|---|---|---|
model | MODEL | The modified model with the new compute data type applied |
Source fingerprint (SHA-256):
bc65f1e452d0122ad175a8b95f38a36503253c9908157037c516496e65c828e6