SelectModelDevice - ComfyUI Built-in Node Documentation

The Select Model Device node allows you to manually choose which device (CPU or a specific GPU) a diffusion model runs on.

The Select Model Device node allows you to manually choose which device (CPU or a specific GPU) a diffusion model runs on. It can move a model to a different device, and it handles conflicts with other multi-GPU nodes automatically. Selecting "default" restores the original device chosen by the model loader.

Inputs

Parameter	Description	Data Type	Required	Range
model	The diffusion model to place on a specific device.	MODEL	Yes
device	The target device for the model. Options are dynamically generated based on the available devices on the current machine. (default: "default")	COMBO	Yes	"default" "cpu" "gpu:0" "gpu:1" … (one "gpu:N" entry per detected GPU)

Parameter Details:

• "default": Restores the load and offload devices assigned by the model loader, even after a previous Select Model Device call.
• "cpu": Pins both the load and offload device to CPU.
• "gpu:N": Pins the load device to the Nth available GPU (for example, "gpu:0" for the first GPU). The offload device is restored to the loader’s original choice.

Important Notes:

• If the requested device does not exist on the current machine (for example, a workflow created on a 2-GPU machine is opened on a 1-GPU machine), the node passes the model through unchanged and logs a message instead of failing. Unknown gpu:N values are allowed during input validation so portable workflows do not error early.
• If the model is already on the requested device, the node uses a fast path and does not reload the model.
• When the requested device differs from the device the input model is already on, a fresh model is spawned using the loader’s reload factory so the new patcher owns independent weights on the new device.
• If the model loader does not support multi-GPU (no reload factory), the node passes the model through unchanged and logs a warning.
• When a MultiGPU CFG Split clone already occupies the selected device, that clone is pruned so two models are not bound to the same device.
• When a non-default device is selected (CPU or GPU), the node also adjusts the model’s compute dtype to one supported by that device.
• Placing this node after a node that has already consumed the model (for example, a KSampler) is not recommended, because any state changed by the prior node will be observed if the device matches the original.

Outputs

Output Name	Description	Data Type
model	The diffusion model, now placed on the selected device. If the device was invalid or unavailable, the model is passed through unchanged.	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): d02a8bd9612861cf696f03969fe693088351de5a72ccbd4c1aed405b104eb71e