Add a GPU/CPU/MPS/XPU device to the parallel processing chain — ComfyUI node from ComfyUI-ParallelAnything. Run it in the cloud, no install required.

This suite of nodes unlocks high-performance parallel processing in ComfyUI by utilizing **Model Replication**. Unlike standard offloading which moves a single model instance between devices, these nodes create independent replicas of the model on each selected GPU/CPU, allowing for true simultaneous batch processing.

ComfyUI-ParallelAnything

device_id

percentage

previous_devices

Add a GPU/CPU/MPS/XPU device to the parallel processing chain

Name	Type	Default	Description
device_id	COMBO	cpu	Select available compute device (CPU/CUDA/MPS/XPU)
percentage	FLOAT	501–100	Percentage of batch (or layers for batch=1) to process on this device
previous_devicesopt	DEVICE_CHAIN		Connect from another ParallelDevice node to chain multiple GPUs

Parallel Device Config

Inputs (3)

Outputs (1)