ComfyUI and ComfyUI-MultiGPU

The custom node provides multi-GPU and virtual VRAM functionality, making it a complement that enhances the powerful, modular diffusion model GUI, API, and backend by extending its hardware utilization capabilities.

ComfyUI
72
Verified
ComfyUI-MultiGPU
62
Established
Maintenance 25/25
Adoption 10/25
Maturity 16/25
Community 21/25
Maintenance 20/25
Adoption 10/25
Maturity 16/25
Community 16/25
Stars: 106,230
Forks: 12,230
Downloads:
Commits (30d): 142
Language: Python
License: GPL-3.0
Stars: 823
Forks: 62
Downloads:
Commits (30d): 14
Language: Python
License: GPL-3.0
No Package No Dependents
No Package No Dependents

About ComfyUI

Comfy-Org/ComfyUI

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Supports diverse generative models across image, video, audio, and 3D modalities with intelligent memory management and GPU offloading for low-VRAM systems. The architecture uses an asynchronous queue system with incremental execution—only re-computing workflow nodes that have changed—and integrates LoRAs, ControlNets, and model merging capabilities. Extensible through custom nodes and external API providers, while maintaining fully offline operation for core functionality.

About ComfyUI-MultiGPU

pollockjj/ComfyUI-MultiGPU

This custom_node for ComfyUI adds one-click "Virtual VRAM" for any UNet and CLIP loader as well MultiGPU integration in WanVideoWrapper, managing the offload/Block Swap of layers to DRAM *or* VRAM to maximize the latent space of your card. Also includes nodes for directly loading entire components (UNet, CLIP, VAE) onto the device you choose

DisTorch2 uses a layer-distribution architecture to split model weights across CPU DRAM and multiple GPUs via byte-precise or ratio-based allocation, enabling users to offload static model components while reserving maximum VRAM for latent space computation. It supports universal `.safetensors` and GGUF model formats with three allocation modes: simple virtual VRAM sliders, expert byte/ratio specifications (e.g., `cuda:0,2.5gb;cpu,*`), and fraction-based distribution—compatible with all ComfyUI checkpoint, CLIP, VAE, ControlNet, and video generation loaders including WanVideoWrapper.

Scores updated daily from GitHub, PyPI, and npm data. How scores work