ComfyUI Node: VAELoaderDisTorch2MultiGPU
Category
multigpu/distorch_2
Inputs
vae_name
- pixel_space
compute_device
- cpu
- cuda:0
virtual_vram_gb FLOAT
donor_device
- cpu
- cuda:0
expert_mode_allocations STRING
eject_models BOOLEAN
Outputs
VAE
Extension: ComfyUI-MultiGPU
This extension adds CUDA device selection to supported loader nodes in ComfyUI. By monkey-patching ComfyUI’s memory management, each model component (like UNet, Clip, or VAE) can be loaded on a specific GPU. Examples included are multi-GPU workflows for SDXL, FLUX, LTXVideo, and Hunyuan Video for both standard and GGUF loader nodes.
Authored by pollockjj
Run ComfyUI workflows in the Cloud!
No downloads or installs are required. Pay only for active GPU usage, not idle time. No complex setups and dependency issues
Learn more