ComfyUI Node: Instant Load Diffusion Model
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.
Category
advanced/loaders/instanttensor
Inputs
unet_name
weight_dtype
- default
- fp8_e4m3fn
- fp8_e4m3fn_fast
- fp8_e5m2
Outputs
MODEL
Extension: ComfyUI-InstantTensorLoaders
InstantTensor-backed variants of ComfyUI's built-in model loader nodes for CUDA-only devices with streaming support for large models.
Authored by redstonewhite
Looking for a different node?
Run ComfyUI workflows without the setup
No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.