ComfyUI Node: Pipeline Memory Barrier

Authored by brosequist

Created

Updated

0 stars

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

utils/memory

Inputs

latent LATENT
log_memory BOOLEAN

Outputs

LATENT

Extension: ComfyUI-PipelineBarrier

A single node that flushes PyTorch's GPU memory cache and runs garbage collection between pipeline stages, preventing OOM errors in multi-stage workflows (e.g. two-pass video generation). Accepts a LATENT input and returns it unchanged.

Authored by brosequist

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.

Learn more