Floyo
Floyo
Workflows
API
Pricing
Floyo
Floyo
Workflows
API
Pricing
Last updated
2026-05-27

Run hundreds of ComfyUI nodes and workflows in your browser.

ComfyUI and My Files on Floyo

ComfyUI-MemoryCleaner is a specialized tool designed to optimize memory usage in the ComfyUI environment, particularly beneficial for users working with large models. By efficiently cleaning up memory after intensive operations, it helps prevent out-of-memory (OOM) errors and enhances overall workflow stability.

  • Reduces memory usage significantly (30-45GB) after heavy operations, allowing for smoother processing of large models.
  • Integrates seamlessly into ComfyUI's workflow by placing the Memory Cleaner node strategically after resource-intensive tasks.
  • Offers both internal and external memory cleanup methods, ensuring higher success rates even in low-privilege environments.

Context

ComfyUI-MemoryCleaner serves as an essential extension for users of ComfyUI, focusing on memory management to enhance performance during resource-heavy tasks. Its primary goal is to mitigate memory-related issues by providing a systematic cleanup process that frees up system resources.

Key Features & Benefits

The tool includes a range of practical features that directly impact user experience. It allows users to configure aggressive memory trimming, manage privileges for optimal performance, and utilize external scripts for enhanced cleanup capabilities. These features are vital for maintaining efficient workflows, especially when handling large datasets or complex models.

Advanced Functionalities

ComfyUI-MemoryCleaner employs several advanced techniques to ensure effective memory management. It utilizes Windows API calls for OS-level memory trimming, which can significantly reduce memory usage. Additionally, it incorporates an external helper script that can be activated automatically if internal cleanup fails, ensuring a higher success rate in freeing memory.

Practical Benefits

This tool streamlines the workflow within ComfyUI by providing users with the ability to manage memory proactively. By preventing memory overflow and crashes during intensive tasks, it enhances control over the processing environment, improves the quality of outputs, and boosts overall efficiency.

Credits/Acknowledgments

The ComfyUI-MemoryCleaner was developed by eddy and is available under the Apache License 2.0. Contributions and feedback from the community are encouraged to enhance its functionality and usability.

Inner Nodes

MemoryCleaner

Discover most popular workflows

Hand-picked based on what hundreds of other artists looked at.