Save 4 hours! We auto-setup your workflow! Free!

Drop your workflow.json — we handle every dependency, custom node, and model. Just open the link and run.

Auto-Setup Workflow Json (Free) Now!
ComfyUI > Nodes > ComfyUI-FlowDenoise

ComfyUI Extension: ComfyUI-FlowDenoise

Repo Name

ComfyUI-FlowDenoise

Author
AIMZ-GFX (Account age: 62 days)
Nodes
View all nodes(3)
Latest Updated
2026-06-01
Github Stars
0.03K

How to Install ComfyUI-FlowDenoise

Install this extension via the ComfyUI Manager by searching for ComfyUI-FlowDenoise
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI-FlowDenoise in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

ComfyUI-FlowDenoise Description

ComfyUI-FlowDenoise enhances image processing by integrating advanced denoising capabilities into the ComfyUI framework. It efficiently reduces noise in images, improving clarity and detail retention.

ComfyUI-FlowDenoise Introduction

ComfyUI-FlowDenoise is an advanced extension designed to enhance the quality of AI-generated videos by reducing unwanted noise and artifacts. Developed by the AIMZ GFX Division, this tool is particularly useful for AI artists who work with video content and seek to improve the visual consistency of their creations. The extension employs cutting-edge optical flow estimation techniques to align video frames, effectively minimizing issues such as color flicker, chroma spikes, and temporal noise patterns. By providing professional-grade motion-compensated temporal video denoising, ComfyUI-FlowDenoise helps you achieve smoother and more visually appealing video outputs.

How ComfyUI-FlowDenoise Works

At the core of ComfyUI-FlowDenoise is the concept of optical flow estimation, which is used to track the movement of objects between consecutive video frames. Imagine each frame of your video as a snapshot in time. The extension uses models like MEMFOF and RAFT to calculate how each pixel moves from one frame to the next. This information allows the extension to align frames accurately, creating a stable reference point for denoising.

Once the frames are aligned, the extension separates the video into chroma (color) and luma (brightness) components. By independently controlling the denoising strength for each component, you can fine-tune the balance between preserving detail and reducing noise. This process is akin to cleaning a painting by carefully removing dirt without damaging the underlying artwork.

ComfyUI-FlowDenoise Features

  • Optical Flow Alignment: Utilizes MEMFOF or RAFT models to align frames, ensuring smooth transitions and reducing motion artifacts.
  • Batched Inference Pipeline: Optimized for high-throughput processing on GPUs with high VRAM, allowing for efficient handling of large video files.
  • Chroma/Luma Separation: Offers independent control over denoising strength for color and brightness, enabling precise adjustments.
  • Multiple Color Spaces: Supports YCbCr, HSV, and LAB color spaces, providing flexibility in how colors are processed.
  • Noise Visualization: Includes heatmap, signed (red/blue), and grayscale preview modes to help you understand and adjust the denoising process.
  • Scene-Aware Processing: Automatically detects scene changes to prevent blending artifacts across different scenes.

ComfyUI-FlowDenoise Models

ComfyUI-FlowDenoise supports several models for optical flow estimation:

  • MEMFOF: A state-of-the-art model that provides high accuracy in motion estimation, ideal for complex scenes.
  • RAFT Small and Large: These models offer a balance between speed and accuracy, suitable for various video content types. Choosing the right model depends on your specific needs. For instance, MEMFOF is recommended for high-detail videos, while RAFT models can be used for faster processing with slightly less precision.

Troubleshooting ComfyUI-FlowDenoise

Here are some common issues you might encounter while using ComfyUI-FlowDenoise, along with solutions:

  • Issue: Video Output is Blurry
  • Solution: Check the denoising strength settings. Reducing the chroma or luma strength might help preserve more detail.
  • Issue: Artifacts Appear at Scene Changes
  • Solution: Ensure that scene-aware processing is enabled to automatically detect and handle scene changes.
  • Issue: High VRAM Usage
  • Solution: Adjust the batch size or use a smaller model like RAFT Small to reduce memory consumption.
  • FAQ:
  • Q: Can I use ComfyUI-FlowDenoise with any video format?
  • A: Yes, the extension is compatible with various video formats, but ensure your input video is properly loaded using compatible nodes.

Learn More about ComfyUI-FlowDenoise

To further explore the capabilities of ComfyUI-FlowDenoise, consider checking out the following resources:

  • Demo Video: Watch a full demonstration of the extension in action on YouTube.
  • ComfyUI-VideoHelperSuite: Learn about additional nodes for video workflows, which can complement your use of ComfyUI-FlowDenoise.
  • Community Forums: Join discussions with other AI artists and developers to share tips and get support. By leveraging these resources, you can maximize the potential of ComfyUI-FlowDenoise and enhance your video projects with professional-grade denoising techniques.

ComfyUI-FlowDenoise Related Nodes

RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

ComfyUI-FlowDenoise detailed guide | ComfyUI