ComfyUI  >  Nodes  >  ComfyUI Frame Interpolation

ComfyUI Extension: ComfyUI Frame Interpolation

Repo Name


Fannovel16 (Account age: 3140 days)
View all nodes (14)
Latest Updated
Github Stars

How to Install ComfyUI Frame Interpolation

Install this extension via the ComfyUI Manager by searching for  ComfyUI Frame Interpolation
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI Frame Interpolation 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
  • High-speed GPU machines
  • 200+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 50+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

ComfyUI Frame Interpolation Description

ComfyUI Frame Interpolation enhances animation by using the KSampler node to gradually increase denoising, resulting in smoother transitions between frames. This efficient method improves visual quality in animated sequences.

ComfyUI Frame Interpolation Introduction

ComfyUI-Frame-Interpolation is an extension designed to enhance video frame interpolation within the ComfyUI framework. Video frame interpolation is a technique used to generate intermediate frames between existing ones, creating smoother motion in videos. This extension provides a set of custom nodes that facilitate this process, making it easier for AI artists to create high-quality, fluid animations from a series of images or video frames.

Key Features:

  • Improved Memory Management: The extension now uses less RAM and VRAM, making it more efficient.
  • Scheduling Multiplier Values: VFI nodes now accept scheduling multiplier values, allowing for more control over the interpolation process.

How ComfyUI Frame Interpolation Works

At its core, ComfyUI-Frame-Interpolation works by taking two or more frames and generating intermediate frames to create a smooth transition between them. This is achieved through various Video Frame Interpolation (VFI) models that predict the motion between frames and generate the necessary intermediate frames.

Basic Principles:

  1. Input Frames: You provide the extension with at least two frames (or more for certain models).
  2. Interpolation Models: The extension uses different VFI models to predict and generate intermediate frames.
  3. Output Frames: The generated frames are combined to create a smooth video sequence. Think of it like creating a flipbook animation where you only draw the key frames, and the extension fills in the gaps to make the motion appear fluid.

ComfyUI Frame Interpolation Features


  • KSampler Gradually Adding More Denoise: Efficiently adds denoise to frames.
  • GMFSS Fortuna VFI: Specialized for anime video frame interpolation.
  • IFRNet VFI: Intermediate Feature Refine Network for efficient frame interpolation.
  • IFUnet VFI: Uses RIFE with IFUNet, FusionNet, and RefineNet.
  • M2M VFI: Many-to-many splatting for efficient video frame interpolation.
  • RIFE VFI (4.0 - 4.9): Real-Time Intermediate Flow Estimation for video frame interpolation.
  • FILM VFI: Frame Interpolation for Large Motion.
  • Sepconv VFI: Uses adaptive separable convolution for video frame interpolation.
  • AMT VFI: All-Pairs Multi-Field Transforms for efficient frame interpolation.
  • Make Interpolation State List: Creates a list of states for interpolation.
  • STMFNet VFI: Requires at least 4 frames, can only do 2x interpolation for now.
  • FLAVR VFI: Same conditions as STMFNet.


  • Scheduling Multiplier Values: Adjust the interpolation process by setting scheduling multipliers.
  • Memory Management: Improved to use less RAM and VRAM, making the process more efficient.

ComfyUI Frame Interpolation Models

Available Models:

  • GMFSS Fortuna: Best for anime video frame interpolation.
  • IFRNet: Efficient for general video frame interpolation.
  • IFUnet: Combines multiple networks for refined interpolation.
  • M2M: Efficient for many-to-many frame interpolation.
  • RIFE (4.0 - 4.9): Real-time interpolation with various versions.
  • FILM: Handles large motion frame interpolation.
  • Sepconv: Uses adaptive separable convolution.
  • AMT: Efficient with all-pairs multi-field transforms.
  • STMFNet: Requires more frames but provides high-quality interpolation.
  • FLAVR: Similar to STMFNet but with different conditions.

When to Use Each Model:

  • GMFSS Fortuna: Use for anime or stylized animations.
  • IFRNet and IFUnet: General-purpose, efficient interpolation.
  • M2M: When dealing with complex, many-to-many frame transitions.
  • RIFE: Real-time applications with various versions for different needs.
  • FILM: Best for scenes with large motion.
  • Sepconv: When adaptive convolution is needed.
  • AMT: Efficient and versatile for various types of videos.
  • STMFNet and FLAVR: High-quality interpolation requiring more frames.

What's New with ComfyUI Frame Interpolation

Recent Updates:

  • Improved Memory Management: The extension now uses less RAM and VRAM, making it more efficient.
  • Scheduling Multiplier Values: VFI nodes now accept scheduling multiplier values, providing more control over the interpolation process. These updates enhance the performance and flexibility of the extension, making it more user-friendly and efficient for AI artists.

Troubleshooting ComfyUI Frame Interpolation

Common Issues and Solutions:

  1. Out of Memory Errors:
  • Solution: Use the clear_cache_after_n_frames setting to avoid running out of memory. Decreasing this value reduces the chance of memory issues but increases processing time.
  1. Installation Issues on Windows:
  • Solution: Run install.bat instead of or python to resolve issues related to cupy.
  1. Non-CUDA Device Support:
  • Solution: If you don't have an NVIDIA card, try using the taichi ops backend. Install it by running install.bat on Windows or pip install taichi on Linux, and change the ops_backend value from cupy to taichi in config.yaml.

Frequently Asked Questions:

  • Q: How do I load images for interpolation?
  • A: Use the LoadImages node from or .
  • Q: What if I only have two or three frames for STMFNet or FLAVR?
  • A: Use Load Images -> Other VFI node (FILM is recommended) with multiplier=4 -> STMFNet VFI/FLAVR VFI.

Learn More about ComfyUI Frame Interpolation

Additional Resources:

  • Tutorials and Documentation: Explore detailed guides and documentation to get the most out of ComfyUI-Frame-Interpolation.
  • Community Forums: Join community forums to ask questions, share your work, and get support from other AI artists and developers. By leveraging these resources, you can enhance your understanding and usage of ComfyUI-Frame-Interpolation, creating stunning animations and videos with ease.

ComfyUI Frame Interpolation Related Nodes


© Copyright 2024 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals.