Updated Windows 11 Install Steps May 25, 2026 - jhogsett/EMA-VFI-WebUI GitHub Wiki

Pre-requisites

• Install Git for Windows (to get code from the GitHub repos)

  • https://git-scm.com/download/win

• Install Anaconda3 for windows (to run Python)

  • https://www.anaconda.com/download

• Install Microsoft Visual Studio (required by NVIDIA Cuda)

  • https://visualstudio.microsoft.com/thank-you-downloading-visual-studio/?sku=Community\&channel=Stable\&version=VS18\&source=VSLandingPage\&cid=2500\&passive=false
  • NOTE: Be sure to install the Desktop Development C++ components and older versions of the MSVC compilers (just in case)

• Install NVIDIA Cuda 12.4 (required by AI components to use your NVIDIA GPU)

  • https://developer.nvidia.com/cuda-12-4-0-download-archive
  • NOTE: Choose Custom Installation and deselect Visual Studio Integration under Cuda

• Install FFmpeg (needed to do video processing)

  • See https://ffmpeg.org/download.html#build-windows.
    • I use the Windows builds at https://www.gyan.dev/ffmpeg/builds/
  • Add the FFmpeg binary path to your Windows PATH environment variable
    • Press the Windows + S keys and search for "edit the system environment variables"
    • Choose the "control panel" result
    • Click the "Environment Variables" button
    • Add the full path of ffmpeg.exe (path name only) to the Path variables for user variables and system variables

Set Up Anaconda Environment

• Open an Anaconda3 command prompt

  • search for Anaconda3 in the Windows Start Menu
  • Choose Anaconda Prompt

• Create a new folder for the application such as C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI

(base) C:\>md C:\Users\YOURUSERNAME\conda
(base) C:\>cd C:\Users\YOURUSERNAME\conda
(base) C:\Users\YOURUSERNAME\conda>md EMA-VFI-WebUI

• Change into the new folder

(base) C:\Users\YOURUSERNAME\conda>cd EMA-VFI-WebUI

• Clone the EMA-VFI-WebUI application git repo

(base) C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI>git clone https://github.com/jhogsett/EMA-VFI-WebUI.git

Create the Anaconda environment from the environment.yml file

• Change into the cloned folder

(base) C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI>cd EMA-VFI-WebUI

• Create the environment

(base) C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI-WebUI>conda env create -f environment.yml

• Activate the environment

(base) C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI-WebUI>conda activate EMA-VFI-WebUI

Set Up the EMA-VFI Engine

Clone the EMA-VFI engine

• Change to the previous folder

(EMA-VFI-WebUI) C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI-WebUI>cd ..

• Clone the EMA-VFI git repo (EMA-VFI-WebUI)

(EMA-VFI-WebUI) C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI>git clone https://github.com/MCG-NJU/EMA-VFI.git

• Change into the newly cloned folder

(EMA-VFI-WebUI) C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI>cd EMA-VFI

• Create a folder for the model checkpoints

(EMA-VFI-WebUI) C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI>md ckpt

• Download the model checkpoints
  • Go to Google Drive at https://drive.google.com/drive/folders/16jUa3HkQ85Z5lb5gce1yoaWkP-rdCd0o?usp=sharing
  • Download these files and place into the C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI\ckpt folder
    • ours.pkl (251.5MB)
    • ours_t.pkl (251.5MB)

Check the EMA-VFI Engine installation by running an inference:

• Run the basic (non-time-based) demo

(EMA-VFI-WebUI) C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI>python demo_2x.py

• If it worked, there will be a new file out_2x.gif in this folder:

  • C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI\example

• Open it to confirm it created an animated gif of a toy train

(EMA-VFI-WebUI) C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI>start example\out_2x.gif

Install Real-ESRGAN

• Go back to the application root folder

(EMA-VFI-WebUI) C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI>cd ..

• Clone the repo

(EMA-VFI-WebUI) C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI>git clone https://github.com/xinntao/Real-ESRGAN.git

• Change into the newly cloned folder

(EMA-VFI-WebUI) C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI>cd Real-ESRGAN

• Run the following (to finalize the setup):

(EMA-VFI-WebUI) C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\Real-ESRGAN>python setup.py develop

IMPORTANT You will need to patch basicsr due to a changed dependent module name

If not, you'll see this error when running the application:

ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'

Do the following:

• Edit the file degradations.py, located for example in C:\Users\YOURUSERNAME\anaconda3\envs\EMA-VFI-WebUI\Lib\site-packages\basicsr\data

Change the line

from torchvision.transforms.functional_tensor import rgb_to_grayscale

to

from torchvision.transforms.functional import rgb_to_grayscale

(See: https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/13985)

NOTE: Real-ESRGAN will download the required 4x+ model on first use

Merge EMA-VFI and Real-ESRGAN components into WebUI Application

• Copy the following folders and files from: C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI to: C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI-WebUI

  • folders: benchmark, ckpt, model
  • files: config.py, dataset.py, Trainer.py

• Copy the following folder from: C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\Real-ESRGAN to: C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI-WebUI

  • folder: realesrgan

Start EMA-VFI WebUI Application

• Change to the application repo folder

(EMA-VFI-WebUI) C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\Real-ESRGAN>cd C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI-WebUI

• Start the application

(EMA-VFI-WebUI) C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI-WebUI>webui.bat

Testing an Interpolation

• Test files are located in C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI-WebUI\images
• On the Interplolate Frames/Frame Interpolation tab:
  • Drag image0.png from the images folder to the "before image" panel
  • Drag image2.png to the "after image" panel
• Click Interpolate
• After a short delay, the Animated Preview panel should show a 3-frame animated GIF

NOTE: Progress can be monitored in the Anaconda3 console window.

Running EMA-VFI WebUI the next time

• Open an Anaconda3 prompt window (via Windows start menu)

  • Anaconda3 -> Anaconda Prompt (anaconda3)

• activate the environment created before

(base) C:\Users\YOURUSERNAME\conda>conda activate EMA-VFI-WebUI

• Change to the application repo folder

(EMA-VFI-WebUI) C:\Users\YOURUSERNAME\conda>cd C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI-WebUI

• Start the application

(EMA-VFI-WebUI) C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI-WebUI>webui.bat

Speeding Up On Windows (Avoiding Windows Antimalware Service slow-down)

• Add the following to the Exclusions section in Windows Security Virus and Threat Protection Settings
  • Files ffmpeg.exe and ffprobe.exe
  • Folder C:\Users\YOURUSERNAME\conda\EMA-VFI-WebUI\EMA-VFI-WebUI
  • Folder used for original and modified content such as C:\Users\YOURUSERNAME\Documents
• Unblock FFmpeg
  • Right click on ffmpeg.exe and ffprobe.exe and check the box labeld "Unblock"