8000
Skip to content

Latest commit

 

History

20 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 

Repository files navigation

RemObj-Fuse

🎬 Automatic Object Remover for DaVinci Resolve Fusion

Free and open-source plugin that integrates the power of LaMa (Resolution-robust Large Mask Inpainting) into Fusion workflows for seamless object removal.

image

✨ Features

  • 🔍 AI-powered object removal and inpainting using the LaMa model
  • 🎞️ Designed for DaVinci Resolve Fusion workflows
  • 🛠️ Lightweight, script-based implementation (Python + Fuse)
  • 🧩 Easy to integrate, works with both Free and Studio version
  • 🆓 100% Free and Open Source

⬇️ Download

Download Source Code


Don't forget to leave a

⚙️ How to Install

  1. First install the python3 from www.python.org.
  2. Download the RemObj Plugin Files.
  3. Paste the RemObj folder in the fuse plugin directory of Resolve. Know How
  4. Follow the RemObj setup, either using remobj_manager.py or install manually.
  5. Open the Fusion page in DaVinci Resolve
  6. Search for the RemObj plugin in the node menu (Shift+Spacebar)
  7. Connect the main footage to the main input (Yellow) and the mask to the secondary input (Green)
  8. Let the plugin do its work
  9. The output will be displayed through the media out (if connected)

⮞ Automatic Setup for beginners [RemObj_Manager]

An easy-to-use Python application has been developed to simplify the RemObj setup. Just open the remobj_manager.py file, either directly in Python or via the Fuse interface and follow the installation steps.

Or Setup Manually


If you encounter any error or prefer to manually install the required libraries, follow the steps below:

  • Install the required packages using pip/pip3 command
pip install onnxruntime opencv-python numpy pillow


For CUDA support, use:

pip install onnxruntime-gpu opencv-python numpy pillow
  • Make sure the LaMa model file lama_sim_fp32.onnx is placed inside the RemObj folder.
    For fixing issues, check this page: wiki

📦 Available Models

Model Name Description Estimated Size
lama_sim_fp32.onnx Standard and simplified LaMa (Large Mask Inpainting) model for object removal 201 MB

Model downloaded from Carve/LaMa-ONNX, simplified using onnxsim for speed-up.

🪄 Video Demo

🌱 Overview

Fuse Version 0.1
Script Version 0.1
Setup Version 1.0
DaVinci Resolve Requirement Free or Studio : 18+
License MIT
Copyright 2026
Author Akash Bora

🐞 Debugging

To view plugin logs and troubleshoot issues, open the console through Fusion page ⮞ Workspace ⮞ Console. Make sure not to check the Disable Logging option in the fuse.
📙 Here is full troubleshooting guide you can follow: wiki

🚧 Planned Improvements

  • Streamline Python Script Execution on Windows. Eliminate the disruptive console popup by implementing a cleaner method to trigger the processing script. Maybe consider using comp:DoAction() or comp:Execute() for a more integrated Fusion workflow.

  • Optimize Model Reloading and improve overall performance during repeated operations.

  • Refactor Image I/O Handling, replace the use of the Clip() method with direct image data passing. Maybe consider the GetPixel() method.

Whether you're fixing bugs, suggesting enhancements, or adding new features—your input is valued. Feel free to fork, improve, and submit pull requests to help evolve this tool.

Get more Resolve plugins at www.akascape.com 👈

Thank You

About

A free and open-source AI plugin for automatic object removal in DaVinci Resolve Fusion using LaMa ONNX model

Topics

Resources

Stars

19 stars

Watchers

0 watching

Forks

Releases

Sponsor this project

Contributors

Languages

0