ShantanuNair / FFMPerative

Chat to Process Video

FFMPerative

Video Production at the Speed of Chat

FFMPerative is your copilot for video editing workflows. Powered by Large Language Models (LLMs) through an intuitive chat interface, now you can compose video edits in natural language. Integrate FFmpeg and cutting-edge machine learning tools without dealing with complex command-line arguments or scripts.

• Get Video Metadata
• Sample Image from Video
• Change Video Playback Speed
• Apply FFmpeg xfade transition filters
• Resize, Crop, Flip, Reverse Video/GIF
• Make a Video from a Directory of Images
• Overlay Image & Video for Picture-in-Picture
• Adjust Audio Levels, Background Noise Removal
• Speech-to-Text Transcription and Closed-Captions
• Split Video by N-second Gops or with Scene Detection
• Image Classifier Inference on every N-th Video Frame

Just describe your desired edits similar to these examples.

Setup

Ubuntu (Recommended)

Install the package via aptitude:

# add our PPA
sudo add-apt-repository ppa:remyxai/ppa
sudo apt update

# install
sudo apt-get install ffmperative

Configure with your huggingface token and your preferred video directory

ffmperative configure

For Windows & Mac, see Docker Setup.

Quickstart

To sample an image from a video clip, simply run FFMPerative from the command-line:

ffmperative "sample the 5th frame from /path/to/video.mp4"

Similarly, it's simple to split a long video into short clips via scene detection:

ffmperative "split the video '/path/to/my_video.mp4' by scene"

Or to add closed-captions with:

ffmperative "merge subtitles 'captions.srt' with video 'video.mp4' calling it 'video_caps.mp4'"

FFMPerative excels in task compositition. For instance, curate video highlights by analyzing speech transcripts:

Features

Python Usage

With ffmpeg installed on your system, you can opt for the minimal installation of FFMPerative through pip.

Setup

Make the minimal install of ffmperative with:

# from PyPI
pip install ffmperative

Usage

Simply import the library and pass your command as a string to ffmp.

from ffmperative import ffmp

ffmp("sample the 5th frame from '/path/to/video.mp4'")

You can also use the command-line interface:

ffmp do --p "sample the 5th frame from '/path/to/video.mp4'"

Notebooks

Explore our notebooks for practical applications of FFMPerative:

• Automatically Edit Videos from Google Drive in Colab

Resources

• Huggingface Transformers Agents
• ffmpeg-python

Community

• B-Roll
• @brollai