"Reality is your best armor."
Deepfake Detection is a blazing-fast Chrome Extension + Telegram Bot that detects AI-generated fake images and videos in real-time.
โ
No installations
โ
No complex setup
โ
Download โ Load into Chrome or start the bot โ Detect Deepfakes Instantly
| ๐ | Chrome Extension |
|---|---|
| ๐ฅ | Download Here (MediaFire) |
| ๐ | Visit Our Website |
|---|---|
| ๐ | v0dev - Official Site |
- Download the
.crxor.zipfile from the link above - Open Chrome โ Go to
chrome://extensions/ - Turn ON Developer Mode (top-right)
- Click Load unpacked โ Select the extracted folder
- ๐ฏ Done! Start detecting deepfakes in real time
๐ More instructions + demo videos on v0dev.site
Powered by FastAPI + Uvicorn
This is the REST API backend that powers the Chrome extension.
pip install -r requirements.txt
# Then run the server:
uvicorn main:app --host 0.0.0.0 --port 8000- Accepts image or video uploads from the extension
- Processes files using trained deepfake models
- Returns detection results in real-time
โ ๏ธ Make sure model files are present and properly loaded withinmain.py.
"Because deepfakes don't announce themselves."
Includes:
deepfake_bot.pyโ Telegram bot logicrequirements.txtโ Python dependenciesmodels.txtโ Direct download links for pretrained models.envโ Required for API keys (not included)
cd backend
python -m venv .venv
# Activate:
# Windows
.venv\Scripts\activate
# macOS/Linux
source .venv/bin/activatepip install -r requirements.txtInside backend/, create a .env file:
TELEGRAM_TOKEN=your_telegram_bot_token
GOOGLE_VISION_API_KEY=your_google_vision_api_key
SERP_API_KEY=your_serp_api_keyModel download links are listed in models.txt.
Download and place them in backend/.
python deepfake_bot.pyStart chatting with the bot on Telegram:
Send /start, then upload an image โ Get instant deepfake results!
- ๐ง AI-Powered Deepfake Detection
- ๐ผ๏ธ Image & Video File Scanning
- โก Instant Results (Few Seconds)
- ๐ 100% Local Processing (Privacy First)
- ๐ Works on WhatsApp Web, Instagram, Telegram, Facebook
| Layer | Tools Used |
|---|---|
| Frontend | React.js, Tailwind CSS |
| Extension | JavaScript + API (FastAPI) |
| Backend | Flask, TensorFlow, FastAPI, Uvicorn |
| Models | XceptionNet, MesoNet, ViT, MViTv2 |
| Metric | Value |
|---|---|
| ๐ฏ Accuracy | >90% |
| โก Detection Speed | <5s (Images) |
| ๐ฅ Video Support | Short Clips |
| ๐ Privacy | 100% Local |
- ๐ฑ Mobile App Version
- ๐๏ธ Audio Deepfake Detection
- ๐จ Enhanced Threat Alerts & Reports
Licensed under the MIT License.
You are free to fork, remix, and contribute.
Developed by People Who Canโt Trust Their Own Eyes ๐ | Stay Real ๐