README.md

metadata

title: KAMY Vision AI
emoji: 🛡️
colorFrom: purple
colorTo: blue
sdk: docker
app_port: 8000
pinned: false

KAMY Vision AI

Multimodal forensic platform for deepfake detection. Analyzes images, audio, video, and text via a layered pipeline combining Vision Transformer ensembles with deterministic forensic signals.

Production: app.kamydev.com · API at oyabun-dev-kamyvision.hf.space · Docs at docs.kamydev.com

---

Stack

• Backend: Python 3.10+, FastAPI, uvicorn, PyTorch, HuggingFace Transformers
• Frontend: React 18, TypeScript, Vite — deployed on Vercel
• API hosting: HuggingFace Spaces (Docker)
• Docs: React + custom CSS — deployed on Vercel

---

Models

Image ensemble (3 ViT models, weighted average)

Model	Weight	Task
Ateeqq/ai-vs-human-image-detector	45%	AI-generated vs human photo
prithivMLmods/AI-vs-Deepfake-vs-Real	35%	3 classes: AI / Deepfake / Real
prithivMLmods/Deep-Fake-Detector-Model	20%	Facial deepfakes

Forensic layers (no ML)

• EXIF — 19 AI generator signatures detected (Gemini, DALL-E, Firefly, Midjourney, Flux, SynthID, Canva AI, Stable Diffusion...)
• FFT — frequency spectrum analysis, GAN oversmoothing and periodic peak detection
• Texture — local variance per 16×16 patch, unnatural uniformity in skin/background
• Color — colorimetric entropy and HSV distribution, artificial saturation patterns

Fusion profiles

The engine selects a profile based on EXIF results, then adjusts weights:

Profile	Trigger	EXIF weight
EXIF_IA_DETECTE	AI source found in metadata	60%
EXIF_FIABLE	Real camera identified	32%
EXIF_ABSENT	No metadata (stripped by social network)	0%, FFT+texture boosted
STANDARD	General case	20%

Audio (pending)

MelodyMachine/Deepfake-audio-detection-V2 (wav2vec2) — pending ONNX conversion.

---

API endpoints

Base URL (local): http://localhost:8000 Base URL (production): https://oyabun-dev-kamyvision.hf.space

Method	Endpoint	Status	Description
GET	/health	Stable	API and model status
POST	/analyze/image	Stable	Full image analysis (3 ViT + 4 forensic layers)
POST	/analyze/image/fast	Stable	Fast image analysis (2 ViT + EXIF only)
POST	/analyze/audio	WIP	Synthetic voice detection
POST	/analyze/video	WIP	Frame-by-frame video analysis
POST	/analyze/text	WIP	AI-generated text detection

# Health check
curl http://localhost:8000/health

# Full image analysis
curl -X POST http://localhost:8000/analyze/image \
  -F "file=@photo.jpg"

# Fast image analysis
curl -X POST http://localhost:8000/analyze/image/fast \
  -F "file=@photo.jpg"

Response structure

{
  "status": "success",
  "verdict": "DEEPFAKE",
  "fake_prob": 0.8731,
  "real_prob": 0.1269,
  "confidence": "high",
  "reason": "AI source detected in EXIF metadata (Google Gemini).",
  "fusion_profile": "EXIF_IA_DETECTE",
  "ai_source": "Google Gemini",
  "layer_scores": {
    "ensemble": 0.82,
    "exif": 0.97,
    "fft": 0.61,
    "texture": 0.55,
    "color": 0.70
  },
  "weights_used": {
    "ensemble": 0.20,
    "exif": 0.60,
    "fft": 0.08,
    "texture": 0.07,
    "color": 0.05
  },
  "models": [
    "Ateeqq/ai-vs-human-image-detector",
    "prithivMLmods/AI-vs-Deepfake-vs-Real",
    "prithivMLmods/Deep-Fake-Detector-Model"
  ]
}

---

Getting started

Prerequisites

Tool	Version
Python	3.10+
Node.js	18+
Docker	24+ (optional)

Backend

git clone https://github.com/oyabun-dev/deepfake_detection
cd deepfake_detection

python -m venv .venv
source .venv/bin/activate

pip install -r requirements.txt
uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

Models (~2–4 GB) are downloaded and cached automatically on first startup.

Frontend

cd frontend-react
npm install
npm run dev

Docker (recommended)

docker compose up --build

• API: http://localhost:8000
• Frontend: http://localhost:3000

---

Project structure

deepfake_detection/
├── app/
│   ├── main.py              — FastAPI application, CORS, routers
│   ├── core/
│   │   ├── config.py        — Constants (formats, thresholds, max size)
│   │   └── device.py        — Automatic CPU/GPU selection
│   ├── routers/
│   │   ├── image.py         — /analyze/image and /analyze/image/fast
│   │   ├── audio.py         — /analyze/audio (WIP)
│   │   ├── video.py         — /analyze/video (WIP)
│   │   └── text.py          — /analyze/text (WIP)
│   └── pipelines/
│       └── image.py         — Full pipeline: run() and run_fast()
├── frontend-react/          — React + Vite frontend
├── docs/                    — React documentation site
├── docker-compose.yml
├── docker-compose.prod.yml
├── Dockerfile
└── requirements.txt

---

Deployment

HuggingFace Spaces (API)

pip install huggingface_hub
huggingface-cli login
git remote add spaces https://huggingface.co/spaces/oyabun-dev/kamyvision
git push spaces main

Vercel (frontend + docs)

Both the React frontend (frontend-react/) and the documentation (docs/) are deployed on Vercel. See the Deployment docs for full configuration.

---

Known limitations

The 3 ViT models were primarily trained on GAN datasets. Performance is degraded on recent diffusion model outputs (Midjourney v6, Stable Diffusion XL, Flux.1). EXIF analysis partially compensates for images that retain their metadata.

---

License

MIT