AI Model Artifacts & Deepfake Detector Directory
Technical breakdowns of the newest generative face-swapping, voice-cloning, and video-diffusion engines, with frame-by-frame artifact recognition.
Deep Live Cam Detector: Spotting Real-Time Webcam Face Swaps
Deep Live Cam went viral in 2024–2025 as an open-source tool enabling anyone to swap their face in real-time onto a live webcam stream using a single reference photo. It is heavily utilized by romance scammers, catfishes, and remote interview impostors on Zoom, Teams, and Omegle. Sealed Rose detects the distinct temporal jitter, edge blending blur, and lighting inconsistencies generated by Deep Live Cam’s ONNX model pipeline.
LivePortrait AI Detector: Spotting Video & Audio Driven Face Animation
LivePortrait (developed by Kuaishou) generates lifelike animated talking videos from a single still portrait by transferring head movements, blinks, and emotional expressions from a driver video. It is widely used by catfish syndicates to turn stolen photos into "video proof" of their identity.
Roop Unleashed Deepfake Detector: Offline Video Face Swap Analysis
Roop Unleashed is a widely used desktop software application that automates face-swapping across full video clips without requiring dataset training. Attackers use it to generate non-consensual deepfakes and fabricate fake celebrity adult content.
F5-TTS Voice Clone Detector: Zero-Shot Audio Deepfake Analysis
F5-TTS is a state-of-the-art open-source text-to-speech model based on flow matching. With just 3 to 5 seconds of audio from a podcast, voicemail, or Instagram story, F5-TTS clones an individual’s voice with unprecedented fidelity, fueling grandparents-in-jail phone scams and CEO fraud.
Chatterbox AI & Agency Chat Bot Detector: Spotting OnlyFans Chatters
OnlyFans agencies hire hundreds of remote chatters in the Philippines, Colombia, and Eastern Europe who use automated CRM tools and LLMs (Chatterbox AI, Infloww) to impersonate top models. They follow strict sales scripts designed to milk tips and PPV purchases from unsuspecting fans.
Mochi 1 Video AI Detector: Genmo Open Video Model Forensics
Mochi 1 is an open-source video generation model from Genmo with 10 billion parameters. It produces high-motion video from text prompts, but exhibits distinctive fluid dynamics inconsistencies and unnatural physical inertia.
CogVideoX-5B Video Detector: Zhipu AI Generation Forensics
CogVideoX-5B (developed by Zhipu AI) uses an expert 3D VAE to compress spatial and temporal dimensions. Sealed Rose inspects 3D VAE reconstruction bounds to identify synthetic video generated by this architecture.
FaceFusion Deepfake Detector: Next-Gen Video Face Swapping Forensics
FaceFusion is the premier open-source face-swapping and face-enhancement framework. It combines high-resolution face swapping (Ghost, Inswapper) with neural restoration (CodeFormer, GFPGAN) and frame color matching. Despite its photorealism, Sealed Rose detects the boundary masks and restoration artifacts left by FaceFusion.