About the project
Detects AI-generated faces (GAN, diffusion) with a MobileNetV2 transfer-learning classifier in PyTorch, about 95% accuracy on the 140k real-vs-fake faces dataset. Includes a FastAPI REST API, drag-and-drop web UI and a Colab/Kaggle training script; the model is published on Kaggle.
Technologies
Topics
More in this category
Data & ML
XRLabLLM
A single-page Turkish presentation on using and integrating large language models.