CapCheck AI Image Detection Vision Transformer (ViT) fine tuned for detecting AI generated images. Model Lineage & Attribution This model builds on the work of others: Layer Model Author License Base Architecture google/vit base patch16 224 in21k Google Apache 2.0 AI Detection Fine tune dima806/ai vs real image detection dima806 Apache 2.0 This Model capcheck/ai image detection CapCheck Apache 2.0 Special thanks to: Google for the Vision Transformer (ViT) architecture dima806 for fine tuning on the CIFAKE dataset for AI image detection Model Description Architecture : ViT Base (86M parameters) Input Size : 224x224 pixels Training Data : CIFAKE dataset (AI generated vs real images) Task : Binary classification (Real vs Fake/AI generated) Usage Labels Label Description Real Authentic photograph or real world image Fake AI generated or synthetically created image Performance This model was trained on the CIFAKE dataset. Performance on modern AI generators (Flux, Midjourney v6, DALL E 3, Stable Diffusion 3) may vary. See dima806's model card for detailed training metrics. Limitations Trained primarily on older AI generators (pre 2024) May have reduced accuracy on: Very new AI generator…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy