Table 1

Accuracy of the diffusion generative AI model proposed in [11]; the quantity is the Truth Negative rate for the ALASKA2 dataset [10, 9] of genuine photographs and true positive rates for all other generative-AI image datasets.

SourceAccuracy
ALASKA2 real photographs97.80%
Stable Diffusion XL Turbo85.01%
— with Consistency Decoder VAE7.79%
Stable Diffusion v396.07%
— with 2 diffusion steps16.93%
Wuerstchen85.01%
— with DDIM noise scheduler96.20%
Kandinsky v2.293.85%
— with 64 diffusion steps7.79%
FLUX.1 Schnell53.81%
— with Finetuning #163.78%
— with Finetuning #247.76%

or Create an Account

Close Modal
Close Modal