Qualitative Failures of Image Generation Models and Their Application in Detecting Deepfakes

The ability of image and video generation models to create photorealistic images has reached unprecedentedheights, making it difficult to distinguish between real and fake images in many cases.However, despite this progress, a gap remains between the quality of generated images and thosefound in the real world. To address this, we have reviewed a vast body of literature from both academicpublications and social media to identify qualitative shortcomings in image generation models,which we have classified into five categories. By understanding these failures, we can identify areaswhere these models need improvement, as well as develop strategies for detecting deep fakes. Theprevalence of deep fakes in today’s society is a serious concern, and our findings can help mitigatetheir negative impact. In order to support research in this field, a collection of instances where modelshave failed is made available at here.