Semantic Approach to Quantifying the Consistency of Diffusion Model Image Generation

arXiv:2404.08799v1 Announce Type: cross
Abstract: In this study, we identify the need for an interpretable, quantitative score of the repeatability, or consistency, of image generation in diffusion models. We propose a semantic approach, using a pairwise mean CLIP (Contrastive Language-Image Pretraining) score as our semantic consistency score. We applied this metric to compare two state-of-the-art open-source image generation diffusion models, Stable Diffusion XL and PixArt-{\alpha}, and we found statistically significant differences between the semantic consistency scores for the models. Agreement …

abstract arxiv clip cs.ai cs.cv cs.hc cs.lg diffusion diffusion model diffusion models identify image image generation language mean pretraining quantitative semantic study type