Towards Highly Realistic Artistic Style Transfer via Stable Diffusion with Step-aware and Layer-aware Prompt

arXiv:2404.11474v1 Announce Type: new
Abstract: Artistic style transfer aims to transfer the learned artistic style onto an arbitrary content image, generating artistic stylized images. Existing generative adversarial network-based methods fail to generate highly realistic stylized images and always introduce obvious artifacts and disharmonious patterns. Recently, large-scale pre-trained diffusion models opened up a new way for generating highly realistic artistic stylized images. However, diffusion model-based methods generally fail to preserve the content structure of input content images well, introducing some undesired …

abstract adversarial arxiv cs.cv diffusion generate generative generative adversarial network image images layer network patterns prompt scale stable diffusion style style transfer transfer type via