Gaojunyao/StyleShot

1---2tags:3- text-to-image4- style-transfer5- stable-diffusion6language:7- en8library_name: diffusers9license: mit10---11 12# StyleShot Model Card13 14 15<div align="center">16 17[**Project Page**](https://styleshot.github.io) **|** [**Paper (ArXiv)**](https://arxiv.org/abs/2407.01414) **|** [**Code**](https://github.com/open-mmlab/StyleShot)18</div>19 20---21 22 23## Introduction24 25we present StyleShot, a generalized plug-to-play style transfer method, capable of generating the high-quality stylized images that match the desired style from any reference image without test-time style-tuning. To the best of our knowledge, To the best of our knowledge, StyleShot is the first work to designate a style-aware encoder based on Stable Diffusion and a content-fusion encoder for better style and content integration, achieving the state-of-the-art text and image-driven style transfer performance compared to existing methods.26 27![arch](./framework.png)28 29## Models30 31### StyleShot for SD 1.532- [ip.bin](https://huggingface.co/Gaojunyao/StyleShot/blob/main/pretrained_weight/ip.bin): weights for ip-adapter and our content-retention encoder.33- [style_aware_encoder.bin](https://huggingface.co/Gaojunyao/StyleShot/blob/main/pretrained_weight/style_aware_encoder.bin): weights for style-aware encoder.34 35## Disclaimer36We develop this repository for RESEARCH purposes, so it can only be used for personal/research/non-commercial purposes.