Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

StyleShot: A Snapshot on Any Style

About

In this paper, we show that, a good style representation is crucial and sufficient for generalized style transfer without test-time tuning. We achieve this through constructing a style-aware encoder and a well-organized style dataset called StyleGallery. With dedicated design for style learning, this style-aware encoder is trained to extract expressive style representation with decoupling training strategy, and StyleGallery enables the generalization ability. We further employ a content-fusion encoder to enhance image-driven style transfer. We highlight that, our approach, named StyleShot, is simple yet effective in mimicking various desired styles, i.e., 3D, flat, abstract or even fine-grained styles, without test-time tuning. Rigorous experiments validate that, StyleShot achieves superior performance across a wide range of styles compared to existing state-of-the-art methods. The project page is available at: https://styleshot.github.io/.

Junyao Gao, Yanchen Liu, Yanan Sun, Yinhao Tang, Yanhong Zeng, Kai Chen, Cairong Zhao• 2024

Related benchmarks

TaskDatasetResultRank
Image Style TransferUser Study
Overall Quality Score76.6
30
Style TransferCIFAR-100 and InstaStyle (test)
Content Score26.9
9
Style TransferStyle-Content Pairs 50 style x 40 content references (test)
CSD Score0.45
8
Text-driven Style TransferBenchmark of 52 prompts and 20 style images 1.0 (test)
Text Alignment0.202
8
Image-driven Style TransferImage-driven style transfer (evaluation set)
CLIP Alignment Score0.66
7
Style TransferSingle image on A100 GPU (test)
Inference Time (s)5
7
Text-driven Style TransferUser preference study set (test)
Human Preference (Text)44.3
6
Showing 7 of 7 rows

Other info

Code

Follow for update