# SpectralCLIP: Preventing Artifacts in Text-Guided Style Transfer from a Spectral Perspective Source: [SpectralCLIP: Preventing Artifacts in Text-Guided Style Transfer from a Spectral Perspective]() Collection index: [llms.txt]() Data updated: 2025-10-28T13:57:02.147Z Authors: Zipeng Xu, Songlong Xing, Enver Sangineto, Nicu Sebe Published: 2023-03-16T12:53:07.000Z ## Abstract Owing to the power of vision-language foundation models, e.g., CLIP, the area of image synthesis has seen recent important advances. Particularly, for style transfer, CLIP enables transferring more general and abstract styles without collecting the style images in advance, as the style can be efficiently described with natural language, and the result is optimized by minimizing the CLIP similarity between the text description and the stylized image. However, directly using CLIP to guide style transfer leads to undesirable artifacts (mainly written words and unrelated visual entities) spread over the image. In this paper, we propose SpectralCLIP, which is based on a spectral representation of the CLIP embedding sequence, where most of the common artifacts occupy specific frequencies. By masking the band including these frequencies, we can condition the generation process to adhere to the target style properties (e.g., color, texture, paint stroke, etc.) while excluding the generation of larger-scale structures corresponding to the artifacts. Experimental results show that SpectralCLIP prevents the generation of artifacts effectively in quantitative and qualitative terms, without impairing the stylisation quality. We also apply SpectralCLIP to text-conditioned image generation and show that it prevents written words in the generated images. Our code is available at https://github.com/zipengxuc/SpectralCLIP. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Text-Driven Image Sentiment Transfer on Emospace Set (test)](): Text-Driven Image Sentiment Transfer; Emospace Set (test); Acc-8: 11.52. - [Image Sentiment Transfer on EmoSpace Set](): Image Sentiment Transfer; EmoSpace Set; SSIM: 41.56. ## Original sources and implementation [Original paper]() [PDF]()