# Language-Driven Image Style Transfer

Source: [Language-Driven Image Style Transfer](<https://www.sota2.com/research/paper/68fa6cfb1e209131cea371a4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T00:23:36.215Z

Authors: Tsu-Jui Fu, Xin Eric Wang, William Yang Wang

Published: 2021-06-01T01:58:50.000Z

## Abstract

Despite having promising results, style transfer, which requires preparing style images in advance, may result in lack of creativity and accessibility. Following human instruction, on the other hand, is the most natural way to perform artistic style transfer that can significantly improve controllability for visual effect applications. We introduce a new task, language-driven artistic style transfer (LDAST), to manipulate the style of a content image, guided by a text. We propose contrastive language visual artist (CLVA) that learns to extract visual semantics from style instructions and accomplish LDAST by the patch-wise style discriminator. The discriminator considers the correlation between language and patches of style images or transferred results to jointly embed style instructions. CLVA further compares contrastive pairs of content images and style instructions to improve the mutual relativeness. The results from the same content image can preserve consistent content structures. Besides, they should present analogous style patterns from style instructions that contain similar visual semantics. The experiments show that our CLVA is effective and achieves superb transferred results on LDAST.

## 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)](<https://www.sota2.com/research/sota/text-driven-image-sentiment-transfer-on-emospace-set-test.md>): Text-Driven Image Sentiment Transfer; Emospace Set (test); Acc-8: 14.23.

- [Image Sentiment Transfer on EmoSpace Set](<https://www.sota2.com/research/sota/image-sentiment-transfer-on-emospace-set.md>): Image Sentiment Transfer; EmoSpace Set; SSIM: 46.5.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2106.00178>)

[PDF](<https://arxiv.org/pdf/2106.00178.pdf>)