通过动态风格提示库，实现多样且真实的艺术风格迁移
DyArtbank: Diverse Artistic Style Transfer via Pre-trained Stable Diffusion and Dynamic Style Prompt Artbank
- 引入可学习的动态风格提示库，存储并动态调用艺术风格
- 生成多样且逼真的风格化图像，支持随机样本生成
- 适合需要丰富风格化数据的应用场景，如艺术创作与数据增强
艺术风格迁移旨在将学习到的风格应用到任意内容图像上。然而，现有方法通常只能生成一致的风格化图像，难以满足用户对多样化风格的需求。为此，我们提出一种新型艺术风格迁移框架DyArtbank，可生成多样且高度逼真的风格化图像。具体而言，我们引入动态风格提示库（DSPA），一组可学习参数，能从艺术作品集合中学习并存储风格信息，动态引导预训练稳定扩散模型生成多样且真实的风格化图像。DSPA还可基于已学风格信息生成随机艺术图像样本，为数据增强提供新思路。此外，提出关键内容特征提示模块（KCFP），向预训练稳定扩散提供充分的内容提示，以保留输入图像的细节结构。大量定性和定量实验验证了所提方法的有效性。代码已开源：https://github.com/Jamie-Cheung/DyArtbank
原文摘要 · Abstract (English)
Artistic style transfer aims to transfer the learned style onto an arbitrary content image. However, most existing style transfer methods can only render consistent artistic stylized images, making it difficult for users to get enough stylized images to enjoy. To solve this issue, we propose a novel artistic style transfer framework called DyArtbank, which can generate diverse and highly realistic artistic stylized images. Specifically, we introduce a Dynamic Style Prompt ArtBank (DSPA), a set of learnable parameters. It can learn and store the style information from the collection of artworks, dynamically guiding pre-trained stable diffusion to generate diverse and highly realistic artistic stylized images. DSPA can also generate random artistic image samples with the learned style information, providing a new idea for data augmentation. Besides, a Key Content Feature Prompt (KCFP) module is proposed to provide sufficient content prompts for pre-trained stable diffusion to preserve the detailed structure of the input content image. Extensive qualitative and quantitative experiments verify the effectiveness of our proposed method. Code is available: https://github.com/Jamie-Cheung/DyArtbank
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。