将图像风格编码为20位Base64代码，实现高效可控的风格生成。
Stylecodes: Encoding Stylistic Information For Image Generation
- 提出基于深度编码器的风格压缩方法，将图像转为20字符的风格码
- 生成的风格码与原图质量损失极小，媲美传统图像到风格转换
- 开源编码架构和训练流程，支持用户自定义风格编码
扩散模型在图像生成中表现优异，但风格控制仍具挑战。现有方案依赖示例图像，操作繁琐。MidJourney提出的srefs（风格参考码）以短数字代码表达特定风格，便于社交分享，且无需上传源图。但用户无法自动生成此类代码，且训练过程不公开。本文提出StyleCodes：一个开源的风格编码架构与训练流程，可将图像风格表示为20字符的Base64代码。实验表明，该编码方式在质量上与传统图像到风格转换方法几乎无差别，同时具备高效、易共享的优势。
原文摘要 · Abstract (English)
Diffusion models excel in image generation, but controlling them remains a challenge. We focus on the problem of style-conditioned image generation. Although example images work, they are cumbersome: srefs (style-reference codes) from MidJourney solve this issue by expressing a specific image style in a short numeric code. These have seen widespread adoption throughout social media due to both their ease of sharing and the fact they allow using an image for style control, without having to post the source images themselves. However, users are not able to generate srefs from their own images, nor is the underlying training procedure public. We propose StyleCodes: an open-source and open-research style encoder architecture and training procedure to express image style as a 20-symbol base64 code. Our experiments show that our encoding results in minimal loss in quality compared to traditional image-to-style techniques.
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。