Personalized Image Filter: Mastering Your Photographic Style
This addresses the challenge for photographers and image editors in automating style transfer while preserving content, though it appears incremental as it builds on existing diffusion models and textual inversion techniques.
The paper tackles the problem of learning and transferring photographic style from reference images by proposing a Personalized Image Filter (PIF) that uses a pretrained text-to-image diffusion model and textual inversion to optimize prompts for photographic concepts, achieving outstanding performance in extracting and transferring various styles.
Photographic style, as a composition of certain photographic concepts, is the charm behind renowned photographers. But learning and transferring photographic style need a profound understanding of how the photo is edited from the unknown original appearance. Previous works either fail to learn meaningful photographic concepts from reference images, or cannot preserve the content of the content image. To tackle these issues, we proposed a Personalized Image Filter (PIF). Based on a pretrained text-to-image diffusion model, the generative prior enables PIF to learn the average appearance of photographic concepts, as well as how to adjust them according to text prompts. PIF then learns the photographic style of reference images with the textual inversion technique, by optimizing the prompts for the photographic concepts. PIF shows outstanding performance in extracting and transferring various kinds of photographic style. Project page: https://pif.pages.dev/