DIFF-NST: Diffusion Interleaving For deFormable Neural Style Transfer
This work introduces a novel method for artists and researchers in computer vision to achieve deformable style transfer, moving beyond traditional texture-based edits to allow more abstract and deformed artistic renditions.
The authors tackled the problem of enabling deformable style transfer, which allows style-based deformation of content images, by leveraging diffusion models like Stable Diffusion. They demonstrated that this approach provides new artistic controls at inference time, addressing a capability that was previously elusive in neural style transfer methods.
Neural Style Transfer (NST) is the field of study applying neural techniques to modify the artistic appearance of a content image to match the style of a reference style image. Traditionally, NST methods have focused on texture-based image edits, affecting mostly low level information and keeping most image structures the same. However, style-based deformation of the content is desirable for some styles, especially in cases where the style is abstract or the primary concept of the style is in its deformed rendition of some content. With the recent introduction of diffusion models, such as Stable Diffusion, we can access far more powerful image generation techniques, enabling new possibilities. In our work, we propose using this new class of models to perform style transfer while enabling deformable style transfer, an elusive capability in previous models. We show how leveraging the priors of these models can expose new artistic controls at inference time, and we document our findings in exploring this new direction for the field of style transfer.