PARASOL: Parametric Style Control for Diffusion Image Synthesis
This work addresses the need for more precise style control in image generation for users in creative and search applications, though it appears incremental as it builds on existing latent diffusion models.
The authors tackled the problem of enabling fine-grained, disentangled control over visual style in diffusion image synthesis by proposing PARASOL, a multi-modal model that jointly conditions on content and style embeddings, resulting in a method for nuanced style manipulation and generative search.
We propose PARASOL, a multi-modal synthesis model that enables disentangled, parametric control of the visual style of the image by jointly conditioning synthesis on both content and a fine-grained visual style embedding. We train a latent diffusion model (LDM) using specific losses for each modality and adapt the classifier-free guidance for encouraging disentangled control over independent content and style modalities at inference time. We leverage auxiliary semantic and style-based search to create training triplets for supervision of the LDM, ensuring complementarity of content and style cues. PARASOL shows promise for enabling nuanced control over visual style in diffusion models for image creation and stylization, as well as generative search where text-based search results may be adapted to more closely match user intent by interpolating both content and style descriptors.