PARASOL: Parametric Style Control for Diffusion Image Synthesis

arXiv:2303.06464v3 Announce Type: replace
Abstract: 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 …

abstract adapt arxiv control cs.cv diffusion diffusion model embedding fine-grained image ldm losses modal multi-modal parametric style synthesis train type visual