SCAdapter: Content-Style Disentanglement for Diffusion Style Transfer
By: Luan Thanh Trinh, Kenji Doi, Atsuki Osanai
Potential Business Impact:
Makes pictures look like famous paintings.
Diffusion models have emerged as the leading approach for style transfer, yet they struggle with photo-realistic transfers, often producing painting-like results or missing detailed stylistic elements. Current methods inadequately address unwanted influence from original content styles and style reference content features. We introduce SCAdapter, a novel technique leveraging CLIP image space to effectively separate and integrate content and style features. Our key innovation systematically extracts pure content from content images and style elements from style references, ensuring authentic transfers. This approach is enhanced through three components: Controllable Style Adaptive Instance Normalization (CSAdaIN) for precise multi-style blending, KVS Injection for targeted style integration, and a style transfer consistency objective maintaining process coherence. Comprehensive experiments demonstrate SCAdapter significantly outperforms state-of-the-art methods in both conventional and diffusion-based baselines. By eliminating DDIM inversion and inference-stage optimization, our method achieves at least $2\times$ faster inference than other diffusion-based approaches, making it both more effective and efficient for practical applications.
Similar Papers
SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models
CV and Pattern Recognition
Lets computers change picture styles without losing meaning.
Leveraging Diffusion Models for Stylization using Multiple Style Images
CV and Pattern Recognition
Changes pictures to look like any art style.
Inversion-Free Style Transfer with Dual Rectified Flows
CV and Pattern Recognition
Makes pictures look like art, super fast.