Using Style Ambiguity Loss to Improve Aesthetics of Diffusion Models
Teaching text-to-image models to be creative involves using style ambiguity loss. In this work, we explore using the style ambiguity training objective, used to approximate creativity, on a diffusion model. We then experiment with forms of style ambiguity loss that do not require training a classifier or a labeled dataset, and find that the models trained with style ambiguity loss can generate better images than the baseline diffusion models and GANs. Code is available at https://github.com/jamesBaker361/clipcreate.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Diffusion-based Facial Aesthetics Enhancement with 3D Structure Guidance
Facial Aesthetics Enhancement (FAE) aims to improve facial attractiveness by adjusting the structure and appearance of a facial image while preserving its identity as much as possible. Most existing methods adopted deep …
Face ModelHierarchical Anti-Aesthetics: Protecting Facial Privacy against Customized Diffusion Models
The rise of customized diffusion models has fueled a boom in personalized visual content creation, but it also introduces serious risks of malicious misuse, thereby posing threats to personal privacy. Image aesthetics ar…
LensStyle: Learning the Optical Aesthetics for Controllable Stylized Lens Effect Rendering
The visual aesthetics of photographs are deeply influenced by lens characteristics such as aperture shape, optical vignetting and optical diffraction, which together define a camera's unique optical style. Existing lens …
Image EditingDeep Multi-Patch Aggregation Network for Image Style, Aesthetics, and Quality Estimation
This paper investigates problems of image style, aesthetics, and quality estimation, which require fine-grained details from high-resolution images, utilizing deep neural network training approach. Existing deep convolut…
Aesthetics Quality AssessmentImage Quality EstimationTraining-Free Multi-Style Fusion Through Reference-Based Adaptive Modulation
We propose Adaptive Multi-Style Fusion (AMSF), a reference-based training-free framework that enables controllable fusion of multiple reference styles in diffusion models. Most of the existing reference-based methods are…