paper-with-me

홈 › Papers

Using Style Ambiguity Loss to Improve Aesthetics of Diffusion Models

2024-10-02 · James Baker

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.

📄 PDF Abstract BibTeX arXiv:2410.02055

Code (1)

jamesbaker361/clipcreate 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Diffusion-based Facial Aesthetics Enhancement with 3D Structure Guidance

2025-03-18 · Lisha Li, Jingwen Hou, Weide Liu, Yuming Fang 외

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 Model

Hierarchical Anti-Aesthetics: Protecting Facial Privacy against Customized Diffusion Models

2026-07-02 · Songping Wang, Yueming Lyu, Shiqi Liu, Chen Zhao 외 arxiv

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

2026-09-04 · Yachuan Huang, Liwen Xiao, Liao Shen, Qiwen Wang 외 arxiv

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 Editing

Deep Multi-Patch Aggregation Network for Image Style, Aesthetics, and Quality Estimation

2015-12-01 · ICCV 2015 12 · Xin Lu, Zhe Lin, Xiaohui Shen, Radomir Mech 외

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 Estimation

Training-Free Multi-Style Fusion Through Reference-Based Adaptive Modulation

2025-09-23 · Xu Liu, Yibo Lu, Xinxian Wang, Xinyu Wu arxiv

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…