paper-with-me

홈 › Papers

Model-Agnostic Human Preference Inversion in Diffusion Models

2024-04-01 · Jeeyung Kim, Ze Wang, Qiang Qiu

Efficient text-to-image generation remains a challenging task due to the high computational costs associated with the multi-step sampling in diffusion models. Although distillation of pre-trained diffusion models has been successful in reducing sampling steps, low-step image generation often falls short in terms of quality. In this study, we propose a novel sampling design to achieve high-quality one-step image generation aligning with human preferences, particularly focusing on exploring the impact of the prior noise distribution. Our approach, Prompt Adaptive Human Preference Inversion (PAHI), optimizes the noise distributions for each prompt based on human preferences without the need for fine-tuning diffusion models. Our experiments showcase that the tailored noise distributions significantly improve image quality with only a marginal increase in computational cost. Our findings underscore the importance of noise optimization and pave the way for efficient and high-quality text-to-image synthesis.

📄 PDF Abstract BibTeX arXiv:2404.00879

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationmodelText to Image GenerationText-to-Image Generation

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

Smoothed Preference Optimization via ReNoise Inversion for Aligning Diffusion Models with Varied Human Preferences

2025-06-03 · Yunhong Lu, Qichao Wang, Hengyuan Cao, Xiaoyin Xu 외

Direct Preference Optimization (DPO) aligns text-to-image (T2I) generation models with human preferences using pairwise preference data. Although substantial resources are expended in collecting and labeling datasets, a …

InPO: Inversion Preference Optimization with Reparametrized DDIM for Efficient Diffusion Model Alignment

2025-03-24 · CVPR 2025 1 · Yunhong Lu, Qichao Wang, Hengyuan Cao, Xierui Wang 외

Without using explicit reward, direct preference optimization (DPO) employs paired human preference data to fine-tune generative models, a method that has garnered considerable attention in large language models (LLMs). …

Latent Embedding Adaptation for Human Preference Alignment in Diffusion Planners

2025-03-24 · Wen Zheng Terence Ng, Jianda Chen, Yuan Xu, Tianwei Zhang

This work addresses the challenge of personalizing trajectories generated in automated decision-making systems by introducing a resource-efficient approach that enables rapid adaptation to individual users' preferences. …

Decision Making

Not All Noises Are Created Equally:Diffusion Noise Selection and Optimization

2024-07-19 · Zipeng Qi, Lichen Bai, Haoyi Xiong, Zeke Xie

Diffusion models that can generate high-quality data from randomly sampled Gaussian noises have become the mainstream generative method in both academia and industry. Are randomly sampled Gaussian noises equally good for…

All

Inversion-DPO: Precise and Efficient Post-Training for Diffusion Models

2025-07-14 · Zejian Li, Yize Li, Chenye Meng, Zhongni Liu 외 arxiv

Recent advancements in diffusion models (DMs) have been propelled by alignment methods that post-train models to better conform to human preferences. However, these approaches typically require computation-intensive trai…

Text-to-Image Generation