中文
相关论文

相关论文: PEO: Training-Free Aesthetic Quality Enhancement i…

200 篇论文

The notable gap between user-provided and model-preferred prompts poses a significant challenge for generating high-quality images with text-to-image models, compelling the need for prompt engineering. Current studies on prompt engineering…

计算机视觉与模式识别 · 计算机科学 2026-03-09 Shiyu Wu , Mingzhen Sun , Weining Wang , Yequan Wang , Jing Liu

Recent advances in diffusion-based text-to-image (T2I) models have led to remarkable success in generating high-quality images from textual prompts. However, ensuring accurate alignment between the text and the generated image remains a…

计算机视觉与模式识别 · 计算机科学 2025-10-01 Jia Jun Cheng Xian , Muchen Li , Haotian Yang , Xin Tao , Pengfei Wan , Leonid Sigal , Renjie Liao

Text-to-image diffusion models, such as Stable Diffusion, have demonstrated remarkable capabilities in generating high-quality and diverse images from natural language prompts. However, recent studies reveal that these models often…

机器学习 · 计算机科学 2025-10-27 Zihao Fu , Ryan Brown , Shun Shao , Kai Rawal , Eoin Delaney , Chris Russell

Text-to-image diffusion models often make implicit assumptions about the world when generating images. While some assumptions are useful (e.g., the sky is blue), they can also be outdated, incorrect, or reflective of social biases present…

计算机视觉与模式识别 · 计算机科学 2023-08-28 Hadas Orgad , Bahjat Kawar , Yonatan Belinkov

We present a simple but effective training-free approach for text-driven image-to-image translation based on a pretrained text-to-image diffusion model. Our goal is to generate an image that aligns with the target task while preserving the…

计算机视觉与模式识别 · 计算机科学 2024-12-23 Hyunsoo Lee , Minsoo Kang , Bohyung Han

Recent progress in generative models, especially in text-guided diffusion models, has enabled the production of aesthetically-pleasing imagery resembling the works of professional human artists. However, one has to carefully compose the…

人机交互 · 计算机科学 2023-06-05 Nikita Pavlichenko , Dmitry Ustalov

Finetuning-free personalized image generation can synthesize customized images without test-time finetuning, attracting wide research interest owing to its high efficiency. Current finetuning-free methods simply adopt a single training…

计算机视觉与模式识别 · 计算机科学 2025-06-30 Qihan Huang , Weilong Dai , Jinlong Liu , Wanggui He , Hao Jiang , Mingli Song , Jie Song

Text-to-image models have shown remarkable progress in generating high-quality images from user-provided prompts. Despite this, the quality of these images varies due to the models' sensitivity to human language nuances. With advancements…

人工智能 · 计算机科学 2024-06-14 Xinrui Yang , Zhuohan Wang , Anthony Hu

Text-to-image diffusion models exhibit strong generative performance but remain highly sensitive to prompt formulation, often requiring extensive manual trial and error to obtain satisfactory results. This motivates the development of…

人工智能 · 计算机科学 2026-04-14 Domício Pereira Neto , João Correia , Penousal Machado

The issue of generative pretraining for vision models has persisted as a long-standing conundrum. At present, the text-to-image (T2I) diffusion model demonstrates remarkable proficiency in generating high-definition images matching textual…

计算机视觉与模式识别 · 计算机科学 2023-12-25 Qiang Wan , Zilong Huang , Bingyi Kang , Jiashi Feng , Li Zhang

Diffusion models (DMs) have become the new trend of generative models and have demonstrated a powerful ability of conditional synthesis. Among those, text-to-image diffusion models pre-trained on large-scale image-text pairs are highly…

计算机视觉与模式识别 · 计算机科学 2023-03-06 Wenliang Zhao , Yongming Rao , Zuyan Liu , Benlin Liu , Jie Zhou , Jiwen Lu

Diffusion-based text-to-image personalization have achieved great success in generating subjects specified by users among various contexts. Even though, existing finetuning-based methods still suffer from model overfitting, which greatly…

计算机视觉与模式识别 · 计算机科学 2024-01-31 Henglei Lv , Jiayu Xiao , Liang Li , Qingming Huang

The alignment of large language models with human values presents a critical challenge, particularly when balancing conflicting objectives like helpfulness and harmlessness. Existing approaches, such as Reinforcement Learning from Human…

计算与语言 · 计算机科学 2025-03-04 Yuxuan Liu

Text-to-image generation has evolved beyond single monolithic models to complex multi-component pipelines. These combine fine-tuned generators, adapters, upscaling blocks and even editing steps, leading to significant improvements in image…

计算机视觉与模式识别 · 计算机科学 2025-11-04 Uri Gadot , Rinon Gal , Yftah Ziser , Gal Chechik , Shie Mannor

Reinforcement learning (RL)-based fine-tuning has emerged as a powerful approach for aligning diffusion models with black-box objectives. Proximal policy optimization (PPO) is a popular choice of method for policy optimization. While…

While text-driven diffusion models demonstrate remarkable performance in image editing, the critical components of their text embeddings remain underexplored. The ambiguity and entanglement of these embeddings pose challenges for precise…

计算机视觉与模式识别 · 计算机科学 2025-08-12 Yitong Yang , Yinglin Wang , Tian Zhang , Jing Wang , Shuting He

Pre-trained diffusion models have enabled significant advancements in All-in-One Restoration (AiOR), offering improved perceptual quality and generalization. However, diffusion-based restoration methods primarily rely on fine-tuning or…

计算机视觉与模式识别 · 计算机科学 2026-04-07 Sudarshan Rajagopalan , Vishal M. Patel

In a surge of text-to-image (T2I) models and their customization methods that generate new images of a user-provided subject, current works focus on alleviating the costs incurred by a lengthy per-subject optimization. These zero-shot…

计算机视觉与模式识别 · 计算机科学 2024-03-22 Yeji Song , Jimyeong Kim , Wonhark Park , Wonsik Shin , Wonjong Rhee , Nojun Kwak

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…

计算机视觉与模式识别 · 计算机科学 2024-04-02 Jeeyung Kim , Ze Wang , Qiang Qiu

Despite recent progress in text-to-image (T2I) generation, existing models often struggle to faithfully capture user intentions from short and under-specified prompts. While prior work has attempted to enhance prompts using large language…