中文
相关论文

相关论文: IMAGE-ALCHEMY: Advancing subject fidelity in perso…

200 篇论文

We present SDXL, a latent diffusion model for text-to-image synthesis. Compared to previous versions of Stable Diffusion, SDXL leverages a three times larger UNet backbone: The increase of model parameters is mainly due to more attention…

计算机视觉与模式识别 · 计算机科学 2023-07-06 Dustin Podell , Zion English , Kyle Lacey , Andreas Blattmann , Tim Dockhorn , Jonas Müller , Joe Penna , Robin Rombach

As text-to-image (T2I) synthesis models increase in size, they demand higher inference costs due to the need for more expensive GPUs with larger memory, which makes it challenging to reproduce these models in addition to the restricted…

计算机视觉与模式识别 · 计算机科学 2024-11-26 Youngwan Lee , Kwanyong Park , Yoorhim Cho , Yong-Ju Lee , Sung Ju Hwang

Recent advancements in human preference optimization, initially developed for Language Models (LMs), have shown promise for text-to-image Diffusion Models, enhancing prompt alignment, visual appeal, and user preference. Unlike LMs,…

计算机视觉与模式识别 · 计算机科学 2025-12-03 Alexander Gambashidze , Anton Kulikov , Yuriy Sosnin , Ilya Makarov

Personalized text-to-image generation has gained significant attention for its capability to generate high-fidelity portraits of specific identities conditioned on user-defined prompts. Existing methods typically involve test-time…

计算机视觉与模式识别 · 计算机科学 2024-11-18 Yujia Wu , Yiming Shi , Jiwei Wei , Chengwei Sun , Yang Yang , Heng Tao Shen

Diffusion-based models have achieved state-of-the-art performance on text-to-image synthesis tasks. However, one critical limitation of these models is the low fidelity of generated images with respect to the text description, such as…

计算机视觉与模式识别 · 计算机科学 2023-04-11 Qiucheng Wu , Yujian Liu , Handong Zhao , Trung Bui , Zhe Lin , Yang Zhang , Shiyu Chang

In this study, we propose an enhanced image restoration model, SUPIR, based on the integration of two low-rank adaptive (LoRA) modules with the Stable Diffusion XL (SDXL) framework. Our method leverages the advantages of LoRA to fine-tune…

计算机视觉与模式识别 · 计算机科学 2024-09-02 Haiyang Zhao

Recent works demonstrate a remarkable ability to customize text-to-image diffusion models while only providing a few example images. What happens if you try to customize such models using multiple, fine-grained concepts in a sequential…

计算机视觉与模式识别 · 计算机科学 2024-05-03 James Seale Smith , Yen-Chang Hsu , Lingyu Zhang , Ting Hua , Zsolt Kira , Yilin Shen , Hongxia Jin

Stable Diffusion XL (SDXL) has become the best open source text-to-image model (T2I) for its versatility and top-notch image quality. Efficiently addressing the computational demands of SDXL models is crucial for wider reach and…

计算机视觉与模式识别 · 计算机科学 2024-01-08 Yatharth Gupta , Vishnu V. Jaddipal , Harish Prabhala , Sayak Paul , Patrick Von Platen

Novel diffusion models can synthesize photo-realistic images with integrated high-quality text. Surprisingly, we demonstrate through attention activation patching that only less than $1$% of diffusion models' parameters, all contained in…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Łukasz Staniszewski , Bartosz Cywiński , Franziska Boenisch , Kamil Deja , Adam Dziedzic

Diffusion models have demonstrated great success in the field of text-to-image generation. However, alleviating the misalignment between the text prompts and images is still challenging. The root reason behind the misalignment has not been…

计算机视觉与模式识别 · 计算机科学 2024-11-28 Dongzhi Jiang , Guanglu Song , Xiaoshi Wu , Renrui Zhang , Dazhong Shen , Zhuofan Zong , Yu Liu , Hongsheng Li

Recent progress in personalized image generation using diffusion models has been significant. However, development in the area of open-domain and non-fine-tuning personalized image generation is proceeding rather slowly. In this paper, we…

计算机视觉与模式识别 · 计算机科学 2024-05-21 Jian Ma , Junhao Liang , Chen Chen , Haonan Lu

Diffusion models have achieved strong results in text-to-image generation, but important limitations remain as prompts become more structured and multi-object. On the architecture side, U-Net backbones are efficient and stable, yet their…

计算机视觉与模式识别 · 计算机科学 2026-05-19 Yu Chang , Jiahao Chen , Anzhe Cheng , Paul Bogdan

We present a framework for high-fidelity product image recontextualization using text-to-image diffusion models and a novel data augmentation pipeline. This pipeline leverages image-to-video diffusion, in/outpainting & negatives to create…

计算机视觉与模式识别 · 计算机科学 2025-03-13 Ishaan Malhi , Praneet Dutta , Ellie Talius , Sally Ma , Brendan Driscoll , Krista Holden , Garima Pruthi , Arunachalam Narayanaswamy

We propose a diffusion distillation method that achieves new state-of-the-art in one-step/few-step 1024px text-to-image generation based on SDXL. Our method combines progressive and adversarial distillation to achieve a balance between…

计算机视觉与模式识别 · 计算机科学 2024-03-05 Shanchuan Lin , Anran Wang , Xiao Yang

The ability to fine-tune generative models for text-to-image generation tasks is crucial, particularly facing the complexity involved in accurately interpreting and visualizing textual inputs. While LoRA is efficient for language model…

计算机视觉与模式识别 · 计算机科学 2024-05-13 Mohan Zhou , Yalong Bai , Qing Yang , Tiejun Zhao

Personalized text-to-image models allow users to generate varied styles of images (specified with a sentence) for an object (specified with a set of reference images). While remarkable results have been achieved using diffusion-based…

计算机视觉与模式识别 · 计算机科学 2024-07-19 Fanyue Wei , Wei Zeng , Zhenyang Li , Dawei Yin , Lixin Duan , Wen Li

Recent advancements in diffusion models have notably improved the perceptual quality of generated images in text-to-image synthesis tasks. However, diffusion models often struggle to produce images that accurately reflect the intended…

计算机视觉与模式识别 · 计算机科学 2024-03-12 Yang Zhang , Teoh Tze Tzun , Lim Wei Hern , Tiviatis Sim , Kenji Kawaguchi

Evaluating the quality of automatically generated image descriptions is a complex task that requires metrics capturing various dimensions, such as grammaticality, coverage, accuracy, and truthfulness. Although human evaluation provides…

计算机视觉与模式识别 · 计算机科学 2024-11-11 Jia-Hong Huang , Hongyi Zhu , Yixian Shen , Stevan Rudinac , Evangelos Kanoulas

Currently, personalized image generation methods mostly require considerable time to finetune and often overfit the concept resulting in generated images that are similar to custom concepts but difficult to edit by prompts. We propose an…

计算机视觉与模式识别 · 计算机科学 2024-03-19 Yuxuan Zhang , Yiren Song , Jinpeng Yu , Han Pan , Zhongliang Jing

Recent text-to-image diffusion models can generate striking visuals from text prompts, but they often fail to maintain subject consistency across generations and contexts. One major limitation of current fine-tuning approaches is the…

计算机视觉与模式识别 · 计算机科学 2025-09-23 Gordon Chen , Ziqi Huang , Cheston Tan , Ziwei Liu
‹ 上一页 1 2 3 10 下一页 ›