![](https://img-blog.csdnimg.cn/20201014180756922.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
论文笔记
文章平均质量分 92
我是浮夸
科研新人,努力学习中,如有错误欢迎指正。
展开
-
BootPIG: Bootstrapping Zero-shot Personalized Image Generation Capabilities inPretrained Diffusion
BootPIG: Bootstrapping Zero-shot Personalized Image Generation Capabilities inPretrained Diffusion Models——【论文笔记】原创 2024-04-15 15:56:28 · 630 阅读 · 2 评论 -
Towards Efficient Diffusion-Based Image Editing with Instant Attention Masks——【论文笔记】
Towards Efficient Diffusion-Based Image Editing with Instant Attention Masks——【论文笔记】原创 2024-03-31 11:43:03 · 926 阅读 · 1 评论 -
Uni-ControlNet: All-in-One Control toText-to-Image Diffusion Models——【论文笔记】
Uni-ControlNet: All-in-One Control toText-to-Image Diffusion Models——【论文笔记】原创 2024-03-05 11:03:59 · 1701 阅读 · 1 评论 -
DreamMatcher: Appearance Matching Self-Attentionfor Semantically-Consistent Text-to-Image Personali
DreamMatcher: Appearance Matching Self-Attentionfor Semantically-Consistent Text-to-Image Personali——【论文笔记】原创 2024-03-04 12:32:34 · 878 阅读 · 0 评论 -
IP-Adapter: Text Compatible Image Prompt Adapter forText-to-Image Diffusion Models——【论文笔记】
IP-Adapter: Text Compatible Image Prompt Adapter forText-to-Image Diffusion Models——【论文笔记】原创 2024-02-27 11:25:58 · 1229 阅读 · 0 评论 -
SVDiff: Compact Parameter Space for Diffusion Fine-Tuning——【论文笔记】
SVDiff: Compact Parameter Space for Diffusion Fine-Tuning——【论文笔记】原创 2024-02-03 17:49:50 · 1633 阅读 · 0 评论 -
Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models——【论文笔记】
Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models——【论文笔记】原创 2024-01-29 15:29:30 · 1042 阅读 · 0 评论 -
Multi-Concept Customization of Text-to-Image Diffusion——【论文笔记】
Multi-Concept Customization of Text-to-Image Diffusion——【论文笔记】原创 2024-01-18 16:10:59 · 1407 阅读 · 3 评论 -
Adding Conditional Control to Text-to-Image Diffusion Models——【论文笔记】
Adding Conditional Control to Text-to-Image Diffusion Models——【论文笔记】原创 2024-01-06 14:54:40 · 1373 阅读 · 0 评论 -
Multi Diffusion: Fusing Diffusion Paths for Controlled Image Generation——【论文笔记】
Multi Diffusion: Fusing Diffusion Paths for Controlled Image Generation——【论文笔记】原创 2024-01-01 16:14:27 · 1377 阅读 · 0 评论 -
Magic Fusion: Boosting Text-to-Image Generation Performance by Fusing Diffusion Models——【论文笔记】
Magic Fusion: Boosting Text-to-Image Generation Performance by Fusing Diffusion Models——【论文笔记】原创 2023-12-29 12:47:15 · 914 阅读 · 1 评论 -
Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models——【论文笔记】
Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models——【论文笔记】原创 2023-12-25 16:23:36 · 1339 阅读 · 0 评论 -
Localizing Object-level Shape Variations with Text-to-Image Diffusion Models——论文笔记
Localizing Object-level Shape Variations with Text-to-Image Diffusion Models 发表于ICCV 2023原创 2023-12-18 17:24:40 · 1100 阅读 · 1 评论 -
Diffusion in style——论文笔记
实现扩散模型的风格化生成原创 2023-12-05 10:58:56 · 470 阅读 · 1 评论 -
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation——论文笔记
在这篇论文中,模型会出现语言漂移的原因是因为在使用少量图像进行微调时,模型可能会过度拟合这些图像,从而忘记了如何生成与这些图像相似但不完全相同的图像。这种现象被称为"过拟合",它会导致模型在生成图像时偏离先验信息,从而产生语言漂移。为了解决这个问题,DreamBooth提出了一个自生类别特定的先验保留损失,以鼓励模型生成符合先验信息的图像,从而保留先验信息的多样性和一致性。这样可以避免模型出现语言漂移现象,从而提高生成图像的质量和准确性。原创 2023-11-27 16:00:13 · 470 阅读 · 1 评论 -
High-Resolution Image Synthesis with Latent Diffusion Models——论文解读
利用潜在扩散模型生成高分辨率的图像,文章是发表于CVPR 2022上的一篇论文原创 2023-11-26 21:45:24 · 433 阅读 · 1 评论