04 2025 档案

Improving Subject-Driven Image Synthesis with Subject-Agnostic Guidance
摘要：https://openaccess.thecvf.com/content/CVPR2024/papers/Chan_Improving_Subject-Driven_Image_Synthesis_with_Subject-Agnostic_Guidance_CVPR_2024_paper.pdf 阅读全文
posted @ 2025-04-30 19:52 郭新晨 阅读(8) 评论(0) 推荐(0)
Flux Already Knows – Activating Subject-Driven Image Generation without Training
摘要：https://arxiv.org/pdf/2504.11478 阅读全文
posted @ 2025-04-30 19:51 郭新晨 阅读(39) 评论(0) 推荐(0)
PASTE, INPAINT AND HARMONIZE VIA DENOISING: SUBJECT-DRIVEN IMAGE EDITING WITH PRE-TRAINED DIFFUSION MODEL
摘要：https://arxiv.org/pdf/2306.07596 阅读全文
posted @ 2025-04-30 19:50 郭新晨 阅读(10) 评论(0) 推荐(0)
DreamEdit: Subject-driven Image Editing
摘要：https://dreameditbenchteam.github.io/ 阅读全文
posted @ 2025-04-30 19:48 郭新晨 阅读(19) 评论(0) 推荐(0)
Official implementations for paper: Customizable Image Synthesis with Multiple Subjects
摘要：https://github.com/ali-vilab/Cones-V2 阅读全文
posted @ 2025-04-30 19:47 郭新晨 阅读(6) 评论(0) 推荐(0)
Cones 2: Customizable Image Synthesis with Multiple Subjects
摘要：https://cones-page.github.io/ 阅读全文
posted @ 2025-04-30 19:46 郭新晨 阅读(8) 评论(0) 推荐(0)
UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning
摘要：https://github.com/bytedance/uno 阅读全文
posted @ 2025-04-30 19:45 郭新晨 阅读(11) 评论(0) 推荐(0)
DynASyn: Multi-Subject Personalization Enabling Dynamic Action Synthesis
摘要：https://arxiv.org/abs/2503.17728 阅读全文
posted @ 2025-04-30 19:45 郭新晨 阅读(5) 评论(0) 推荐(0)
探索多主体自定义图像合成新境界：Cones 2 深度解析与推荐
摘要：https://blog.csdn.net/gitblog_00214/article/details/141315562 阅读全文
posted @ 2025-04-30 19:44 郭新晨 阅读(7) 评论(0) 推荐(0)
CVPR2024 | 图片生成与编辑相关的AIGC文章汇总
摘要：https://zhuanlan.zhihu.com/p/687467814 阅读全文
posted @ 2025-04-30 19:43 郭新晨 阅读(4) 评论(0) 推荐(0)
MS-DIFFUSION: MULTI-SUBJECT ZERO-SHOT IMAGE PERSONALIZATION WITH LAYOUT GUIDANCE
摘要：https://arxiv.org/pdf/2406.07209 阅读全文
posted @ 2025-04-30 19:41 郭新晨 阅读(15) 评论(0) 推荐(0)
Deep Unfolding Multi-modal Image Fusion Network via Attribution Analysis
摘要：https://arxiv.org/pdf/2502.01467 阅读全文
posted @ 2025-04-30 19:41 郭新晨 阅读(7) 评论(0) 推荐(0)
MambaDFuse: A Mamba-based Dual-phase Model for Multi-modality Image Fusion
摘要：https://arxiv.org/pdf/2404.08406 阅读全文
posted @ 2025-04-30 19:40 郭新晨 阅读(9) 评论(0) 推荐(0)
FastComposer：一种无需微调的多主题图像生成技术
摘要：https://zhuanlan.zhihu.com/p/635154796 阅读全文
posted @ 2025-04-30 19:39 郭新晨 阅读(7) 评论(0) 推荐(0)
image to 3d repository
摘要：https://github.com/guochengqian/Magic123 https://github.com/junshutang/Make-It-3D https://github.com/yiyuzhuang/IDOL https://github.com/SUDO-AI-3D/One 阅读全文
posted @ 2025-04-27 14:22 郭新晨 阅读(12) 评论(0) 推荐(0)
Virtual Try-On App using Flutter
摘要：https://github.com/shreyassai123/virtual-tryon 阅读全文
posted @ 2025-04-25 18:02 郭新晨 阅读(5) 评论(0) 推荐(0)
image to video
摘要：https://ppetrichor.github.io/levitor.github.io/ https://github.com/angelvillar96/TextOCVP https://github.com/MOSTAFA1172m/Image-text-video-I2VGENXL ht 阅读全文
posted @ 2025-04-22 17:42 郭新晨 阅读(16) 评论(0) 推荐(0)
Tripo开源TripoSG 1.5B模型，推动单图像生成高保真3D形状技术发展
摘要：https://mp.weixin.qq.com/s/AysG2PIbrhh0dAzdWR4Bbw 阅读全文
posted @ 2025-04-10 11:20 郭新晨 阅读(25) 评论(0) 推荐(0)
照片秒变精模 | 用法线桥接实现“毫米级建模”，「毛孔级精度」让游戏&影视等行业狂喜！
摘要：https://stable-x.github.io/Hi3DGen/ 阅读全文
posted @ 2025-04-10 11:08 郭新晨 阅读(7) 评论(0) 推荐(0)
WonderTurbo:Generating Interactive 3D World in 0.72 Seconds
摘要：https://wonderturbo.github.io/ 阅读全文
posted @ 2025-04-09 19:46 郭新晨 阅读(19) 评论(0) 推荐(0)
tryon projects
摘要：https://github.com/shadow2496/VITON-HD https://github.com/rlawjdghek/StableVITON https://github.com/hywang2002/MV-VTON https://github.com/rlawjdghek/P 阅读全文
posted @ 2025-04-09 19:44 郭新晨 阅读(18) 评论(1) 推荐(0)