logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回

Controllable Generation With Text-to-Image Diffusion Models: A Survey

delete2025-12-19
delete0
PRE
AI
F
Feng Zhou
Q
Qing Song
L
Lu Yang
DOI：10.1109/TPAMI.2025.3646548delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
在视觉生成领域快速发展的背景下，扩散模型已彻底改变了该领域的格局，凭借其出色的文本引导生成功能，显著提升了能力。然而，仅依赖文本对这些模型进行条件控制，无法完全满足不同应用和场景的多样性与复杂性需求。认识到这一不足，多项研究致力于控制预训练的文本到图像（T2I）模型，以支持新型条件输入。本综述对基于T2I扩散模型的可控生成文献进行了全面回顾，涵盖了该领域的基础理论与实际进展。我们的综述首先简要介绍了去噪扩散概率模型（DDPMs）的基础知识以及广泛应用的T2I扩散模型。此外，我们从条件控制的角度，将相关研究分为三个方向进行概述：基于特定条件的生成、基于多条件的生成以及通用可控生成。针对每个类别，我们分析了其底层控制机制，并基于核心技术对代表性方法进行了综述。
Keyword:
Survey
text-to-image diffusion model
controllable generation
AIGC

期刊

IEEE Transactions on Pattern Analysis and Machine Intelligence 封面图
IEEE Transactions on Pattern Analysis and Machine Intelligence
IF:
18.6
论文数:
1.0K
被引数:
9.8W

机构

B
beijing university of posts and telecommunications
学者数:
2.3K
论文数: 861
被引数: 0
引用论文

引用论文

Initno: Boosting Text-to-Image Diffusion Models via Initial Noise OptimizationInitno: 通过初始噪声优化提升文本到图像扩散模型
err2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2024-06-16
err0
PREAI
errXiefan Guo; Jinlin Liu; Miaomiao Cui; Jiankai Li; Hongyu Yang; Di Huang
err分享
err收藏
MagiCapture: High-Resolution Multi-Concept Portrait Customization
errProceedings of the AAAI Conference on Artificial Intelligence
IF0
err
err0
PREAI
errHyung,Junha; Shin,Jaeyo; Choo,Jaegul
err分享
err收藏
LCM-Lookahead for Encoder-Based Text-to-Image Personalization
errLecture Notes in Computer Science
IF0
err2025-01-01
err0
PREAI
errGal,Rinon; Lichter,Or; Richardson,Elad; Patashnik,Or; Bermano,Amit H.; Chechik,Gal; Cohen-Or,Daniel
err分享
err收藏
C3Net: Compound Conditioned ControlNet for Multimodal Content Generation
err
IF0
err2024-06-16
err0
PREAI
errJuntao Zhang; Yuehuai Liu; Yu-Wing Tai; Chi-Keung Tang
err分享
err收藏
VideoBooth: Diffusion-based Video Generation with Image PromptsVideoBooth: 基于图像提示的扩散视频生成
err2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2024-06-16
err0
PREAI
errYuming Jiang; Tianxing Wu; Shuai Yang; Chenyang Si; Dahua Lin; Yu Qiao; Chen Change Loy; Ziwei Liu
err分享
err收藏
Cross Initialization for Face Personalization of Text-to-Image Models跨初始化文本到图像模型的个性化人脸技术
err2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2024-06-16
err0
PREAI
errLianyu Pang; Jian Yin; Haoran Xie; Qiping Wang; Qing Li; Xudong Mao
err分享
err收藏
Dense Text-to-Image Generation with Attention Modulation
err2023 IEEE/CVF International Conference on Computer Vision (ICCV)
IF0
err2023-10-01
err0
errOAAI
errYunji Kim; Jiyoung Lee; Jin-Hwa Kim; Jung-Woo Ha; Jun-Yan Zhu
err分享
err收藏
PartCraft: Crafting Creative Objects by Parts
errLecture Notes in Computer Science
IF0
err2025-01-01
err0
PREAI
errNg,Kam Woh; Zhu,Xiatian; Song,Yi-Zhe; Xiang,Tao
err分享
err收藏
Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis粗到精的隐式扩散用于姿态引导的人像图像合成
err2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
IF0
err2024-06-16
err0
PREAI
errYanzuo Lu; Manlin Zhang; Andy J Ma; Xiaohua Xie; Jianhuang Lai
err分享
err收藏
MagicTailor: Component-Controllable Personalization in Text-to-Image Diffusion Models
errProceedings of the Thirty-ThirdInternational Joint Conference on Artificial Intelligence
IF0
err2024-08-01
err0
PREAI
errZhou,Donghao; Huang,Jiancheng; Bai,Jinbin; Wang,Jiaze; Chen,Hao; Chen,Guangyong; Hu,Xiaowei; Heng,Pheng-Ann
err分享
err收藏
学者 查看更多内容