Imagen de Portada

DreamBoothDPO: Improving Personalized Generation using Direct Preference Optimization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ayupov, Shamil, Nakhodnov, Maksim, Yaschenko, Anastasia, Kuznetsov, Andrey, Alanov, Aibek
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Beyond Fine-Tuning: A Systematic Study of Sampling Techniques in Personalized Image Generation
por: Soboleva, Vera, et al.
Publicado: (2025)

ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models
por: Sorokin, Dmitrii, et al.
Publicado: (2025)

Inverse-and-Edit: Effective and Fast Image Editing by Cycle Consistency Models
por: Beletskii, Ilia, et al.
Publicado: (2025)

SHIFT: Steering Hidden Intermediates in Flow Transformers
por: Konovalova, Nina, et al.
Publicado: (2026)

MaterialFusion: High-Quality, Zero-Shot, and Controllable Material Transfer with Diffusion Models
por: Garifullin, Kamil, et al.
Publicado: (2025)

Heeding the Inner Voice: Aligning ControlNet Training via Intermediate Features Feedback
por: Konovalova, Nina, et al.
Publicado: (2025)

T-LoRA: Single Image Diffusion Model Customization Without Overfitting
por: Soboleva, Vera, et al.
Publicado: (2025)

FastFace: Tuning Identity Preservation in Distilled Diffusion via Guidance and Attention
por: Karpukhin, Sergey, et al.
Publicado: (2025)

HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach
por: Nikolaev, Maxim, et al.
Publicado: (2024)

ATATA: One Algorithm to Align Them All
por: Pang, Boyi, et al.
Publicado: (2026)

AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation
por: Pang, Lianyu, et al.
Publicado: (2024)

The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing
por: Bobkov, Denis, et al.
Publicado: (2024)

High-Frequency Anti-DreamBooth: Robust Defense against Personalized Image Synthesis
por: Onikubo, Takuto, et al.
Publicado: (2024)

DeDPO: Debiased Direct Preference Optimization for Diffusion Models
por: Pham, Khiem, et al.
Publicado: (2026)

Reg-DPO: SFT-Regularized Direct Preference Optimization with GT-Pair for Improving Video Generation
por: Du, Jie, et al.
Publicado: (2025)

Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing
por: Titov, Vadim, et al.
Publicado: (2024)

AVC-DPO: Aligned Video Captioning via Direct Preference Optimization
por: Tang, Jiyang, et al.
Publicado: (2025)

PersonaBooth: Personalized Text-to-Motion Generation
por: Kim, Boeun, et al.
Publicado: (2025)

A New Chinese Landscape Paintings Generation Model based on Stable Diffusion using DreamBooth
por: Gu, Yujia, et al.
Publicado: (2024)

GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver
por: Oganov, Aleksandr, et al.
Publicado: (2025)

Generating Synthetic Data via Augmentations for Improved Facial Resemblance in DreamBooth and InstantID
por: Ulusan, Koray, et al.
Publicado: (2025)

SEE-DPO: Self Entropy Enhanced Direct Preference Optimization
por: Shekhar, Shivanshu, et al.
Publicado: (2024)

HuViDPO:Enhancing Video Generation through Direct Preference Optimization for Human-Centric Alignment
por: Jiang, Lifan, et al.
Publicado: (2025)

HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Models
por: Ruiz, Nataniel, et al.
Publicado: (2023)

PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation
por: Huang, Qihan, et al.
Publicado: (2024)

FocusDPO: Dynamic Preference Optimization for Multi-Subject Personalized Image Generation via Adaptive Focus
por: Jin, Qiaoqiao, et al.
Publicado: (2025)

SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization
por: Jia, Hongrui, et al.
Publicado: (2024)

InstructBooth: Instruction-following Personalized Text-to-Image Generation
por: Chae, Daewon, et al.
Publicado: (2023)

Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation
por: Croitoru, Florinel-Alin, et al.
Publicado: (2026)

Random Direct Preference Optimization for Radiography Report Generation
por: Samokhin, Valentin, et al.
Publicado: (2025)

VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models
por: Huang, Haojian, et al.
Publicado: (2025)

$ϕ$-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models
por: Truong, Thanh-Dat, et al.
Publicado: (2026)

MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models
por: Liu, Ziyu, et al.
Publicado: (2024)

DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models
por: Wu, Ziyi, et al.
Publicado: (2025)

S2H-DPO: Hardness-Aware Preference Optimization for Vision-Language Models
por: Shukla, Nitish, et al.
Publicado: (2026)

Few-shot multi-token DreamBooth with LoRa for style-consistent character generation
por: Pascual, Ruben, et al.
Publicado: (2025)

V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization
por: Xie, Yuxi, et al.
Publicado: (2024)

AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization
por: Chaubey, Ashutosh, et al.
Publicado: (2026)

RealDPO: Real or Not Real, that is the Preference
por: Cheng, Guo, et al.
Publicado: (2025)

InpaintDPO: Mitigating Spatial Relationship Hallucinations in Foreground-conditioned Inpainting via Diverse Preference Optimization
por: Li, Qirui, et al.
Publicado: (2025)