paper-with-me

홈 › Papers

Compositional Inversion for Stable Diffusion Models

2023-12-13 · Xulu Zhang, Xiao-Yong Wei, Jinlin Wu, Tianyi Zhang, Zhaoxiang Zhang, Zhen Lei, Qing Li

Inversion methods, such as Textual Inversion, generate personalized images by incorporating concepts of interest provided by user images. However, existing methods often suffer from overfitting issues, where the dominant presence of inverted concepts leads to the absence of other desired concepts. It stems from the fact that during inversion, the irrelevant semantics in the user images are also encoded, forcing the inverted concepts to occupy locations far from the core distribution in the embedding space. To address this issue, we propose a method that guides the inversion process towards the core distribution for compositional embeddings. Additionally, we introduce a spatial regularization approach to balance the attention on the concepts being composed. Our method is designed as a post-training approach and can be seamlessly integrated with other inversion methods. Experimental results demonstrate the effectiveness of our proposed approach in mitigating the overfitting problem and generating more diverse and balanced compositions of concepts in the synthesized images. The source code is available at https://github.com/zhangxulu1996/Compositional-Inversion.

📄 PDF Abstract BibTeX arXiv:2312.08048

Code (1)

zhangxulu1996/compositional-inversion 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Inversion-DPO: Precise and Efficient Post-Training for Diffusion Models

2025-07-14 · Zejian Li, Yize Li, Chenye Meng, Zhongni Liu 외 arxiv

Recent advancements in diffusion models (DMs) have been propelled by alignment methods that post-train models to better conform to human preferences. However, these approaches typically require computation-intensive trai…

Text-to-Image Generation

Stable and Near-Reversible Diffusion ODE Solvers for Image Editing

2026-05-12 · Barbora Barancikova, Daniil Shmelev, Cristopher Salvi arxiv

The inversion of diffusion models plays a central role in image editing. Algebraically reversible ODE solvers provide an appealing approach to diffusion inversion for text-guided image editing, by eliminating the inversi…

Image Editing

EDICT: Exact Diffusion Inversion via Coupled Transformations

2022-11-22 · CVPR 2023 1 · Bram Wallace, Akash Gokul, Nikhil Naik

Finding an initial noise vector that produces an input image when fed into the diffusion process (known as inversion) is an important problem in denoising diffusion models (DDMs), with applications for real image editing…

DenoisingImage ReconstructionImage StylizationText-based Image Editing+1

Are Diffusion Models Vision-And-Language Reasoners?

2023-05-25 · NeurIPS 2023 11 · Benno Krojer, Elinor Poole-Dayan, Vikram Voleti, Christopher Pal 외

Text-conditioned image generation models have recently shown immense qualitative success using denoising diffusion processes. However, unlike discriminative vision-and-language models, it is a non-trivial task to subject…

DenoisingImage GenerationImage-text matchingText Matching

Aided design of bridge aesthetics based on Stable Diffusion fine-tuning

2024-09-24 · Leye Zhang, Xiangxiang Tian, Chengli Zhang, Hongjun Zhang

Stable Diffusion fine-tuning technique is tried to assist bridge-type innovation. The bridge real photo dataset is built, and Stable Diffusion is fine tuned by using four methods that are Textual Inversion, Dreambooth, H…