paper-with-me

홈 › Papers

Exploring the latent space of diffusion models directly through singular value decomposition

2025-02-04 · Li Wang, Boyan Gao, Yanran Li, Zhao Wang, Xiaosong Yang, David A. Clifton, Jun Xiao

Despite the groundbreaking success of diffusion models in generating high-fidelity images, their latent space remains relatively under-explored, even though it holds significant promise for enabling versatile and interpretable image editing capabilities. The complicated denoising trajectory and high dimensionality of the latent space make it extremely challenging to interpret. Existing methods mainly explore the feature space of U-Net in Diffusion Models (DMs) instead of the latent space itself. In contrast, we directly investigate the latent space via Singular Value Decomposition (SVD) and discover three useful properties that can be used to control generation results without the requirements of data collection and maintain identity fidelity generated images. Based on these properties, we propose a novel image editing framework that is capable of learning arbitrary attributes from one pair of latent codes destined by text prompts in Stable Diffusion Models. To validate our approach, extensive experiments are conducted to demonstrate its effectiveness and flexibility in image editing. We will release our codes soon to foster further research and applications in this area.

📄 PDF Abstract BibTeX arXiv:2502.02225

Code (0)

등록된 구현이 없습니다.

Tasks

Denoising

Methods 이 논문이 사용한 방법론

Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
U-Net 설명 없음

Similar Papers 제목 키워드 기반

Exploring Molecule Generation Using Latent Space Graph Diffusion

2025-01-07 · Prashanth Pombala, Gerrit Grossmann, Verena Wolf

Generating molecular graphs is a challenging task due to their discrete nature and the competitive objectives involved. Diffusion models have emerged as SOTA approaches in data generation across various modalities. For m…

Computational EfficiencyDenoising

InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models

2023-06-14 · Yingheng Wang, Yair Schiff, Aaron Gokaslan, Weishen Pan 외

While diffusion models excel at generating high-quality samples, their latent variables typically lack semantic meaning and are not suitable for representation learning. Here, we propose InfoDiffusion, an algorithm that …

Representation Learning

Isometric Representation Learning for Disentangled Latent Space of Diffusion Models

2024-07-16 · Jaehoon Hahm, Junho Lee, Sunghyun Kim, Joonseok Lee

The latent space of diffusion model mostly still remains unexplored, despite its great success and potential in the field of generative modeling. In fact, the latent space of existing diffusion models are entangled, with…

Representation Learning

Exploring MLLM-Diffusion Information Transfer with MetaCanvas

2025-12-12 · Han Lin, Xichen Pan, Ziqi Huang, Ji Hou 외 arxiv

Multimodal learning has rapidly advanced visual understanding, largely via multimodal large language models (MLLMs) that use powerful LLMs as cognitive cores. In visual generation, however, these powerful core models are…

Text-to-Image GenerationVideo Generation

Exploring Attribute Variations in Style-based GANs using Diffusion Models

2023-11-27 · Rishubh Parihar, Prasanna Balaji, Raghav Magazine, Sarthak Vora 외

Existing attribute editing methods treat semantic attributes as binary, resulting in a single edit per attribute. However, attributes such as eyeglasses, smiles, or hairstyles exhibit a vast range of diversity. In this w…

AttributeDenoisingDiversity