Related papers: A training-free framework for high-fidelity appear…

Diffusion Transformers (DiTs) have greatly advanced text-to-image generation, but models still struggle to generate the correct spatial relations between objects as specified in the text prompt. In this study, we adopt a mechanistic…

Video generation has drawn significant interest recently, pushing the development of large-scale models capable of producing realistic videos with coherent motion. Due to memory constraints, these models typically generate short video…

Transformer-based diffusion models have achieved significant advancements across a variety of generative tasks. However, producing high-quality outputs typically necessitates large transformer models, which result in substantial training…

Diffusion Transformers have emerged as the foundation for vision generative models, but their scalability is limited by the high cost of hyperparameter (HP) tuning at large scales. Recently, Maximal Update Parametrization ($\mu$P) was…

We present FreeMorph, the first tuning-free method for image morphing that accommodates inputs with different semantics or layouts. Unlike existing methods that rely on finetuning pre-trained diffusion models and are limited by time…

We present the Hourglass Diffusion Transformer (HDiT), an image generative model that exhibits linear scaling with pixel count, supporting training at high-resolution (e.g. $1024 \times 1024$) directly in pixel-space. Building on the…

This paper presents innovative enhancements to diffusion models by integrating a novel multi-resolution network and time-dependent layer normalization. Diffusion models have gained prominence for their effectiveness in high-fidelity image…

Current learning-based subject customization approaches, predominantly relying on U-Net architectures, suffer from limited generalization ability and compromised image quality. Meanwhile, optimization-based methods require subject-specific…

Inverting visual representations within deep neural networks (DNNs) presents a challenging and important problem in the field of security and privacy for deep learning. The main goal is to invert the features of an unidentified target image…

Text-to-image diffusion models have demonstrated remarkable effectiveness in rapid and high-fidelity personalization, even when provided with only a few user images. However, the effectiveness of personalization techniques has lead to…

Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities…

With the recent surge of generative models, diffusion-based approaches have become mainstream for view synthesis tasks, either in an explicit depth-warp-inpaint or in an implicit end-to-end manner. Despite their success, both paradigms…

This paper does not describe a new method; instead, it provides a thorough exploration of an important yet understudied design space related to recent advances in text-to-image synthesis -- specifically, the deep fusion of large language…

Recent advances in diffusion models have demonstrated remarkable capabilities in video generation. However, the computational intensity remains a significant challenge for practical applications. While feature caching has been proposed to…

Large-scale generative models, such as text-to-image diffusion models, have garnered widespread attention across diverse domains due to their creative and high-fidelity image generation. Nonetheless, existing large-scale diffusion models…

Pre-trained diffusion models have demonstrated remarkable proficiency in synthesizing images across a wide range of scenarios with customizable prompts, indicating their effective capacity to capture universal features. Motivated by this,…

Face recognition poses serious privacy risks due to its reliance on sensitive and immutable biometric data. While modern systems mitigate privacy risks by mapping facial images to embeddings (commonly regarded as privacy-preserving), model…

Diffusion models have emerged as the leading approach for image synthesis, demonstrating exceptional photorealism and diversity. However, training diffusion models at high resolutions remains computationally prohibitive, and existing…

Recent advancements in large-scale text-to-image diffusion models have enabled many applications in image editing. However, none of these methods have been able to edit the layout of single existing images. To address this gap, we propose…

This technical report presents a diffusion model based framework for face swapping between two portrait images. The basic framework consists of three components, i.e., IP-Adapter, ControlNet, and Stable Diffusion's inpainting pipeline, for…