Related papers: Efficient Scaling of Diffusion Transformers for Te…
The aim of this work is to explore the potential of pre-trained vision-language models, e.g. Vision Transformers (ViT), enhanced with advanced data augmentation strategies for the detection of AI-generated images. Our approach leverages a…
Score-based diffusion models have captured widespread attention and funded fast progress of recent vision generative tasks. In this paper, we focus on diffusion model backbone which has been much neglected before. We systematically explore…
Vision Transformers have attracted a lot of attention recently since the successful implementation of Vision Transformer (ViT) on vision tasks. With vision Transformers, specifically the multi-head self-attention modules, networks can…
Text encoders in diffusion models have rapidly evolved, transitioning from CLIP to T5-XXL. Although this evolution has significantly enhanced the models' ability to understand complex prompts and generate text, it also leads to a…
Vision Transformer (ViT) has demonstrated promising performance in computer vision tasks, comparable to state-of-the-art neural networks. Yet, this new type of deep neural network architecture is vulnerable to adversarial attacks limiting…
Diffusion Transformers (DiTs) can generate short photorealistic videos, yet directly training and sampling longer videos with full attention across the video remains computationally challenging. Alternative methods break long videos down…
Existing parameter-efficient fine-tuning (PEFT) methods have achieved significant success on vision transformers (ViTs) adaptation by improving parameter efficiency. However, the exploration of enhancing inference efficiency during…
Diffusion-based models have achieved state-of-the-art performance on text-to-image synthesis tasks. However, one critical limitation of these models is the low fidelity of generated images with respect to the text description, such as…
Diffusion models (DMs) embark a new era of generative modeling and offer more opportunities for efficient generating high-quality and realistic data samples. However, their widespread use has also brought forth new challenges in model…
Diffusion Transformers (DiTs) have recently gained substantial attention in both industrial and academic fields for their superior visual generation capabilities, outperforming traditional diffusion models that use U-Net. However,the…
Diffusion Transformers (DiTs) have recently improved video generation quality. However, their heavy computational cost makes real-time or on-device generation infeasible. In this work, we introduce S2DiT, a Streaming Sandwich Diffusion…
Diffusion Transformer (DiT) has driven significant progress in image generation tasks. However, DiT inferencing is notoriously compute-intensive and incurs long latency even on datacenter-scale GPUs, primarily due to its iterative nature…
While generative modeling on time series facilitates more capable and flexible probabilistic forecasting, existing generative time series models do not address the multi-dimensional properties of time series data well. The prevalent…
In this work, we introduce Dual Attention Vision Transformers (DaViT), a simple yet effective vision transformer architecture that is able to capture global context while maintaining computational efficiency. We propose approaching the…
We propose Latent-Shift -- an efficient text-to-video generation method based on a pretrained text-to-image generation model that consists of an autoencoder and a U-Net diffusion model. Learning a video diffusion model in the latent space…
Diffusion models have recently gained state of the art performance on many image generation tasks. However, most models require significant computational resources to achieve this. This becomes apparent in the application of medical image…
Diffusion Transformer (DiT) is a crucial method for content generation. However, it needs a lot of time to sample. Many studies have attempted to use caching to reduce the time consumption of sampling. Existing caching methods accelerate…
Scaling video diffusion transformers (DiTs) is limited by their quadratic 3D attention, even though most of the attention mass concentrates on a small subset of positions. We turn this observation into VSA, a trainable, hardware-efficient…
This paper introduces a pioneering 3D volumetric encoder designed for text-to-3D generation. To scale up the training data for the diffusion model, a lightweight network is developed to efficiently acquire feature volumes from multi-view…
Recent breakthroughs of transformer-based diffusion models, particularly with Multimodal Diffusion Transformers (MMDiT) driven models like FLUX and Qwen Image, have facilitated thrilling experiences in text-to-image generation and editing.…