Related papers: DDiT: Dynamic Resource Allocation for Diffusion Tr…
Diffusion models have achieved remarkable progress in high-fidelity image, video, and audio generation, yet inference remains computationally expensive. Nevertheless, current diffusion acceleration methods based on distributed parallelism…
This work presents a diffusion transformer framework for data-driven structural topology optimization that combines the accuracy of physics-based methods with the efficiency of generative deep learning. Conventional approaches such as the…
We present Vchitect-2.0, a parallel transformer architecture designed to scale up video diffusion models for large-scale text-to-video generation. The overall Vchitect-2.0 system has several key designs. (1) By introducing a novel…
Diffusion transformers (DiTs) combine transformer architectures with diffusion models. However, their computational complexity imposes significant limitations on real-time applications and sustainability of AI systems. In this study, we aim…
We present VoiceDiT, a multi-modal generative model for producing environment-aware speech and audio from text and visual prompts. While aligning speech with text is crucial for intelligible speech, achieving this alignment in noisy…
Diffusion Transformer (DiT) faces challenges when generating images with higher resolution compared at training resolution, causing especially structural degradation due to attention dilution. Previous approaches attempt to mitigate this by…
Diffusion models are widely recognized for generating high-quality and diverse images, but their poor real-time performance has led to numerous acceleration works, primarily focusing on UNet-based structures. With the more successful…
Diffusion models achieve superior performance in image generation tasks. However, it incurs significant computation overheads due to its iterative structure. To address these overheads, we analyze this iterative structure and observe that…
Generating temporally-consistent high-fidelity videos can be computationally expensive, especially over longer temporal spans. More-recent Diffusion Transformers (DiTs) -- despite making significant headway in this context -- have only…
Diffusion models are the standard toolkit for generative modelling of 3D atomic systems. However, for different types of atomic systems -- such as molecules and materials -- the generative processes are usually highly specific to the target…
The increased model capacity of Diffusion Transformers (DiTs) and the demand for generating higher resolutions of images and videos have led to a significant rise in inference latency, impacting real-time performance adversely. While prior…
While Diffusion Transformers (DiTs) have achieved breakthroughs in video generation, this long sequence generation task remains constrained by the quadratic complexity of attention mechanisms, resulting in significant inference latency.…
Generating high-fidelity, temporally consistent videos in autonomous driving scenarios faces a significant challenge, e.g. problematic maneuvers in corner cases. Despite recent video generation works are proposed to tackcle the mentioned…
Video virtual try-on (VVT) technology has garnered considerable academic interest owing to its promising applications in e-commerce advertising and entertainment. However, most existing end-to-end methods rely heavily on scarce paired…
Transformer architectures, particularly Diffusion Transformers (DiTs), have become widely used in diffusion and flow-matching models due to their strong performance compared to convolutional UNets. However, the isotropic design of DiTs…
Diffusion Transformers (DiTs) deliver remarkable image and video generation quality but incur high computational cost, limiting scalability and on-device deployment. We introduce CoReDiT, a structured token pruning framework for DiTs across…
High-fidelity video generation remains challenging for diffusion models due to the difficulty of modeling complex spatio-temporal dynamics efficiently. Recent video diffusion methods typically represent a video as a sequence of…
Existing video tokenizers typically use the traditional Variational Autoencoder (VAE) architecture for video compression and reconstruction. However, to achieve good performance, its training process often relies on complex multi-stage…
In this paper, we explore the visual representations produced from a pre-trained text-to-video (T2V) diffusion model for video understanding tasks. We hypothesize that the latent representation learned from a pretrained generative T2V model…
Video motion transfer aims to synthesize videos by generating visual content according to a text prompt while transferring the motion pattern observed in a reference video. Recent methods predominantly use the Diffusion Transformer (DiT)…