VDT: General-purpose Video Diffusion Transformers via Mask Modeling
read the original abstract
This work introduces Video Diffusion Transformer (VDT), which pioneers the use of transformers in diffusion-based video generation. It features transformer blocks with modularized temporal and spatial attention modules to leverage the rich spatial-temporal representation inherited in transformers. We also propose a unified spatial-temporal mask modeling mechanism, seamlessly integrated with the model, to cater to diverse video generation scenarios. VDT offers several appealing benefits. 1) It excels at capturing temporal dependencies to produce temporally consistent video frames and even simulate the physics and dynamics of 3D objects over time. 2) It facilitates flexible conditioning information, \eg, simple concatenation in the token space, effectively unifying different token lengths and modalities. 3) Pairing with our proposed spatial-temporal mask modeling mechanism, it becomes a general-purpose video diffuser for harnessing a range of tasks, including unconditional generation, video prediction, interpolation, animation, and completion, etc. Extensive experiments on these tasks spanning various scenarios, including autonomous driving, natural weather, human action, and physics-based simulation, demonstrate the effectiveness of VDT. Additionally, we present comprehensive studies on how \model handles conditioning information with the mask modeling mechanism, which we believe will benefit future research and advance the field. Project page: https:VDT-2023.github.io
This paper has not been read by Pith yet.
Forward citations
Cited by 9 Pith papers
-
AttentionBender: Manipulating Cross-Attention in Video Diffusion Transformers as a Creative Probe
AttentionBender applies 2D transforms to cross-attention maps in video diffusion transformers, producing distributed distortions and glitch aesthetics that reveal entangled attention mechanisms while serving as both a...
-
FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generation
FrameDiT proposes Matrix Attention for DiTs to achieve SOTA video generation with improved temporal coherence and efficiency comparable to local factorized attention.
-
GF-DiT: Scheduling Parallelism for Diffusion Transformer Serving
GF-DiT dynamically adapts parallelism during DiT serving via trajectory tasks and group-free collectives, reporting up to 6x throughput and 95% latency reduction versus static configurations.
-
GF-DiT: Scheduling Parallelism for Diffusion Transformer Serving
GF-DiT introduces elastic GPU parallelism scheduling for DiT serving via asynchronous trajectory tasks and group-free collectives, reporting up to 6.01x throughput gains over static configurations.
-
Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models
Lumos-Nexus is a training-efficient video generation framework using two-stage alignment of a lightweight model followed by progressive frequency bridging to a high-fidelity generator in homogeneous latent space, plus...
-
RoPeSLR: 3D RoPE-driven Sparse-LowRank Attention for Efficient Diffusion Transformers
RoPeSLR combines 3D RoPE-guided sparse attention with head-wise low-rank parameterization to achieve sub-quadratic complexity in DiTs while preserving distance awareness for efficient ultra-long video synthesis.
-
Multimodal Diffusion Transformer with Memory Bank for Scalable Long-Duration Talking Video Generation
LetsTalk combines a multimodal diffusion transformer, noise-regularized memory bank, deep compression autoencoder, and symbiotic/direct fusion schemes to achieve state-of-the-art quality and efficiency in long-duratio...
-
Making Time Editable in Video Diffusion Transformers
Introduces a lightweight temporal module to extend pretrained DiT video models with time editing capabilities while preserving the original generative prior.
-
Evolution of Video Generative Foundations
This survey traces video generation technology from GANs to diffusion models and then to autoregressive and multimodal approaches while analyzing principles, strengths, and future trends.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.