Research
Introducing Vidu S1: Real-Time Interactive Video Generation
阅读论文
Research
Motubrain: An Advanced World Action Model for Robot Control
阅读论文
Research
Motus: A Unified Latent Action World Model
阅读论文
Open Source
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
阅读论文
Research
SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention
阅读论文
Research
Vidar: Embodied Video Diffusion Model for Generalist Manipulation
阅读论文
Research
SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration
阅读论文
Research
Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models
阅读论文
Research
One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale
阅读论文
Research
All are Worth Words: A ViT Backbone for Diffusion Models
阅读论文
Research
Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models
阅读论文
