5 papers
ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems
Xiangyuan Xue, Zeyu Lu, Di Huang +3
Much previous AI research has focused on developing monolithic models to maximize their intelligence, with the primary goal of enhancing performance on specific tasks. In contrast,…
ScaMo: Exploring the Scaling Law in Autoregressive Motion Generation Model
Shunlin Lu, Jingbo Wang, Zeyu Lu +6
The scaling law has been validated in various domains, such as natural language processing (NLP) and massive computer vision tasks; however, its application to motion generation re…
FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model
ZiDong Wang, Zeyu Lu, Di Huang +3
\textit{Nature is infinitely resolution-free}. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing imag…
FiT: Flexible Vision Transformer for Diffusion Model
Zeyu Lu, Zidong Wang, Di Huang +4
Nature is infinitely resolution-free. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolut…
Diffusion Models Need Visual Priors for Image Generation
Xiaoyu Yue, Zidong Wang, Zeyu Lu +5
Conventional class-guided diffusion models generally succeed in generating images with correct semantic content, but often struggle with texture details. This limitation stems from…