5 papers · 1 filter
SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
Dongting Hu, Jierun Chen, Xijie Huang +16
Existing text-to-image (T2I) diffusion models face several limitations, including large model sizes, slow runtime, and low-quality generation on mobile devices. This paper aims to…
Slicing Vision Transformer for Flexible Inference
Yitian Zhang, Huseyin Coskun, Xu Ma +6
Vision Transformers (ViT) is known for its scalability. In this work, we target to scale down a ViT to fit in an environment with dynamic-changing resource constraints. We observe…
SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device
Yushu Wu, Zhixing Zhang, Yanyu Li +11
We have witnessed the unprecedented success of diffusion-based video generation over the past year. Recently proposed models from the community have wielded the power to generate c…
AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation
Anil Kag, Huseyin Coskun, Jierun Chen +5
Neural network architecture design requires making many crucial decisions. The common desiderata is that similar decisions, with little modifications, can be reused in a variety of…
Scalable Ranked Preference Optimization for Text-to-Image Generation
Shyamgopal Karthik, Huseyin Coskun, Zeynep Akata +3
Direct Preference Optimization (DPO) has emerged as a powerful approach to align text-to-image (T2I) models with human feedback. Unfortunately, successful application of DPO to T2I…