5 papers
Vitality-Aware Compression for Efficient Image-to-Shape Diffusion Transformers
Jaeah Lee, Hyunjin Kim, Jaewoong Cho +1
We propose the first compression approach for image-to-shape Diffusion Transformers (DiTs) that substantially reduces model size while preserving geometric fidelity. Despite remark…
Rare-to-Frequent: Unlocking Compositional Generation Power of Diffusion Models on Rare Concepts with LLM Guidance
Dongmin Park, Sebin Kim, Taehong Moon +3
State-of-the-art text-to-image (T2I) diffusion models often struggle to generate rare compositions of concepts, e.g., objects with unusual attributes. In this paper, we show that t…
Efficient Generative Modeling with Residual Vector Quantization-Based Tokens
Jaehyeon Kim, Taehong Moon, Keon Lee +1
We introduce ResGen, an efficient Residual Vector Quantization (RVQ)-based generative model for high-fidelity generation with fast sampling. RVQ improves data fidelity by increasin…
Fast and Accurate Neural Rendering Using Semi-Gradients
In-Young Cho, Jaewoong Cho
We propose a simple yet effective neural network-based framework for global illumination rendering. Recently, rendering techniques that learn neural radiance caches by minimizing t…
A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models
Taehong Moon, Moonseok Choi, EungGu Yun +4
Diffusion models have shown remarkable performance in generation problems over various domains including images, videos, text, and audio. A practical bottleneck of diffusion models…