← Search

Heyang Jiang

2 accepted papers

2024

Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment

NeurIPS 2024poster

In this paper, we point out that suboptimal noise-data mapping leads to slow training of diffusion models. During diffusion training, current methods diffuse each image across the entire noise space, resulting in a mixture of all images at every point in the noise layer. We emphasize that this rando…

2024

Inf-DiT: Upsampling any-resolution image with memory-efficient diffusion transformer.

ECCV 2024poster

"Diffusion models have shown remarkable performance in image generation in recent years. However, due to a quadratic increase in memory during generating ultra-high-resolution images (e.g. 4096 × 4096), the resolution of generated images is often limited to 1024×1024. In this work. we propose a unid…