#artificial intelligence
Sep 2025
DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
DC-Gen, a general framework that accelerates text-to-image diffusion models by leveraging a deeply compressed latent space, uses an efficient post-training pipeline to preserve the quality of the base model to reduce the latency of 4K image generation.
Wen-Kun He, Yuchao Gu, Jun-Yu Chen et al.
· arXiv.org · 9 citations
· ⚡1