Saved in:
Bibliographic Details
Main Authors: He, Wenkun, Gu, Yuchao, Chen, Junyu, Zou, Dongyun, Lin, Yujun, Zhang, Zhekai, Xi, Haocheng, Li, Muyang, Zhu, Ligeng, Yu, Jincheng, Chen, Junsong, Xie, Enze, Han, Song, Cai, Han
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.25180
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908570714374144
author He, Wenkun
Gu, Yuchao
Chen, Junyu
Zou, Dongyun
Lin, Yujun
Zhang, Zhekai
Xi, Haocheng
Li, Muyang
Zhu, Ligeng
Yu, Jincheng
Chen, Junsong
Xie, Enze
Han, Song
Cai, Han
author_facet He, Wenkun
Gu, Yuchao
Chen, Junyu
Zou, Dongyun
Lin, Yujun
Zhang, Zhekai
Xi, Haocheng
Li, Muyang
Zhu, Ligeng
Yu, Jincheng
Chen, Junsong
Xie, Enze
Han, Song
Cai, Han
contents Existing text-to-image diffusion models excel at generating high-quality images, but face significant efficiency challenges when scaled to high resolutions, like 4K image generation. While previous research accelerates diffusion models in various aspects, it seldom handles the inherent redundancy within the latent space. To bridge this gap, this paper introduces DC-Gen, a general framework that accelerates text-to-image diffusion models by leveraging a deeply compressed latent space. Rather than a costly training-from-scratch approach, DC-Gen uses an efficient post-training pipeline to preserve the quality of the base model. A key challenge in this paradigm is the representation gap between the base model's latent space and a deeply compressed latent space, which can lead to instability during direct fine-tuning. To overcome this, DC-Gen first bridges the representation gap with a lightweight embedding alignment training. Once the latent embeddings are aligned, only a small amount of LoRA fine-tuning is needed to unlock the base model's inherent generation quality. We verify DC-Gen's effectiveness on SANA and FLUX.1-Krea. The resulting DC-Gen-SANA and DC-Gen-FLUX models achieve quality comparable to their base models but with a significant speedup. Specifically, DC-Gen-FLUX reduces the latency of 4K image generation by 53x on the NVIDIA H100 GPU. When combined with NVFP4 SVDQuant, DC-Gen-FLUX generates a 4K image in just 3.5 seconds on a single NVIDIA 5090 GPU, achieving a total latency reduction of 138x compared to the base FLUX.1-Krea model. Code: https://github.com/dc-ai-projects/DC-Gen.
format Preprint
id arxiv_https___arxiv_org_abs_2509_25180
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
He, Wenkun
Gu, Yuchao
Chen, Junyu
Zou, Dongyun
Lin, Yujun
Zhang, Zhekai
Xi, Haocheng
Li, Muyang
Zhu, Ligeng
Yu, Jincheng
Chen, Junsong
Xie, Enze
Han, Song
Cai, Han
Computer Vision and Pattern Recognition
Artificial Intelligence
Existing text-to-image diffusion models excel at generating high-quality images, but face significant efficiency challenges when scaled to high resolutions, like 4K image generation. While previous research accelerates diffusion models in various aspects, it seldom handles the inherent redundancy within the latent space. To bridge this gap, this paper introduces DC-Gen, a general framework that accelerates text-to-image diffusion models by leveraging a deeply compressed latent space. Rather than a costly training-from-scratch approach, DC-Gen uses an efficient post-training pipeline to preserve the quality of the base model. A key challenge in this paradigm is the representation gap between the base model's latent space and a deeply compressed latent space, which can lead to instability during direct fine-tuning. To overcome this, DC-Gen first bridges the representation gap with a lightweight embedding alignment training. Once the latent embeddings are aligned, only a small amount of LoRA fine-tuning is needed to unlock the base model's inherent generation quality. We verify DC-Gen's effectiveness on SANA and FLUX.1-Krea. The resulting DC-Gen-SANA and DC-Gen-FLUX models achieve quality comparable to their base models but with a significant speedup. Specifically, DC-Gen-FLUX reduces the latency of 4K image generation by 53x on the NVIDIA H100 GPU. When combined with NVFP4 SVDQuant, DC-Gen-FLUX generates a 4K image in just 3.5 seconds on a single NVIDIA 5090 GPU, achieving a total latency reduction of 138x compared to the base FLUX.1-Krea model. Code: https://github.com/dc-ai-projects/DC-Gen.
title DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2509.25180