| title | Qwen-Image-VAE-2.0 Technical Report |
|---|---|
| authors | Zekai Zhang, Deqing Li, Kuan Cao, Yujia Wu, Chenfei Wu, Yu Wu, Liang Peng, Hao Meng, Jiahao Li, Jie Zhang, Kaiyuan Gao, Kun Yan, Lihan Jiang, Ningyuan Tang, Shengming Yin, Tianhe Wu, Xiao Xu, Xiaoyue Chen, Yan Shu, Yanran Zhang, Yilei Chen, Yixian Xu, Yuxiang Chen, Zhendong Wang, Zihao Liu, Zikai Zhou, Yiliang Gu, Yi Wang, Xiaoxiao Xu, Lin Qu |
| date | 2026-05-13 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2605.13565 |
| affiliation | Qwen |
| upvotes | 61 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | We present Qwen-Image-VAE-2.0, a suite of high-compression Variational Autoencoders (VAEs) that achieve significant advances in both reconstruction fidelity and diffusability. To address the reconstruction bottlenecks of high compression, we adopt an improved architecture featuring Global Skip Connections (GSC) and expanded latent channels. Moreover, we scale training to billions of images and incorporate a synthetic rendering engine to improve performance in text-rich scenarios. To tackle the convergence challenges of high-dimensional latent space, we implement an enhanced semantic alignment strategy to make the latent space highly amenable to diffusion modeling. To optimize computational efficiency, we leverage an asymmetric and attention-free encoder-decoder backbone to minimize encoding overhead. We present a comprehensive evaluation of Qwen-Image-VAE-2.0 on public reconstruction benchmarks. To evaluate performance in text-rich scenarios, we propose OmniDoc-TokenBench, a new benchmark comprising a diverse collection of real-world documents coupled with specialized OCR-based evaluation metrics. Qwen-Image-VAE-2.0 achieves state-of-the-art reconstruction performance, demonstrating exceptional capabilities in both general domains and text-rich scenarios at high compression ratio. Furthermore, downstream DiT experiments reveal our models possess superior diffusability, significantly accelerating convergence compared to existing high-compression baselines. These establish Qwen-Image-VAE-2.0 as a leading model with high compression, superior reconstruction, and exceptional diffusability. |
cite
@misc{zhang2026qwen,
title={Qwen-Image-VAE-2.0 Technical Report},
author={Zekai Zhang and Deqing Li and Kuan Cao and Yujia Wu and Chenfei Wu and Yu Wu and Liang Peng and Hao Meng and Jiahao Li and Jie Zhang and Kaiyuan Gao and Kun Yan and Lihan Jiang and Ningyuan Tang and Shengming Yin and Tianhe Wu and Xiao Xu and Xiaoyue Chen and Yan Shu and Yanran Zhang and Yilei Chen and Yixian Xu and Yuxiang Chen and Zhendong Wang and Zihao Liu and Zikai Zhou and Yiliang Gu and Yi Wang and Xiaoxiao Xu and Lin Qu},
year={2026},
eprint={2605.13565},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2605.13565}
}