Qwen-Image-VAE-2.0 Technical Report
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916009669033984 |
|---|---|
| author | Zhang, Zekai Li, Deqing Cao, Kuan Wu, Yujia Wu, Chenfei Wu, Yu Peng, Liang Meng, Hao Li, Jiahao Zhang, Jie Gao, Kaiyuan Yan, Kun Jiang, Lihan Tang, Ningyuan Yin, Shengming Wu, Tianhe Xu, Xiao Chen, Xiaoyue Shu, Yan Zhang, Yanran Chen, Yilei Xu, Yixian Chen, Yuxiang Wang, Zhendong Liu, Zihao Zhou, Zikai Gu, Yiliang Wang, Yi Xu, Xiaoxiao Qu, Lin |
| author_facet | Zhang, Zekai Li, Deqing Cao, Kuan Wu, Yujia Wu, Chenfei Wu, Yu Peng, Liang Meng, Hao Li, Jiahao Zhang, Jie Gao, Kaiyuan Yan, Kun Jiang, Lihan Tang, Ningyuan Yin, Shengming Wu, Tianhe Xu, Xiao Chen, Xiaoyue Shu, Yan Zhang, Yanran Chen, Yilei Xu, Yixian Chen, Yuxiang Wang, Zhendong Liu, Zihao Zhou, Zikai Gu, Yiliang Wang, Yi Xu, Xiaoxiao Qu, Lin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_13565 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Qwen-Image-VAE-2.0 Technical Report Zhang, Zekai Li, Deqing Cao, Kuan Wu, Yujia Wu, Chenfei Wu, Yu Peng, Liang Meng, Hao Li, Jiahao Zhang, Jie Gao, Kaiyuan Yan, Kun Jiang, Lihan Tang, Ningyuan Yin, Shengming Wu, Tianhe Xu, Xiao Chen, Xiaoyue Shu, Yan Zhang, Yanran Chen, Yilei Xu, Yixian Chen, Yuxiang Wang, Zhendong Liu, Zihao Zhou, Zikai Gu, Yiliang Wang, Yi Xu, Xiaoxiao Qu, Lin Computer Vision and Pattern Recognition 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. |
| title | Qwen-Image-VAE-2.0 Technical Report |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.13565 |