Cover Image

Wan-Image: Pushing the Boundaries of Generative Visual Intelligence

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Mao, Chaojie, Xie, Chen-Wei, Zhong, Chongyang, Deng, Haoyou, Zhao, Jiaxing, Xiao, Jie, Xing, Jinbo, Zhang, Jingfeng, Zhou, Jingren, Zhang, Jingyi, Dan, Jun, Zhu, Kai, Zhao, Kang, Yan, Keyu, Chen, Minghui, Li, Pandeng, Chen, Shuangle, Shen, Tong, Liu, Yu, Jiang, Yue, Pan, Yulin, Tuo, Yuxiang, Jiang, Zeyinzi, Han, Zhen, Wang, Ang, Zhang, Bang, Ai, Baole, Wen, Bin, Feng, Boang, Yu, Feiwu, Wang, Gang, Zhao, Haiming, Kang, He, Xiang, Jianjing, Zeng, Jianyuan, Wang, Jinkai, Zhou, Junjie, Sun, Ke, Wu, Linqian, Gong, Pei, Wu, Pingyu, Wu, Ruiwen, Su, Tongtong, Zhou, Wenmeng, Shen, Wenting, Yu, Wenyuan, Xu, Xianjun, Huang, Xiaoming, Shen, Xiejie, Xu, Xin, Kou, Yan, Lv, Yangyu, Zhai, Yifan, Huang, Yitong, Zheng, Yun, Hong, Yuntao, Zhang, Zhe, Zhang, Zhicheng
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866915954266472448
author	Mao, Chaojie Xie, Chen-Wei Zhong, Chongyang Deng, Haoyou Zhao, Jiaxing Xiao, Jie Xing, Jinbo Zhang, Jingfeng Zhou, Jingren Zhang, Jingyi Dan, Jun Zhu, Kai Zhao, Kang Yan, Keyu Chen, Minghui Li, Pandeng Chen, Shuangle Shen, Tong Liu, Yu Jiang, Yue Pan, Yulin Tuo, Yuxiang Jiang, Zeyinzi Han, Zhen Wang, Ang Zhang, Bang Ai, Baole Wen, Bin Feng, Boang Yu, Feiwu Wang, Gang Zhao, Haiming Kang, He Xiang, Jianjing Zeng, Jianyuan Wang, Jinkai Zhou, Junjie Sun, Ke Wu, Linqian Gong, Pei Wu, Pingyu Wu, Ruiwen Su, Tongtong Zhou, Wenmeng Shen, Wenting Yu, Wenyuan Xu, Xianjun Huang, Xiaoming Shen, Xiejie Xu, Xin Kou, Yan Lv, Yangyu Zhai, Yifan Huang, Yitong Zheng, Yun Hong, Yuntao Zhang, Zhe Zhang, Zhicheng
author_facet	Mao, Chaojie Xie, Chen-Wei Zhong, Chongyang Deng, Haoyou Zhao, Jiaxing Xiao, Jie Xing, Jinbo Zhang, Jingfeng Zhou, Jingren Zhang, Jingyi Dan, Jun Zhu, Kai Zhao, Kang Yan, Keyu Chen, Minghui Li, Pandeng Chen, Shuangle Shen, Tong Liu, Yu Jiang, Yue Pan, Yulin Tuo, Yuxiang Jiang, Zeyinzi Han, Zhen Wang, Ang Zhang, Bang Ai, Baole Wen, Bin Feng, Boang Yu, Feiwu Wang, Gang Zhao, Haiming Kang, He Xiang, Jianjing Zeng, Jianyuan Wang, Jinkai Zhou, Junjie Sun, Ke Wu, Linqian Gong, Pei Wu, Pingyu Wu, Ruiwen Su, Tongtong Zhou, Wenmeng Shen, Wenting Yu, Wenyuan Xu, Xianjun Huang, Xiaoming Shen, Xiejie Xu, Xin Kou, Yan Lv, Yangyu Zhai, Yifan Huang, Yitong Zheng, Yun Hong, Yuntao Zhang, Zhe Zhang, Zhicheng
contents	We present Wan-Image, a unified visual generation system explicitly engineered to paradigm-shift image generation models from casual synthesizers into professional-grade productivity tools. While contemporary diffusion models excel at aesthetic generation, they frequently encounter critical bottlenecks in rigorous design workflows that demand absolute controllability, complex typography rendering, and strict identity preservation. To address these challenges, Wan-Image features a natively unified multi-modal architecture by synergizing the cognitive capabilities of large language models with the high-fidelity pixel synthesis of diffusion transformers, which seamlessly translates highly nuanced user intents into precise visual outputs. It is fundamentally powered by large-scale multi-modal data scaling, a systematic fine-grained annotation engine, and curated reinforcement learning data to surpass basic instruction following and unlock expert-level professional capabilities. These include ultra-long complex text rendering, hyper-diverse portrait generation, palette-guided generation, multi-subject identity preservation, coherent sequential visual generation, precise multi-modal interactive editing, native alpha-channel generation, and high-efficiency 4K synthesis. Across diverse human evaluations, Wan-Image exceeds Seedream 5.0 Lite and GPT Image 1.5 in overall performance, reaching parity with Nano Banana Pro in challenging tasks. Ultimately, Wan-Image revolutionizes visual content creation across e-commerce, entertainment, education, and personal productivity, redefining the boundaries of professional visual synthesis.
format	Preprint
id	arxiv_https___arxiv_org_abs_2604_19858
institution	arXiv
publishDate	2026
record_format	arxiv
spellingShingle	Wan-Image: Pushing the Boundaries of Generative Visual Intelligence Mao, Chaojie Xie, Chen-Wei Zhong, Chongyang Deng, Haoyou Zhao, Jiaxing Xiao, Jie Xing, Jinbo Zhang, Jingfeng Zhou, Jingren Zhang, Jingyi Dan, Jun Zhu, Kai Zhao, Kang Yan, Keyu Chen, Minghui Li, Pandeng Chen, Shuangle Shen, Tong Liu, Yu Jiang, Yue Pan, Yulin Tuo, Yuxiang Jiang, Zeyinzi Han, Zhen Wang, Ang Zhang, Bang Ai, Baole Wen, Bin Feng, Boang Yu, Feiwu Wang, Gang Zhao, Haiming Kang, He Xiang, Jianjing Zeng, Jianyuan Wang, Jinkai Zhou, Junjie Sun, Ke Wu, Linqian Gong, Pei Wu, Pingyu Wu, Ruiwen Su, Tongtong Zhou, Wenmeng Shen, Wenting Yu, Wenyuan Xu, Xianjun Huang, Xiaoming Shen, Xiejie Xu, Xin Kou, Yan Lv, Yangyu Zhai, Yifan Huang, Yitong Zheng, Yun Hong, Yuntao Zhang, Zhe Zhang, Zhicheng Computer Vision and Pattern Recognition We present Wan-Image, a unified visual generation system explicitly engineered to paradigm-shift image generation models from casual synthesizers into professional-grade productivity tools. While contemporary diffusion models excel at aesthetic generation, they frequently encounter critical bottlenecks in rigorous design workflows that demand absolute controllability, complex typography rendering, and strict identity preservation. To address these challenges, Wan-Image features a natively unified multi-modal architecture by synergizing the cognitive capabilities of large language models with the high-fidelity pixel synthesis of diffusion transformers, which seamlessly translates highly nuanced user intents into precise visual outputs. It is fundamentally powered by large-scale multi-modal data scaling, a systematic fine-grained annotation engine, and curated reinforcement learning data to surpass basic instruction following and unlock expert-level professional capabilities. These include ultra-long complex text rendering, hyper-diverse portrait generation, palette-guided generation, multi-subject identity preservation, coherent sequential visual generation, precise multi-modal interactive editing, native alpha-channel generation, and high-efficiency 4K synthesis. Across diverse human evaluations, Wan-Image exceeds Seedream 5.0 Lite and GPT Image 1.5 in overall performance, reaching parity with Nano Banana Pro in challenging tasks. Ultimately, Wan-Image revolutionizes visual content creation across e-commerce, entertainment, education, and personal productivity, redefining the boundaries of professional visual synthesis.
title	Wan-Image: Pushing the Boundaries of Generative Visual Intelligence
topic	Computer Vision and Pattern Recognition
url	https://arxiv.org/abs/2604.19858