Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gao, Yu, Gong, Lixue, Guo, Qiushan, Hou, Xiaoxia, Lai, Zhichao, Li, Fanshi, Li, Liang, Lian, Xiaochen, Liao, Chao, Liu, Liyang, Liu, Wei, Shi, Yichun, Sun, Shiqi, Tian, Yu, Tian, Zhi, Wang, Peng, Wang, Rui, Wang, Xuanda, Wang, Xun, Wang, Ye, Wu, Guofeng, Wu, Jie, Xia, Xin, Xiao, Xuefeng, Zhai, Zhonghua, Zhang, Xinyu, Zhang, Qi, Zhang, Yuwei, Zhao, Shijia, Yang, Jianchao, Huang, Weilin
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2504.11346
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913916299247616
author Gao, Yu
Gong, Lixue
Guo, Qiushan
Hou, Xiaoxia
Lai, Zhichao
Li, Fanshi
Li, Liang
Lian, Xiaochen
Liao, Chao
Liu, Liyang
Liu, Wei
Shi, Yichun
Sun, Shiqi
Tian, Yu
Tian, Zhi
Wang, Peng
Wang, Rui
Wang, Xuanda
Wang, Xun
Wang, Ye
Wu, Guofeng
Wu, Jie
Xia, Xin
Xiao, Xuefeng
Zhai, Zhonghua
Zhang, Xinyu
Zhang, Qi
Zhang, Yuwei
Zhao, Shijia
Yang, Jianchao
Huang, Weilin
author_facet Gao, Yu
Gong, Lixue
Guo, Qiushan
Hou, Xiaoxia
Lai, Zhichao
Li, Fanshi
Li, Liang
Lian, Xiaochen
Liao, Chao
Liu, Liyang
Liu, Wei
Shi, Yichun
Sun, Shiqi
Tian, Yu
Tian, Zhi
Wang, Peng
Wang, Rui
Wang, Xuanda
Wang, Xun
Wang, Ye
Wu, Guofeng
Wu, Jie
Xia, Xin
Xiao, Xuefeng
Zhai, Zhonghua
Zhang, Xinyu
Zhang, Qi
Zhang, Yuwei
Zhao, Shijia
Yang, Jianchao
Huang, Weilin
contents We present Seedream 3.0, a high-performance Chinese-English bilingual image generation foundation model. We develop several technical improvements to address existing challenges in Seedream 2.0, including alignment with complicated prompts, fine-grained typography generation, suboptimal visual aesthetics and fidelity, and limited image resolutions. Specifically, the advancements of Seedream 3.0 stem from improvements across the entire pipeline, from data construction to model deployment. At the data stratum, we double the dataset using a defect-aware training paradigm and a dual-axis collaborative data-sampling framework. Furthermore, we adopt several effective techniques such as mixed-resolution training, cross-modality RoPE, representation alignment loss, and resolution-aware timestep sampling in the pre-training phase. During the post-training stage, we utilize diversified aesthetic captions in SFT, and a VLM-based reward model with scaling, thereby achieving outputs that well align with human preferences. Furthermore, Seedream 3.0 pioneers a novel acceleration paradigm. By employing consistent noise expectation and importance-aware timestep sampling, we achieve a 4 to 8 times speedup while maintaining image quality. Seedream 3.0 demonstrates significant improvements over Seedream 2.0: it enhances overall capabilities, in particular for text-rendering in complicated Chinese characters which is important to professional typography generation. In addition, it provides native high-resolution output (up to 2K), allowing it to generate images with high visual quality.
format Preprint
id arxiv_https___arxiv_org_abs_2504_11346
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Seedream 3.0 Technical Report
Gao, Yu
Gong, Lixue
Guo, Qiushan
Hou, Xiaoxia
Lai, Zhichao
Li, Fanshi
Li, Liang
Lian, Xiaochen
Liao, Chao
Liu, Liyang
Liu, Wei
Shi, Yichun
Sun, Shiqi
Tian, Yu
Tian, Zhi
Wang, Peng
Wang, Rui
Wang, Xuanda
Wang, Xun
Wang, Ye
Wu, Guofeng
Wu, Jie
Xia, Xin
Xiao, Xuefeng
Zhai, Zhonghua
Zhang, Xinyu
Zhang, Qi
Zhang, Yuwei
Zhao, Shijia
Yang, Jianchao
Huang, Weilin
Computer Vision and Pattern Recognition
We present Seedream 3.0, a high-performance Chinese-English bilingual image generation foundation model. We develop several technical improvements to address existing challenges in Seedream 2.0, including alignment with complicated prompts, fine-grained typography generation, suboptimal visual aesthetics and fidelity, and limited image resolutions. Specifically, the advancements of Seedream 3.0 stem from improvements across the entire pipeline, from data construction to model deployment. At the data stratum, we double the dataset using a defect-aware training paradigm and a dual-axis collaborative data-sampling framework. Furthermore, we adopt several effective techniques such as mixed-resolution training, cross-modality RoPE, representation alignment loss, and resolution-aware timestep sampling in the pre-training phase. During the post-training stage, we utilize diversified aesthetic captions in SFT, and a VLM-based reward model with scaling, thereby achieving outputs that well align with human preferences. Furthermore, Seedream 3.0 pioneers a novel acceleration paradigm. By employing consistent noise expectation and importance-aware timestep sampling, we achieve a 4 to 8 times speedup while maintaining image quality. Seedream 3.0 demonstrates significant improvements over Seedream 2.0: it enhances overall capabilities, in particular for text-rendering in complicated Chinese characters which is important to professional typography generation. In addition, it provides native high-resolution output (up to 2K), allowing it to generate images with high visual quality.
title Seedream 3.0 Technical Report
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2504.11346