Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| 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 |