arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.07584cs.CV
收藏

LongCat-Image 技术报告

LongCat-Image Technical Report

Meituan LongCat Team(美团LongCat团队)

Meituan LongCat Team, Hanghang Ma, Haoxian Tan, Jiale Huang, Junqiang Wu, Jun-Yan He, Lishuai Gao, Songlin Xiao, Xiaoming Wei, Xiaoqi Ma, Xunliang Cai, Yayong Guan, Jie Hu

AI总结:

LongCat-Image通过双语开源模型提升多语言图像生成与编辑能力,实现高效部署与高质量输出。

摘要:

我们介绍了LongCat-Image,一种开创性的开源且双语(中英)基础模型,用于图像生成,旨在解决当前领先模型在多语言文本渲染、照片级真实感、部署效率和开发者可及性方面存在的核心挑战。1)我们通过在预训练、中训练和SFT阶段采用严格的数据筛选策略,辅以RL阶段协调使用筛选奖励模型,使模型成为新的状态-of-the-art(SOTA),在文本渲染能力和照片级真实感方面表现优异,并显著提升审美质量。2)值得注意的是,它为中文字符渲染设定了新的行业标准。通过支持甚至复杂罕见的字符,它在覆盖范围上优于主要的开源和商业解决方案,同时在准确性上也取得优越成绩。3)该模型通过其紧凑的设计实现了显著的效率。核心扩散模型仅有6B参数,比领域内常见的近20B或更大的混合专家(MoE)架构要小得多。这确保了极低的VRAM使用和快速推理,显著降低了部署成本。除了生成外,LongCat-Image在图像编辑方面也表现出色,在标准基准上实现了SOTA结果,其编辑一致性优于其他开源作品。4)为了全面赋能社区,我们建立了迄今为止最全面的开源生态系统。我们不仅发布多种文本到图像和图像编辑的模型版本,包括中训练和后训练阶段的检查点,还发布了完整的训练流程工具链。我们相信LongCat-Image的开放性将为开发者和研究人员提供坚实支持,推动视觉内容创作的前沿。

英文摘要:

We introduce LongCat-Image, a pioneering open-source and bilingual (Chinese-English) foundation model for image generation, designed to address core challenges in multilingual text rendering, photorealism, deployment efficiency, and developer accessibility prevalent in current leading models. 1) We achieve this through rigorous data curation strategies across the pre-training, mid-training, and SFT stages, complemented by the coordinated use of curated reward models during the RL phase. This strategy establishes the model as a new state-of-the-art (SOTA), delivering superior text-rendering capabilities and remarkable photorealism, and significantly enhancing aesthetic quality. 2) Notably, it sets a new industry standard for Chinese character rendering. By supporting even complex and rare characters, it outperforms both major open-source and commercial solutions in coverage, while also achieving superior accuracy. 3) The model achieves remarkable efficiency through its compact design. With a core diffusion model of only 6B parameters, it is significantly smaller than the nearly 20B or larger Mixture-of-Experts (MoE) architectures common in the field. This ensures minimal VRAM usage and rapid inference, significantly reducing deployment costs. Beyond generation, LongCat-Image also excels in image editing, achieving SOTA results on standard benchmarks with superior editing consistency compared to other open-source works. 4) To fully empower the community, we have established the most comprehensive open-source ecosystem to date. We are releasing not only multiple model versions for text-to-image and image editing, including checkpoints after mid-training and post-training stages, but also the entire toolchain of training procedure. We believe that the openness of LongCat-Image will provide robust support for developers and researchers, pushing the frontiers of visual content creation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑