LongCat-Image Technical Report
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911308265291776 |
|---|---|
| author | Meituan LongCat Team Ma, Hanghang Tan, Haoxian Huang, Jiale Wu, Junqiang He, Jun-Yan Gao, Lishuai Xiao, Songlin Wei, Xiaoming Ma, Xiaoqi Cai, Xunliang Guan, Yayong Hu, Jie |
| author_facet | Meituan LongCat Team Ma, Hanghang Tan, Haoxian Huang, Jiale Wu, Junqiang He, Jun-Yan Gao, Lishuai Xiao, Songlin Wei, Xiaoming Ma, Xiaoqi Cai, Xunliang Guan, Yayong Hu, Jie |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_07584 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LongCat-Image Technical Report Meituan LongCat Team Ma, Hanghang Tan, Haoxian Huang, Jiale Wu, Junqiang He, Jun-Yan Gao, Lishuai Xiao, Songlin Wei, Xiaoming Ma, Xiaoqi Cai, Xunliang Guan, Yayong Hu, Jie Computer Vision and Pattern Recognition 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. |
| title | LongCat-Image Technical Report |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.07584 |