---
title: "Qwen-Image Technical Report — paper by Wu et al. (2025)"
description: "The Qwen Team presents Qwen-Image, a diffusion foundation model that targets both. 102 references, cited by 79 papers here."
authors: ["Chenfei Wu", "Jiahao Li", "Jingren Zhou", "Junyang Lin", "Kaiyuan Gao", "Kun Yan", "Sheng-ming Yin", "Shuai Bai", "Xiao Xu", "Yilei Chen", "Yuxiang Chen", "Zecheng Tang", "Zekai Zhang", "Zhengyi Wang", "An Yang", "Bowen Yu", "Chen Cheng", "Dayiheng Liu", "Deqing Li", "Hang Zhang", "Hao Meng", "Hu Wei", "Jingyuan Ni", "Kai Chen", "Kuan Cao", "Liang Peng", "Lin Qu", "Minggang Wu", "Peng Wang", "Shuting Yu", "Tingkun Wen", "Wensen Feng", "Xiaoxiao Xu", "Yi Wang", "Yichang Zhang", "Yongqiang Zhu", "Yujia Wu", "Yuxuan Cai", "Zenan Liu"]
year: 2025
venue: "arXiv:2508.02324"
source: "https://arxiv.org/abs/2508.02324"
doi: "10.48550/arxiv.2508.02324"
arxiv: "2508.02324"
licence: "arXiv — non-exclusive licence to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/wu-2025-qwen-image-technical-report/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wu-2025-qwen-image-technical-report/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/) / Qwen-Image Technical Report

# Qwen-Image Technical Report

**Authors:** [Chenfei Wu](https://md.research.elamur.ai/free/en/authors/chenfei-wu/), [Jiahao Li](https://md.research.elamur.ai/free/en/authors/jiahao-li/), [Jingren Zhou](https://md.research.elamur.ai/free/en/authors/jingren-zhou/), [Junyang Lin](https://md.research.elamur.ai/free/en/authors/junyang-lin/), Kaiyuan Gao, Kun Yan, Sheng-ming Yin, [Shuai Bai](https://md.research.elamur.ai/free/en/authors/shuai-bai/), Xiao Xu, Yilei Chen, Yuxiang Chen, [Zecheng Tang](https://md.research.elamur.ai/free/en/authors/zecheng-tang/), Zekai Zhang, Zhengyi Wang, [An Yang](https://md.research.elamur.ai/free/en/authors/an-yang/), [Bowen Yu](https://md.research.elamur.ai/free/en/authors/bowen-yu/), Chen Cheng, [Dayiheng Liu](https://md.research.elamur.ai/free/en/authors/dayiheng-liu/), Deqing Li, [Hang Zhang](https://md.research.elamur.ai/free/en/authors/hang-zhang/), Hao Meng, Hu Wei, Jingyuan Ni, [Kai Chen](https://md.research.elamur.ai/free/en/authors/kai-chen/), Kuan Cao, Liang Peng, Lin Qu, Minggang Wu, [Peng Wang](https://md.research.elamur.ai/free/en/authors/peng-wang/), Shuting Yu, Tingkun Wen, Wensen Feng, Xiaoxiao Xu, [Yi Wang](https://md.research.elamur.ai/free/en/authors/yi-wang/), Yichang Zhang, Yongqiang Zhu, Yujia Wu, Yuxuan Cai and Zenan Liu · **Year:** 2025 · **Venue:** arXiv:2508.02324 · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2508.02324) · [PDF](https://arxiv.org/pdf/2508.02324) · [DOI 10.48550/arxiv.2508.02324](https://doi.org/10.48550/arxiv.2508.02324) · [arXiv 2508.02324](https://arxiv.org/abs/2508.02324) · [OpenAlex](https://openalex.org/W6966874861)

**Citations:** 3 citations (OpenAlex, 2026-10-14) · 79 in our library, of the 141,840 papers whose bibliographies we read

## Summary
Even leading commercial image generators, such as GPT Image 1 and Seedream 3.0, struggle with two tasks: rendering complex text inside images, especially multi-line or Chinese text, and editing images while keeping unedited content unchanged. The Qwen Team presents Qwen-Image, a diffusion foundation model that targets both. For text rendering, the team built a data pipeline covering collection, filtering, annotation, synthesis and balancing. Training follows a curriculum that starts with images without text and moves to simple text, then to paragraph-level, layout-aware descriptions. For editing, the model trains jointly on T2I, TI2I and I2I reconstruction. Each source image is encoded twice: Qwen2.5-VL supplies semantic features and a VAE supplies low-level detail. Both condition an MMDiT backbone. Qwen-Image reaches state-of-the-art results on general generation and editing benchmarks and leads by a wide margin on Chinese text rendering. The authors argue it can also handle understanding tasks through editing, such as depth estimation. The model is released openly, giving researchers a strong base for multilingual, text-heavy image generation.

## Key points
- **Architecture:** a double-stream MMDiT conditioned by a frozen Qwen2.5-VL, which uses separate system prompts for text-only and text+image inputs. It uses a video VAE rather than an image VAE and a new positional scheme, MSRoPE, that encodes image and text positions together.
- **Generation benchmarks:** GenEval, DPG and OneIG-Bench.
- **Editing benchmarks:** GEdit, ImgEdit and GSO.
- **Text-rendering benchmarks:** LongText-Bench, ChineseWord and CVTG-2K, where the gains over prior models are largest.
- **Training infrastructure:** a Producer-Consumer setup built on TensorPipe. Producers handle data I/O and VAE encoding, while consumers train the model with Megatron.
- **Understanding tasks:** detection, segmentation, depth estimation, novel view synthesis and super-resolution are framed as editing. Depth results come close to, but do not beat, specialized discriminative models.
- **Availability:** weights and code are on Hugging Face, ModelScope and GitHub (QwenLM/Qwen-Image).

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (2): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 9,085 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 1,282 works

## Cite

Cite as: Chenfei Wu, Jiahao Li, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kun Yan, Sheng-ming Yin, Shuai Bai, Xiao Xu, Yilei Chen, Yuxiang Chen, Zecheng Tang, Zekai Zhang, Zhengyi Wang, An Yang, Bowen Yu, Chen Cheng, Dayiheng Liu, Deqing Li, Hang Zhang, Hao Meng, Hu Wei, Jingyuan Ni, Kai Chen, Kuan Cao, Liang Peng, Lin Qu, Minggang Wu, Peng Wang, Shuting Yu, Tingkun Wen, Wensen Feng, Xiaoxiao Xu, Yi Wang, Yichang Zhang, Yongqiang Zhu, Yujia Wu, Yuxuan Cai and Zenan Liu. 2025. Qwen-Image Technical Report. arXiv:2508.02324.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{wu2025qwen,
  title = {{Qwen-Image Technical Report}},
  author = {Chenfei Wu, Jiahao Li, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kun Yan, Sheng-ming Yin, Shuai Bai, Xiao Xu, Yilei Chen, Yuxiang Chen, Zecheng Tang, Zekai Zhang, Zhengyi Wang, An Yang, Bowen Yu, Chen Cheng, Dayiheng Liu, Deqing Li, Hang Zhang, Hao Meng, Hu Wei, Jingyuan Ni, Kai Chen, Kuan Cao, Liang Peng, Lin Qu, Minggang Wu, Peng Wang, Shuting Yu, Tingkun Wen, Wensen Feng, Xiaoxiao Xu, Yi Wang, Yichang Zhang, Yongqiang Zhu, Yujia Wu, Yuxuan Cai and Zenan Liu},
  year = {2025},
  doi = {10.48550/arxiv.2508.02324},
  eprint = {2508.02324},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2508.02324}
}
```

- [← previous EfficientQAT: Efficient Quantization-Aware Training for Large Language Models](https://md.research.elamur.ai/free/en/papers/chen-2025-efficientqat-efficient-quantization-aware-training/)
- [next → OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models](https://md.research.elamur.ai/free/en/papers/huang-2025-opencoder-open-cookbook-top-tier/)
- [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/)

## References

102 references, 11 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Niket Agarwal, Arslan Ali, Maciej Bala, Yogesh Balaji, Erik Barker, Tiffany Cai, Prithvijit Chattopadhyay, Yongxin Chen, Yin Cui, Yifan Ding, et al. Cosmos world foundation model platform for physical ai. arXiv preprint arXiv:2501.03575, 2025. — [arXiv:2501.03575](https://arxiv.org/abs/2501.03575) [find](https://scholar.google.com/scholar?q=Niket+Agarwal%2C+Arslan+Ali%2C+Maciej+Bala%2C+Yogesh+Balaji%2C+Erik+Barker%2C+Tiffany+Cai%2C+Prithvijit+Chattopadhyay%2C+Yongxin+Chen%2C+Yin+Cui%2C+Yifan+Ding%2C+et+al%2E+Cosmos+world+foundation+model+platform+for+physical)
2. Shuai Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Sibo Song, Kai Dang, Peng Wang, Shijie Wang, Jun Tang, Humen Zhong, Yuanzhi Zhu, Mingkun Yang, Zhaohai Li, Jianqiang Wan, Pengfei Wang, Wei Ding, Zheren Fu, Yiheng Xu, Jiabo Ye, Xi Zhang, Tianbao Xie, Zesen Cheng, Hang Zhang, Zhibo Yang, Ha… — [Qwen2.5-VL Technical Report](https://md.research.elamur.ai/free/en/papers/bai-2025-qwen2-5-vl-technical/)
3. BlackForest. Flux. [https://github.com/black-forest-labs/flux](https://github.com/black-forest-labs/flux), 2024. [↗](https://github.com/black-forest-labs/flux)
4. Aleksei Bochkovskii, Amaël Delaunoy, Hugo Germain, Marcel Santos, Yichao Zhou, Stephan R Richter, and Vladlen Koltun. Depth pro: Sharp monocular metric depth in less than a second. arXiv preprint arXiv:2410.02073, 2024. [find](https://scholar.google.com/scholar?q=Aleksei+Bochkovskii%2C+Ama%C3%ABl+Delaunoy%2C+Hugo+Germain%2C+Marcel+Santos%2C+Yichao+Zhou%2C+Stephan+R+Richter%2C+and+Vladlen+Koltun%2E+Depth+pro%3A+Sharp+monocular+metric+depth+in+less+than+a+second%2E+arXiv+preprint+arXi)
5. Tim Brooks, Aleksander Holynski, and Alexei A Efros. Instructpix2pix: Learning to follow image editing instructions. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp. 18392–18402, 2023. [find](https://scholar.google.com/scholar?q=Tim+Brooks%2C+Aleksander+Holynski%2C+and+Alexei+A+Efros%2E+Instructpix2pix%3A+Learning+to+follow+image+editing+instructions%2E+In+Proceedings+of+the+IEEE%2FCVF+conference+on+computer+vision+and+pattern+recognitio)
6. Qi Cai, Jingwen Chen, Yang Chen, Yehao Li, Fuchen Long, Yingwei Pan, Zhaofan Qiu, Yiheng Zhang, Fengbin Gao, Peihan Xu, et al. Hidream-i1: A high-efficient image generative foundation model with sparse diffusion transformer. arXiv preprint arXiv:2505.22705, 2025. — [arXiv:2505.22705](https://arxiv.org/abs/2505.22705) [find](https://scholar.google.com/scholar?q=Qi+Cai%2C+Jingwen+Chen%2C+Yang+Chen%2C+Yehao+Li%2C+Fuchen+Long%2C+Yingwei+Pan%2C+Zhaofan+Qiu%2C+Yiheng+Zhang%2C+Fengbin+Gao%2C+Peihan+Xu%2C+et+al%2E+Hidream%2Di1%3A+A+high%2Defficient+image+generative+foundation+model+with+spars)
7. Jingjing Chang, Yixiao Fang, Peng Xing, Shuhan Wu, Wei Cheng, Rui Wang, Xianfang Zeng, Gang Yu, and Hai-Bao Chen. Oneig-bench: Omni-dimensional nuanced evaluation for image generation. arXiv preprint arXiv:2506.07977, 2025. — [arXiv:2506.07977](https://arxiv.org/abs/2506.07977) [find](https://scholar.google.com/scholar?q=Jingjing+Chang%2C+Yixiao+Fang%2C+Peng+Xing%2C+Shuhan+Wu%2C+Wei+Cheng%2C+Rui+Wang%2C+Xianfang+Zeng%2C+Gang+Yu%2C+and+Hai%2DBao+Chen%2E+Oneig%2Dbench%3A+Omni%2Ddimensional+nuanced+evaluation+for+image+generation%2E+arXiv+preprint+)
8. Jingye Chen, Yupan Huang, Tengchao Lv, Lei Cui, Qifeng Chen, and Furu Wei. Textdiffuser-2: Unleashing the power of language models for text rendering. In European Conference on Computer Vision, pp. 386–402. Springer, 2024a. [find](https://scholar.google.com/scholar?q=Jingye+Chen%2C+Yupan+Huang%2C+Tengchao+Lv%2C+Lei+Cui%2C+Qifeng+Chen%2C+and+Furu+Wei%2E+Textdiffuser%2D2%3A+Unleashing+the+power+of+language+models+for+text+rendering%2E+In+European+Conference+on+Computer+Vision%2C+pp%2E+38)
9. Jiuhai Chen, Zhiyang Xu, Xichen Pan, Yushi Hu, Can Qin, Tom Goldstein, Lifu Huang, Tianyi Zhou, Saining Xie, Silvio Savarese, et al. Blip3-o: A family of fully open unified multimodal models-architecture, training and dataset. arXiv preprint arXiv:2505.09568, 2025a. — [arXiv:2505.09568](https://arxiv.org/abs/2505.09568) [find](https://scholar.google.com/scholar?q=Jiuhai+Chen%2C+Zhiyang+Xu%2C+Xichen+Pan%2C+Yushi+Hu%2C+Can+Qin%2C+Tom+Goldstein%2C+Lifu+Huang%2C+Tianyi+Zhou%2C+Saining+Xie%2C+Silvio+Savarese%2C+et+al%2E+Blip3%2Do%3A+A+family+of+fully+open+unified+multimodal+models%2Darchitect)
10. Junsong Chen, Chongjian Ge, Enze Xie, Yue Wu, Lewei Yao, Xiaozhe Ren, Zhongdao Wang, Ping Luo, Huchuan Lu, and Zhenguo Li. Pixart-σ: Weak-to-strong training of diffusion transformer for 4k text-to-image generation. In European Conference on Computer Vision, pp. 74–91. Springer, 2024b. [find](https://scholar.google.com/scholar?q=Junsong+Chen%2C+Chongjian+Ge%2C+Enze+Xie%2C+Yue+Wu%2C+Lewei+Yao%2C+Xiaozhe+Ren%2C+Zhongdao+Wang%2C+Ping+Luo%2C+Huchuan+Lu%2C+and+Zhenguo+Li%2E+Pixart%2D%CF%83%3A+Weak%2Dto%2Dstrong+training+of+diffusion+transformer+for+4k+text%2Dto%2Dima)
11. Junsong Chen, Jincheng Yu, Chongjian Ge, Lewei Yao, Enze Xie, Zhongdao Wang, James T Kwok, Ping Luo, Huchuan Lu, and Zhenguo Li. Pixart-α: Fast training of diffusion transformer for photorealistic text-to-image synthesis. In ICLR, 2024c. [find](https://scholar.google.com/scholar?q=Junsong+Chen%2C+Jincheng+Yu%2C+Chongjian+Ge%2C+Lewei+Yao%2C+Enze+Xie%2C+Zhongdao+Wang%2C+James+T+Kwok%2C+Ping+Luo%2C+Huchuan+Lu%2C+and+Zhenguo+Li%2E+Pixart%2D%CE%B1%3A+Fast+training+of+diffusion+transformer+for+photorealistic+tex)
12. Xiaokang Chen, Zhiyu Wu, Xingchao Liu, Zizheng Pan, Wen Liu, Zhenda Xie, Xingkai Yu, and Chong Ruan. [Janus-pro: Unified multimodal understanding and generation with data and model scaling](https://md.research.elamur.ai/free/en/papers/chen-2025-janus-pro-unified-multimodal/). arXiv preprint arXiv:2501.17811, 2025b.
13. Zhennan Chen, Yajie Li, Haofan Wang, Zhibo Chen, Zhengkai Jiang, Jun Li, Qian Wang, Jian Yang, and Ying Tai. Region-aware text-to-image generation via hard binding and soft refinement. arXiv preprint arXiv:2411.06558, 2024d. — [arXiv:2411.06558](https://arxiv.org/abs/2411.06558) [find](https://scholar.google.com/scholar?q=Zhennan+Chen%2C+Yajie+Li%2C+Haofan+Wang%2C+Zhibo+Chen%2C+Zhengkai+Jiang%2C+Jun+Li%2C+Qian+Wang%2C+Jian+Yang%2C+and+Ying+Tai%2E+Region%2Daware+text%2Dto%2Dimage+generation+via+hard+binding+and+soft+refinement%2E+arXiv+preprint+)
14. Angela Dai, Angel X Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, and Matthias Nießner. Scannet: Richly-annotated 3d reconstructions of indoor scenes. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5828–5839, 2017. [find](https://scholar.google.com/scholar?q=Angela+Dai%2C+Angel+X+Chang%2C+Manolis+Savva%2C+Maciej+Halber%2C+Thomas+Funkhouser%2C+and+Matthias+Nie%C3%9Fner%2E+Scannet%3A+Richly%2Dannotated+3d+reconstructions+of+indoor+scenes%2E+In+Proceedings+of+the+IEEE+conference+o)
15. Google DeepMind. Gemini 2.0. [https://gemini.google.com/](https://gemini.google.com/), 2025. [↗](https://gemini.google.com/)
16. Chaorui Deng, Deyao Zhu, Kunchang Li, Chenhui Gou, Feng Li, Zeyu Wang, Shu Zhong, Weihao Yu, Xiaonan Nie, Ziang Song, et al. Emerging properties in unified multimodal pretraining. arXiv preprint arXiv:2505.14683, 2025. — [arXiv:2505.14683](https://arxiv.org/abs/2505.14683) [find](https://scholar.google.com/scholar?q=Chaorui+Deng%2C+Deyao+Zhu%2C+Kunchang+Li%2C+Chenhui+Gou%2C+Feng+Li%2C+Zeyu+Wang%2C+Shu+Zhong%2C+Weihao+Yu%2C+Xiaonan+Nie%2C+Ziang+Song%2C+et+al%2E+Emerging+properties+in+unified+multimodal+pretraining%2E+arXiv+preprint+arXiv)
17. Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In CVPR, 2009. [find](https://scholar.google.com/scholar?q=Jia+Deng%2C+Wei+Dong%2C+Richard+Socher%2C+Li%2DJia+Li%2C+Kai+Li%2C+and+Li+Fei%2DFei%2E+Imagenet%3A+A+large%2Dscale+hierarchical+image+database%2E+In+CVPR%2C+2009%2E)
18. Laura Downs, Anthony Francis, Nate Koenig, Brandon Kinman, Ryan Hickman, Krista Reymann, Thomas B. McHugh, and Vincent Vanhoucke. Google scanned objects: A high-quality dataset of 3d scanned household items, 2022. URL https://arxiv.org/abs/2204.11918. — [arXiv:2204.11918](https://arxiv.org/abs/2204.11918) [↗](https://arxiv.org/abs/2204.11918)
19. Nikai Du, Zhennan Chen, Zhizhou Chen, Shan Gao, Xi Chen, Zhengkai Jiang, Jian Yang, and Ying Tai. Textcrafter: Accurately rendering multiple texts in complex visual scenes. arXiv preprint arXiv:2503.23461, 2025. [find](https://scholar.google.com/scholar?q=Nikai+Du%2C+Zhennan+Chen%2C+Zhizhou+Chen%2C+Shan+Gao%2C+Xi+Chen%2C+Zhengkai+Jiang%2C+Jian+Yang%2C+and+Ying+Tai%2E+Textcrafter%3A+Accurately+rendering+multiple+texts+in+complex+visual+scenes%2E+arXiv+preprint+arXiv%3A2503%2E2)
20. Arpad E. Elo and Sam Sloan. The Rating of Chess Players, Past and Present. Ishi Press, 2008. [find](https://scholar.google.com/scholar?q=Arpad+E%2E+Elo+and+Sam+Sloan%2E+The+Rating+of+Chess+Players%2C+Past+and+Present%2E+Ishi+Press%2C+2008%2E)
21. Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas Müller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, et al. Scaling rectified flow transformers for high-resolution image synthesis. In ICML, 2024. [find](https://scholar.google.com/scholar?q=Patrick+Esser%2C+Sumith+Kulal%2C+Andreas+Blattmann%2C+Rahim+Entezari%2C+Jonas+M%C3%BCller%2C+Harry+Saini%2C+Yam+Levi%2C+Dominik+Lorenz%2C+Axel+Sauer%2C+Frederic+Boesel%2C+et+al%2E+Scaling+rectified+flow+transformers+for+high%2Dre)
22. Xiao Fu, Wei Yin, Mu Hu, Kaixuan Wang, Yuexin Ma, Ping Tan, Shaojie Shen, Dahua Lin, and Xiaoxiao Long. Geowizard: Unleashing the diffusion priors for 3d geometry estimation from a single image. In European Conference on Computer Vision, pp. 241–258. Springer, 2024. [find](https://scholar.google.com/scholar?q=Xiao+Fu%2C+Wei+Yin%2C+Mu+Hu%2C+Kaixuan+Wang%2C+Yuexin+Ma%2C+Ping+Tan%2C+Shaojie+Shen%2C+Dahua+Lin%2C+and+Xiaoxiao+Long%2E+Geowizard%3A+Unleashing+the+diffusion+priors+for+3d+geometry+estimation+from+a+single+image%2E+In+Eu)
23. Yu Gao, Lixue Gong, Qiushan Guo, Xiaoxia Hou, Zhichao Lai, Fanshi Li, Liang Li, Xiaochen Lian, Chao Liao, Liyang Liu, et al. Seedream 3.0 technical report. arXiv preprint arXiv:2504.11346, 2025. — [arXiv:2504.11346](https://arxiv.org/abs/2504.11346) [find](https://scholar.google.com/scholar?q=Yu+Gao%2C+Lixue+Gong%2C+Qiushan+Guo%2C+Xiaoxia+Hou%2C+Zhichao+Lai%2C+Fanshi+Li%2C+Liang+Li%2C+Xiaochen+Lian%2C+Chao+Liao%2C+Liyang+Liu%2C+et+al%2E+Seedream+3%2E0+technical+report%2E+arXiv+preprint+arXiv%3A2504%2E11346%2C+2025%2E+%E2%80%94+%5Bar)
24. Andreas Geiger, Philip Lenz, Christoph Stiller, and Raquel Urtasun. Vision meets robotics: The kitti dataset. The International Journal of Robotics Research, 32(11):1231–1237, 2013. [find](https://scholar.google.com/scholar?q=Andreas+Geiger%2C+Philip+Lenz%2C+Christoph+Stiller%2C+and+Raquel+Urtasun%2E+Vision+meets+robotics%3A+The+kitti+dataset%2E+The+International+Journal+of+Robotics+Research%2C+32%2811%29%3A1231%E2%80%931237%2C+2013%2E)
25. Zigang Geng, Yibing Wang, Yeyao Ma, Chen Li, Yongming Rao, Shuyang Gu, Zhao Zhong, Qinglin Lu, Han Hu, Xiaosong Zhang, Linus, Di Wang, and Jie Jiang. X-omni: Reinforcement learning makes discrete autoregressive image generative models great again. CoRR, abs/2507.22058, 2025. — [arXiv:2507.22058](https://arxiv.org/abs/2507.22058) [find](https://scholar.google.com/scholar?q=Zigang+Geng%2C+Yibing+Wang%2C+Yeyao+Ma%2C+Chen+Li%2C+Yongming+Rao%2C+Shuyang+Gu%2C+Zhao+Zhong%2C+Qinglin+Lu%2C+Han+Hu%2C+Xiaosong+Zhang%2C+Linus%2C+Di+Wang%2C+and+Jie+Jiang%2E+X%2Domni%3A+Reinforcement+learning+makes+discrete+auto)
26. Dhruba Ghosh, Hannaneh Hajishirzi, and Ludwig Schmidt. Geneval: An object-focused framework for evaluating text-to-image alignment. Advances in Neural Information Processing Systems, 36:52132–52152, 2023. [find](https://scholar.google.com/scholar?q=Dhruba+Ghosh%2C+Hannaneh+Hajishirzi%2C+and+Ludwig+Schmidt%2E+Geneval%3A+An+object%2Dfocused+framework+for+evaluating+text%2Dto%2Dimage+alignment%2E+Advances+in+Neural+Information+Processing+Systems%2C+36%3A52132%E2%80%9352152%2C+2)
27. Lixue Gong, Xiaoxia Hou, Fanshi Li, Liang Li, Xiaochen Lian, Fei Liu, Liyang Liu, Wei Liu, Wei Lu, Yichun Shi, et al. Seedream 2.0: A native chinese-english bilingual image generation foundation model. arXiv preprint arXiv:2503.07703, 2025. [find](https://scholar.google.com/scholar?q=Lixue+Gong%2C+Xiaoxia+Hou%2C+Fanshi+Li%2C+Liang+Li%2C+Xiaochen+Lian%2C+Fei+Liu%2C+Liyang+Liu%2C+Wei+Liu%2C+Wei+Lu%2C+Yichun+Shi%2C+et+al%2E+Seedream+2%2E0%3A+A+native+chinese%2Denglish+bilingual+image+generation+foundation+model)
28. Google. Imagen, 2025. URL [https://deepmind.google/models/imagen/](https://deepmind.google/models/imagen/). [↗](https://deepmind.google/models/imagen/)
29. Imagen Team Google. Imagen 3, 2024. [find](https://scholar.google.com/scholar?q=Imagen+Team+Google%2E+Imagen+3%2C+2024%2E)
30. Ming Gui, Johannes Schusterbauer, Ulrich Prestel, Pingchuan Ma, Dmytro Kotovenko, Olga Grebenkova, Stefan Andreas Baumann, Vincent Tao Hu, and Björn Ommer. Depthfm: Fast monocular depth estimation with flow matching. arXiv preprint arXiv:2403.13788, 2024. — [arXiv:2403.13788](https://arxiv.org/abs/2403.13788) [find](https://scholar.google.com/scholar?q=Ming+Gui%2C+Johannes+Schusterbauer%2C+Ulrich+Prestel%2C+Pingchuan+Ma%2C+Dmytro+Kotovenko%2C+Olga+Grebenkova%2C+Stefan+Andreas+Baumann%2C+Vincent+Tao+Hu%2C+and+Bj%C3%B6rn+Ommer%2E+Depthfm%3A+Fast+monocular+depth+estimation+wit)
31. Jian Han, Jinlai Liu, Yi Jiang, Bin Yan, Yuqi Zhang, Zehuan Yuan, Bingyue Peng, and Xiaobing Liu. Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesis. In Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 15733–15744, 2025. [find](https://scholar.google.com/scholar?q=Jian+Han%2C+Jinlai+Liu%2C+Yi+Jiang%2C+Bin+Yan%2C+Yuqi+Zhang%2C+Zehuan+Yuan%2C+Bingyue+Peng%2C+and+Xiaobing+Liu%2E+Infinity%3A+Scaling+bitwise+autoregressive+modeling+for+high%2Dresolution+image+synthesis%2E+In+Proceedings+)
32. Byeongho Heo, Song Park, Dongyoon Han, and Sangdoo Yun. Rotary position embedding for vision transformer. In European Conference on Computer Vision, pp. 289–305. Springer, 2024. [find](https://scholar.google.com/scholar?q=Byeongho+Heo%2C+Song+Park%2C+Dongyoon+Han%2C+and+Sangdoo+Yun%2E+Rotary+position+embedding+for+vision+transformer%2E+In+European+Conference+on+Computer+Vision%2C+pp%2E+289%E2%80%93305%2E+Springer%2C+2024%2E)
33. Jonathan Ho, Ajay Jain, and Pieter Abbeel. Denoising diffusion probabilistic models. Advances in neural information processing systems, 33:6840–6851, 2020. [find](https://scholar.google.com/scholar?q=Jonathan+Ho%2C+Ajay+Jain%2C+and+Pieter+Abbeel%2E+Denoising+diffusion+probabilistic+models%2E+Advances+in+neural+information+processing+systems%2C+33%3A6840%E2%80%936851%2C+2020%2E)
34. Mu Hu, Wei Yin, Chi Zhang, Zhipeng Cai, Xiaoxiao Long, Hao Chen, Kaixuan Wang, Gang Yu, Chunhua Shen, and Shaojie Shen. Metric3d v2: A versatile monocular geometric foundation model for zero-shot metric depth and surface normal estimation. arXiv preprint arXiv:2404.15506, 2024a. — [arXiv:2404.15506](https://arxiv.org/abs/2404.15506) [find](https://scholar.google.com/scholar?q=Mu+Hu%2C+Wei+Yin%2C+Chi+Zhang%2C+Zhipeng+Cai%2C+Xiaoxiao+Long%2C+Hao+Chen%2C+Kaixuan+Wang%2C+Gang+Yu%2C+Chunhua+Shen%2C+and+Shaojie+Shen%2E+Metric3d+v2%3A+A+versatile+monocular+geometric+foundation+model+for+zero%2Dshot+metr)
35. Xiwei Hu, Rui Wang, Yixiao Fang, Bin Fu, Pei Cheng, and Gang Yu. Ella: Equip diffusion models with llm for enhanced semantic alignment. arXiv preprint arXiv:2403.05135, 2024b. — [arXiv:2403.05135](https://arxiv.org/abs/2403.05135) [find](https://scholar.google.com/scholar?q=Xiwei+Hu%2C+Rui+Wang%2C+Yixiao+Fang%2C+Bin+Fu%2C+Pei+Cheng%2C+and+Gang+Yu%2E+Ella%3A+Equip+diffusion+models+with+llm+for+enhanced+semantic+alignment%2E+arXiv+preprint+arXiv%3A2403%2E05135%2C+2024b%2E+%E2%80%94+%5BarXiv%3A2403%2E05135%5D%28htt)
36. Ideogram. Ideogram 3.0, 2025. URL [https://about.ideogram.ai/3.0](https://about.ideogram.ai/3.0). [↗](https://about.ideogram.ai/3.0)
37. Leslie Pack Kaelbling, Michael L Littman, and Andrew W Moore. Reinforcement learning: A survey. Journal of artificial intelligence research, 4:237–285, 1996. [find](https://scholar.google.com/scholar?q=Leslie+Pack+Kaelbling%2C+Michael+L+Littman%2C+and+Andrew+W+Moore%2E+Reinforcement+learning%3A+A+survey%2E+Journal+of+artificial+intelligence+research%2C+4%3A237%E2%80%93285%2C+1996%2E)
38. Bingxin Ke, Anton Obukhov, Shengyu Huang, Nando Metzger, Rodrigo Caye Daudt, and Konrad Schindler. Repurposing diffusion-based image generators for monocular depth estimation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9492–9502, 2024. [find](https://scholar.google.com/scholar?q=Bingxin+Ke%2C+Anton+Obukhov%2C+Shengyu+Huang%2C+Nando+Metzger%2C+Rodrigo+Caye+Daudt%2C+and+Konrad+Schindler%2E+Repurposing+diffusion%2Dbased+image+generators+for+monocular+depth+estimation%2E+In+Proceedings+of+the+IE)
39. Weijie Kong, Qi Tian, Zijian Zhang, Rox Min, Zuozhuo Dai, Jin Zhou, Jiangfeng Xiong, Xin Li, Bo Wu, Jianwei Zhang, et al. [Hunyuanvideo: A systematic framework for large video generative models](https://md.research.elamur.ai/free/en/papers/kong-2024-hunyuanvideo-systematic-framework-large/). arXiv preprint arXiv:2412.03603, 2024.
40. Vijay Anand Korthikanti, Jared Casper, Sangkug Lym, Lawrence McAfee, Michael Andersch, Mohammad Shoeybi, and Bryan Catanzaro. [Reducing activation recomputation in large transformer models](https://md.research.elamur.ai/free/en/papers/korthikanti-2022-reducing-activation-recomputation-large-transformer/). Proceedings of Machine Learning and Systems, 5:341–353, 2023.
41. Black Forest Labs, Stephen Batifol, Andreas Blattmann, Frederic Boesel, Saksham Consul, Cyril Diagne, Tim Dockhorn, Jack English, Zion English, Patrick Esser, et al. Flux. 1 kontext: Flow matching for in-context image generation and editing in latent space. arXiv preprint arXiv:2506.15742, 2025. — [arXiv:2506.15742](https://arxiv.org/abs/2506.15742) [find](https://scholar.google.com/scholar?q=Black+Forest+Labs%2C+Stephen+Batifol%2C+Andreas+Blattmann%2C+Frederic+Boesel%2C+Saksham+Consul%2C+Cyril+Diagne%2C+Tim+Dockhorn%2C+Jack+English%2C+Zion+English%2C+Patrick+Esser%2C+et+al%2E+Flux%2E+1+kontext%3A+Flow+matching+for)
42. Hsin-Ying Lee, Hung-Yu Tseng, and Ming-Hsuan Yang. Exploiting diffusion prior for generalizable dense prediction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7861–7871, 2024. [find](https://scholar.google.com/scholar?q=Hsin%2DYing+Lee%2C+Hung%2DYu+Tseng%2C+and+Ming%2DHsuan+Yang%2E+Exploiting+diffusion+prior+for+generalizable+dense+prediction%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition%2C+)
43. Daiqing Li, Aleks Kamko, Ehsan Akhgari, Ali Sabet, Linmiao Xu, and Suhail Doshi. Playground v2. 5: Three insights towards enhancing aesthetic quality in text-to-image generation. arXiv preprint arXiv:2402.17245, 2024a. — [arXiv:2402.17245](https://arxiv.org/abs/2402.17245) [find](https://scholar.google.com/scholar?q=Daiqing+Li%2C+Aleks+Kamko%2C+Ehsan+Akhgari%2C+Ali+Sabet%2C+Linmiao+Xu%2C+and+Suhail+Doshi%2E+Playground+v2%2E+5%3A+Three+insights+towards+enhancing+aesthetic+quality+in+text%2Dto%2Dimage+generation%2E+arXiv+preprint+arXiv%3A)
44. Zhimin Li, Jianwei Zhang, Qin Lin, Jiangfeng Xiong, Yanxin Long, Xinchi Deng, Yingfang Zhang, Xingchao Liu, Minbin Huang, Zedong Xiao, Dayou Chen, Jiajun He, Jiahao Li, Wenyue Li, Chen Zhang, Rongwei Quan, Jianxiang Lu, Jiabin Huang, Xiaoyan Yuan, Xiaoxiao Zheng, Yixuan Li, Jihong Zhang, Chao Zhang,… [find](https://scholar.google.com/scholar?q=Zhimin+Li%2C+Jianwei+Zhang%2C+Qin+Lin%2C+Jiangfeng+Xiong%2C+Yanxin+Long%2C+Xinchi+Deng%2C+Yingfang+Zhang%2C+Xingchao+Liu%2C+Minbin+Huang%2C+Zedong+Xiao%2C+Dayou+Chen%2C+Jiajun+He%2C+Jiahao+Li%2C+Wenyue+Li%2C+Chen+Zhang%2C+Rongwei+)
45. Jian Liang, Chenfei Wu, Xiaowei Hu, Zhe Gan, Jianfeng Wang, Lijuan Wang, Zicheng Liu, Yuejian Fang, and Nan Duan. Nuwa-infinity: Autoregressive over autoregressive generation for infinite visual synthesis. Advances in Neural Information Processing Systems, 35:15420–15432, 2022. [find](https://scholar.google.com/scholar?q=Jian+Liang%2C+Chenfei+Wu%2C+Xiaowei+Hu%2C+Zhe+Gan%2C+Jianfeng+Wang%2C+Lijuan+Wang%2C+Zicheng+Liu%2C+Yuejian+Fang%2C+and+Nan+Duan%2E+Nuwa%2Dinfinity%3A+Autoregressive+over+autoregressive+generation+for+infinite+visual+synth)
46. Bin Lin, Zongjian Li, Xinhua Cheng, Yuwei Niu, Yang Ye, Xianyi He, Shenghai Yuan, Wangbo Yu, Shaodong Wang, Yunyang Ge, et al. Uniworld-v1: High-resolution semantic encoders for unified visual understanding and generation. arXiv preprint arXiv:2506.03147, 2025. — [arXiv:2506.03147](https://arxiv.org/abs/2506.03147) [find](https://scholar.google.com/scholar?q=Bin+Lin%2C+Zongjian+Li%2C+Xinhua+Cheng%2C+Yuwei+Niu%2C+Yang+Ye%2C+Xianyi+He%2C+Shenghai+Yuan%2C+Wangbo+Yu%2C+Shaodong+Wang%2C+Yunyang+Ge%2C+et+al%2E+Uniworld%2Dv1%3A+High%2Dresolution+semantic+encoders+for+unified+visual+underst)
47. Jie Liu, Gongye Liu, Jiajun Liang, Yangguang Li, Jiaheng Liu, Xintao Wang, Pengfei Wan, Di Zhang, and Wanli Ouyang. Flow-grpo: Training flow matching models via online rl. arXiv preprint arXiv:2505.05470, 2025a. — [arXiv:2505.05470](https://arxiv.org/abs/2505.05470) [find](https://scholar.google.com/scholar?q=Jie+Liu%2C+Gongye+Liu%2C+Jiajun+Liang%2C+Yangguang+Li%2C+Jiaheng+Liu%2C+Xintao+Wang%2C+Pengfei+Wan%2C+Di+Zhang%2C+and+Wanli+Ouyang%2E+Flow%2Dgrpo%3A+Training+flow+matching+models+via+online+rl%2E+arXiv+preprint+arXiv%3A2505%2E05)
48. Ruoshi Liu, Rundi Wu, Basile Van Hoorick, Pavel Tokmakov, Sergey Zakharov, and Carl Vondrick. Zero-1-to-3: Zero-shot one image to 3d object. In Proceedings of the IEEE/CVF international conference on computer vision, pp. 9298–9309, 2023. [find](https://scholar.google.com/scholar?q=Ruoshi+Liu%2C+Rundi+Wu%2C+Basile+Van+Hoorick%2C+Pavel+Tokmakov%2C+Sergey+Zakharov%2C+and+Carl+Vondrick%2E+Zero%2D1%2Dto%2D3%3A+Zero%2Dshot+one+image+to+3d+object%2E+In+Proceedings+of+the+IEEE%2FCVF+international+conference+on+)
49. Shiyu Liu, Yucheng Han, Peng Xing, Fukun Yin, Rui Wang, Wei Cheng, Jiaqi Liao, Yingming Wang, Honghao Fu, Chunrui Han, et al. Step1x-edit: A practical framework for general image editing. arXiv preprint arXiv:2504.17761, 2025b. [find](https://scholar.google.com/scholar?q=Shiyu+Liu%2C+Yucheng+Han%2C+Peng+Xing%2C+Fukun+Yin%2C+Rui+Wang%2C+Wei+Cheng%2C+Jiaqi+Liao%2C+Yingming+Wang%2C+Honghao+Fu%2C+Chunrui+Han%2C+et+al%2E+Step1x%2Dedit%3A+A+practical+framework+for+general+image+editing%2E+arXiv+prepri)
50. Xingchao Liu, Chengyue Gong, and Qiang Liu. [Flow straight and fast: Learning to generate and transfer data with rectified flow](https://md.research.elamur.ai/free/en/papers/liu-2022-flow-straight-fast-learning-generate/). arXiv preprint arXiv:2209.03003, 2022.
51. Yiyang Ma, Xingchao Liu, Xiaokang Chen, Wen Liu, Chengyue Wu, Zhiyu Wu, Zizheng Pan, Zhenda Xie, Haowei Zhang, Xingkai Yu, et al. Janusflow: Harmonizing autoregression and rectified flow for unified multimodal understanding and generation. In Proceedings of the Computer Vision and Pattern Recognitio… [find](https://scholar.google.com/scholar?q=Yiyang+Ma%2C+Xingchao+Liu%2C+Xiaokang+Chen%2C+Wen+Liu%2C+Chengyue+Wu%2C+Zhiyu+Wu%2C+Zizheng+Pan%2C+Zhenda+Xie%2C+Haowei+Zhang%2C+Xingkai+Yu%2C+et+al%2E+Janusflow%3A+Harmonizing+autoregression+and+rectified+flow+for+unified+m)
52. Midjourney. midjourney v7, 2025. URL [https://github.com/midjourney](https://github.com/midjourney). [↗](https://github.com/midjourney)
53. George A. Miller. [Wordnet: a lexical database for english](https://md.research.elamur.ai/free/en/papers/miller-1994-wordnet/). Commun. ACM, 38(11):39–41, November 1995. ISSN 0001-0782. doi: 10.1145/219717.219748. URL https://doi.org/10.1145/219717.219748. [↗](https://doi.org/10.1145/219717.219748)
54. Philipp Moritz, Robert Nishihara, Stephanie Wang, Alexey Tumanov, Richard Liaw, Eric Liang, Melih Elibol, Zongheng Yang, William Paul, Michael I Jordan, et al. Ray: A distributed framework for emerging { AI } applications. In 13th USENIX symposium on operating systems design and implementation (OSDI… [find](https://scholar.google.com/scholar?q=Philipp+Moritz%2C+Robert+Nishihara%2C+Stephanie+Wang%2C+Alexey+Tumanov%2C+Richard+Liaw%2C+Eric+Liang%2C+Melih+Elibol%2C+Zongheng+Yang%2C+William+Paul%2C+Michael+I+Jordan%2C+et+al%2E+Ray%3A+A+distributed+framework+for+emergin)
55. Pushmeet Kohli Nathan Silberman, Derek Hoiem and Rob Fergus. Indoor segmentation and support inference from rgbd images. In ECCV, 2012. [find](https://scholar.google.com/scholar?q=Pushmeet+Kohli+Nathan+Silberman%2C+Derek+Hoiem+and+Rob+Fergus%2E+Indoor+segmentation+and+support+inference+from+rgbd+images%2E+In+ECCV%2C+2012%2E)
56. OpenAI. DALL·E 3. [https://openai.com/research/dall-e-3](https://openai.com/research/dall-e-3), September 2023. [↗](https://openai.com/research/dall-e-3)
57. OpenAI. Gpt-image-1, 2025. URL [https://openai.com/index/introducing-4o-image-generation/](https://openai.com/index/introducing-4o-image-generation/). [↗](https://openai.com/index/introducing-4o-image-generation/)
58. Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas Müller, Joe Penna, and Robin Rombach. [Sdxl: Improving latent diffusion models for high-resolution image synthesis](https://md.research.elamur.ai/free/en/papers/podell-2023-sdxl-improving-latent-diffusion-models/). arXiv preprint arXiv:2307.01952, 2023.
59. Qi Qin, Le Zhuo, Yi Xin, Ruoyi Du, Zhen Li, Bin Fu, Yiting Lu, Jiakang Yuan, Xinyue Li, Dongyang Liu, et al. Lumina-image 2.0: A unified and efficient image generative framework. arXiv preprint arXiv:2503.21758, 2025. — [arXiv:2503.21758](https://arxiv.org/abs/2503.21758) [find](https://scholar.google.com/scholar?q=Qi+Qin%2C+Le+Zhuo%2C+Yi+Xin%2C+Ruoyi+Du%2C+Zhen+Li%2C+Bin+Fu%2C+Yiting+Lu%2C+Jiakang+Yuan%2C+Xinyue+Li%2C+Dongyang+Liu%2C+et+al%2E+Lumina%2Dimage+2%2E0%3A+A+unified+and+efficient+image+generative+framework%2E+arXiv+preprint+arXiv%3A)
60. Qwen. Qwen3-coder is the code version of qwen3, the large language model series developed by qwen team, alibaba cloud., 2025. URL [https://github.com/QwenLM/Qwen3-Coder](https://github.com/QwenLM/Qwen3-Coder). [↗](https://github.com/QwenLM/Qwen3-Coder)
61. Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D Manning, Stefano Ermon, and Chelsea Finn. [Direct preference optimization: Your language model is secretly a reward model](https://md.research.elamur.ai/free/en/papers/rafailov-2023-direct-preference-optimization-language-model/). Advances in neural information processing systems, 36:53728–53741, 2023.
62. René Ranftl, Katrin Lasinger, David Hafner, Konrad Schindler, and Vladlen Koltun. Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE transactions on pattern analysis and machine intelligence, 44(3):1623–1637, 2020. [find](https://scholar.google.com/scholar?q=Ren%C3%A9+Ranftl%2C+Katrin+Lasinger%2C+David+Hafner%2C+Konrad+Schindler%2C+and+Vladlen+Koltun%2E+Towards+robust+monocular+depth+estimation%3A+Mixing+datasets+for+zero%2Dshot+cross%2Ddataset+transfer%2E+IEEE+transactions+on+)
63. René Ranftl, Alexey Bochkovskiy, and Vladlen Koltun. Vision transformers for dense prediction. In Proceedings of the IEEE/CVF international conference on computer vision, pp. 12179–12188, 2021. [find](https://scholar.google.com/scholar?q=Ren%C3%A9+Ranftl%2C+Alexey+Bochkovskiy%2C+and+Vladlen+Koltun%2E+Vision+transformers+for+dense+prediction%2E+In+Proceedings+of+the+IEEE%2FCVF+international+conference+on+computer+vision%2C+pp%2E+12179%E2%80%9312188%2C+2021%2E)
64. Recraft. Recraft v3. [https://www.recraft.ai/](https://www.recraft.ai/), 2024. [↗](https://www.recraft.ai/)
65. Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. High-resolution image synthesis with latent diffusion models, 2021. [find](https://scholar.google.com/scholar?q=Robin+Rombach%2C+Andreas+Blattmann%2C+Dominik+Lorenz%2C+Patrick+Esser%2C+and+Bj%C3%B6rn+Ommer%2E+High%2Dresolution+image+synthesis+with+latent+diffusion+models%2C+2021%2E)
66. Thomas Schops, Johannes L Schonberger, Silvano Galliani, Torsten Sattler, Konrad Schindler, Marc Pollefeys, and Andreas Geiger. A multi-view stereo benchmark with high-resolution images and multi-camera videos. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 326… [find](https://scholar.google.com/scholar?q=Thomas+Schops%2C+Johannes+L+Schonberger%2C+Silvano+Galliani%2C+Torsten+Sattler%2C+Konrad+Schindler%2C+Marc+Pollefeys%2C+and+Andreas+Geiger%2E+A+multi%2Dview+stereo+benchmark+with+high%2Dresolution+images+and+multi%2Dcame)
67. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Yang Wu, et al. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). arXiv preprint arXiv:2402.03300, 2024.
68. Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro. Megatron-lm: Training multi-billion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053, 2019. [find](https://scholar.google.com/scholar?q=Mohammad+Shoeybi%2C+Mostofa+Patwary%2C+Raul+Puri%2C+Patrick+LeGresley%2C+Jared+Casper%2C+and+Bryan+Catanzaro%2E+Megatron%2Dlm%3A+Training+multi%2Dbillion+parameter+language+models+using+model+parallelism%2E+arXiv+preprin)
69. Kuaishou Kolors team. Kolors2.0. [https://app.klingai.com/cn/](https://app.klingai.com/cn/), 2025. [↗](https://app.klingai.com/cn/)
70. Michael Tschannen, Alexey Gritsenko, Xiao Wang, Muhammad Ferjad Naeem, Ibrahim Alabdulmohsin, Nikhil Parthasarathy, Talfan Evans, Lucas Beyer, Ye Xia, Basil Mustafa, et al. Siglip 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv p… [find](https://scholar.google.com/scholar?q=Michael+Tschannen%2C+Alexey+Gritsenko%2C+Xiao+Wang%2C+Muhammad+Ferjad+Naeem%2C+Ibrahim+Alabdulmohsin%2C+Nikhil+Parthasarathy%2C+Talfan+Evans%2C+Lucas+Beyer%2C+Ye+Xia%2C+Basil+Mustafa%2C+et+al%2E+Siglip+2%3A+Multilingual+visi)
71. Yuxiang Tuo, Wangmeng Xiang, Jun-Yan He, Yifeng Geng, and Xuansong Xie. Anytext: Multilingual visual text generation and editing. In The Twelfth International Conference on Learning Representations, 2024. [find](https://scholar.google.com/scholar?q=Yuxiang+Tuo%2C+Wangmeng+Xiang%2C+Jun%2DYan+He%2C+Yifeng+Geng%2C+and+Xuansong+Xie%2E+Anytext%3A+Multilingual+visual+text+generation+and+editing%2E+In+The+Twelfth+International+Conference+on+Learning+Representations%2C+2)
72. Igor Vasiljevic, Nick Kolkin, Shanyi Zhang, Ruotian Luo, Haochen Wang, Falcon Z Dai, Andrea F Daniele, Mohammadreza Mostajabi, Steven Basart, Matthew R Walter, et al. Diode: A dense indoor and outdoor depth dataset. arXiv preprint arXiv:1908.00463, 2019. — [arXiv:1908.00463](https://arxiv.org/abs/1908.00463) [find](https://scholar.google.com/scholar?q=Igor+Vasiljevic%2C+Nick+Kolkin%2C+Shanyi+Zhang%2C+Ruotian+Luo%2C+Haochen+Wang%2C+Falcon+Z+Dai%2C+Andrea+F+Daniele%2C+Mohammadreza+Mostajabi%2C+Steven+Basart%2C+Matthew+R+Walter%2C+et+al%2E+Diode%3A+A+dense+indoor+and+outdoor)
73. Bram Wallace, Meihua Dang, Rafael Rafailov, Linqi Zhou, Aaron Lou, Senthil Purushwalkam, Stefano Ermon, Caiming Xiong, Shafiq Joty, and Nikhil Naik. Diffusion model alignment using direct preference optimization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, p… [find](https://scholar.google.com/scholar?q=Bram+Wallace%2C+Meihua+Dang%2C+Rafael+Rafailov%2C+Linqi+Zhou%2C+Aaron+Lou%2C+Senthil+Purushwalkam%2C+Stefano+Ermon%2C+Caiming+Xiong%2C+Shafiq+Joty%2C+and+Nikhil+Naik%2E+Diffusion+model+alignment+using+direct+preference+o)
74. Team Wan, Ang Wang, Baole Ai, Bin Wen, Chaojie Mao, Chen-Wei Xie, Di Chen, Feiwu Yu, Haiming Zhao, Jianxiao Yang, et al. Wan: Open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314, 2025. [find](https://scholar.google.com/scholar?q=Team+Wan%2C+Ang+Wang%2C+Baole+Ai%2C+Bin+Wen%2C+Chaojie+Mao%2C+Chen%2DWei+Xie%2C+Di+Chen%2C+Feiwu+Yu%2C+Haiming+Zhao%2C+Jianxiao+Yang%2C+et+al%2E+Wan%3A+Open+and+advanced+large%2Dscale+video+generative+models%2E+arXiv+preprint+arXi)
75. Peng Wang and Yichun Shi. Imagedream: Image-prompt multi-view diffusion for 3d generation. arXiv preprint arXiv:2312.02201, 2023. — [arXiv:2312.02201](https://arxiv.org/abs/2312.02201) [find](https://scholar.google.com/scholar?q=Peng+Wang+and+Yichun+Shi%2E+Imagedream%3A+Image%2Dprompt+multi%2Dview+diffusion+for+3d+generation%2E+arXiv+preprint+arXiv%3A2312%2E02201%2C+2023%2E+%E2%80%94+%5BarXiv%3A2312%2E02201%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2312%2E02201%29)
76. Peng Wang, Yichun Shi, Xiaochen Lian, Zhonghua Zhai, Xin Xia, Xuefeng Xiao, Weilin Huang, and Jianchao Yang. Seededit 3.0: Fast and high-quality generative image editing. arXiv preprint arXiv:2506.05083, 2025. — [arXiv:2506.05083](https://arxiv.org/abs/2506.05083) [find](https://scholar.google.com/scholar?q=Peng+Wang%2C+Yichun+Shi%2C+Xiaochen+Lian%2C+Zhonghua+Zhai%2C+Xin+Xia%2C+Xuefeng+Xiao%2C+Weilin+Huang%2C+and+Jianchao+Yang%2E+Seededit+3%2E0%3A+Fast+and+high%2Dquality+generative+image+editing%2E+arXiv+preprint+arXiv%3A2506%2E050)
77. Xinlong Wang, Xiaosong Zhang, Zhengxiong Luo, Quan Sun, Yufeng Cui, Jinsheng Wang, Fan Zhang, Yueze Wang, Zhen Li, Qiying Yu, et al. Emu3: Next-token prediction is all you need. arXiv preprint arXiv:2409.18869, 2024a. — [arXiv:2409.18869](https://arxiv.org/abs/2409.18869) [find](https://scholar.google.com/scholar?q=Xinlong+Wang%2C+Xiaosong+Zhang%2C+Zhengxiong+Luo%2C+Quan+Sun%2C+Yufeng+Cui%2C+Jinsheng+Wang%2C+Fan+Zhang%2C+Yueze+Wang%2C+Zhen+Li%2C+Qiying+Yu%2C+et+al%2E+Emu3%3A+Next%2Dtoken+prediction+is+all+you+need%2E+arXiv+preprint+arXiv%3A2)
78. Zhengyi Wang, Yikai Wang, Yifei Chen, Chendong Xiang, Shuo Chen, Dajiang Yu, Chongxuan Li, Hang Su, and Jun Zhu. Crm: Single image to 3d textured mesh with convolutional reconstruction model. In European conference on computer vision, pp. 57–74. Springer, 2024b. [find](https://scholar.google.com/scholar?q=Zhengyi+Wang%2C+Yikai+Wang%2C+Yifei+Chen%2C+Chendong+Xiang%2C+Shuo+Chen%2C+Dajiang+Yu%2C+Chongxuan+Li%2C+Hang+Su%2C+and+Jun+Zhu%2E+Crm%3A+Single+image+to+3d+textured+mesh+with+convolutional+reconstruction+model%2E+In+Europ)
79. Xinyu Wei, Jinrui Zhang, Zeqing Wang, Hongyang Wei, Zhen Guo, and Lei Zhang. Tiif-bench: How does your t2i model follow your instructions? arXiv preprint arXiv:2506.02161, 2025. — [arXiv:2506.02161](https://arxiv.org/abs/2506.02161) [find](https://scholar.google.com/scholar?q=Xinyu+Wei%2C+Jinrui+Zhang%2C+Zeqing+Wang%2C+Hongyang+Wei%2C+Zhen+Guo%2C+and+Lei+Zhang%2E+Tiif%2Dbench%3A+How+does+your+t2i+model+follow+your+instructions%3F+arXiv+preprint+arXiv%3A2506%2E02161%2C+2025%2E+%E2%80%94+%5BarXiv%3A2506%2E02161%5D%28h)
80. Chenfei Wu, Jian Liang, Lei Ji, Fan Yang, Yuejian Fang, Daxin Jiang, and Nan Duan. Nüwa: Visual synthesis pre-training for neural visual world creation. In European conference on computer vision, pp. 720–736. Springer, 2022. [find](https://scholar.google.com/scholar?q=Chenfei+Wu%2C+Jian+Liang%2C+Lei+Ji%2C+Fan+Yang%2C+Yuejian+Fang%2C+Daxin+Jiang%2C+and+Nan+Duan%2E+N%C3%BCwa%3A+Visual+synthesis+pre%2Dtraining+for+neural+visual+world+creation%2E+In+European+conference+on+computer+vision%2C+pp%2E+)
81. Chengyue Wu, Xiaokang Chen, Zhiyu Wu, Yiyang Ma, Xingchao Liu, Zizheng Pan, Wen Liu, Zhenda Xie, Xingkai Yu, Chong Ruan, et al. [Janus: Decoupling visual encoding for unified multimodal understanding and generation](https://md.research.elamur.ai/free/en/papers/wu-2024-janus-decoupling-visual-encoding/). In Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 12966–1…
82. Chenyuan Wu, Pengfei Zheng, Ruiran Yan, Shitao Xiao, Xin Luo, Yueze Wang, Wanli Li, Xiyan Jiang, Yexin Liu, Junjie Zhou, et al. Omnigen2: Exploration to advanced multimodal generation. arXiv preprint arXiv:2506.18871, 2025b. — [arXiv:2506.18871](https://arxiv.org/abs/2506.18871) [find](https://scholar.google.com/scholar?q=Chenyuan+Wu%2C+Pengfei+Zheng%2C+Ruiran+Yan%2C+Shitao+Xiao%2C+Xin+Luo%2C+Yueze+Wang%2C+Wanli+Li%2C+Xiyan+Jiang%2C+Yexin+Liu%2C+Junjie+Zhou%2C+et+al%2E+Omnigen2%3A+Exploration+to+advanced+multimodal+generation%2E+arXiv+preprint+)
83. Xianfeng Wu, Yajing Bai, Haoze Zheng, Harold Haodong Chen, Yexin Liu, Zihao Wang, Xuran Ma, Wen-Jie Shu, Xianzu Wu, Harry Yang, et al. Lightgen: Efficient image generation through knowledge distillation and direct preference optimization. arXiv preprint arXiv:2503.08619, 2025c. [find](https://scholar.google.com/scholar?q=Xianfeng+Wu%2C+Yajing+Bai%2C+Haoze+Zheng%2C+Harold+Haodong+Chen%2C+Yexin+Liu%2C+Zihao+Wang%2C+Xuran+Ma%2C+Wen%2DJie+Shu%2C+Xianzu+Wu%2C+Harry+Yang%2C+et+al%2E+Lightgen%3A+Efficient+image+generation+through+knowledge+distillati)
84. Shitao Xiao, Yueze Wang, Junjie Zhou, Huaying Yuan, Xingrun Xing, Ruiran Yan, Chaofan Li, Shuting Wang, Tiejun Huang, and Zheng Liu. Omnigen: Unified image generation. In Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 13294–13304, 2025. [find](https://scholar.google.com/scholar?q=Shitao+Xiao%2C+Yueze+Wang%2C+Junjie+Zhou%2C+Huaying+Yuan%2C+Xingrun+Xing%2C+Ruiran+Yan%2C+Chaofan+Li%2C+Shuting+Wang%2C+Tiejun+Huang%2C+and+Zheng+Liu%2E+Omnigen%3A+Unified+image+generation%2E+In+Proceedings+of+the+Computer+V)
85. Enze Xie, Junsong Chen, Yuyang Zhao, Jincheng Yu, Ligeng Zhu, Chengyue Wu, Yujun Lin, Zhekai Zhang, Muyang Li, Junyu Chen, et al. Sana 1.5: Efficient scaling of training-time and inference-time compute in linear diffusion transformer. arXiv preprint arXiv:2501.18427, 2025a. — [arXiv:2501.18427](https://arxiv.org/abs/2501.18427) [find](https://scholar.google.com/scholar?q=Enze+Xie%2C+Junsong+Chen%2C+Yuyang+Zhao%2C+Jincheng+Yu%2C+Ligeng+Zhu%2C+Chengyue+Wu%2C+Yujun+Lin%2C+Zhekai+Zhang%2C+Muyang+Li%2C+Junyu+Chen%2C+et+al%2E+Sana+1%2E5%3A+Efficient+scaling+of+training%2Dtime+and+inference%2Dtime+comput)
86. Jinheng Xie, Weijia Mao, Zechen Bai, David Junhao Zhang, Weihao Wang, Kevin Qinghong Lin, Yuchao Gu, Zhijie Chen, Zhenheng Yang, and Mike Zheng Shou. Show-o: One single transformer to unify multimodal understanding and generation. arXiv preprint arXiv:2408.12528, 2024. — [arXiv:2408.12528](https://arxiv.org/abs/2408.12528) [find](https://scholar.google.com/scholar?q=Jinheng+Xie%2C+Weijia+Mao%2C+Zechen+Bai%2C+David+Junhao+Zhang%2C+Weihao+Wang%2C+Kevin+Qinghong+Lin%2C+Yuchao+Gu%2C+Zhijie+Chen%2C+Zhenheng+Yang%2C+and+Mike+Zheng+Shou%2E+Show%2Do%3A+One+single+transformer+to+unify+multimodal)
87. Jinheng Xie, Zhenheng Yang, and Mike Zheng Shou. Show-o2: Improved native unified multimodal models. arXiv preprint arXiv:2506.15564, 2025b. — [arXiv:2506.15564](https://arxiv.org/abs/2506.15564) [find](https://scholar.google.com/scholar?q=Jinheng+Xie%2C+Zhenheng+Yang%2C+and+Mike+Zheng+Shou%2E+Show%2Do2%3A+Improved+native+unified+multimodal+models%2E+arXiv+preprint+arXiv%3A2506%2E15564%2C+2025b%2E+%E2%80%94+%5BarXiv%3A2506%2E15564%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2506%2E15564%29)
88. An Yang, Junshu Pan, Junyang Lin, Rui Men, Yichang Zhang, Jingren Zhou, and Chang Zhou. Chinese clip: Contrastive vision-language pretraining in chinese. arXiv:2211.01335, 2022. — [arXiv:2211.01335](https://arxiv.org/abs/2211.01335) [find](https://scholar.google.com/scholar?q=An+Yang%2C+Junshu+Pan%2C+Junyang+Lin%2C+Rui+Men%2C+Yichang+Zhang%2C+Jingren+Zhou%2C+and+Chang+Zhou%2E+Chinese+clip%3A+Contrastive+vision%2Dlanguage+pretraining+in+chinese%2E+arXiv%3A2211%2E01335%2C+2022%2E+%E2%80%94+%5BarXiv%3A2211%2E01335%5D%28h)
89. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). arXiv preprint arXiv:2505.09388, 2025.
90. Lihe Yang, Bingyi Kang, Zilong Huang, Xiaogang Xu, Jiashi Feng, and Hengshuang Zhao. Depth anything: Unleashing the power of large-scale unlabeled data. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10371–10381, 2024a. [find](https://scholar.google.com/scholar?q=Lihe+Yang%2C+Bingyi+Kang%2C+Zilong+Huang%2C+Xiaogang+Xu%2C+Jiashi+Feng%2C+and+Hengshuang+Zhao%2E+Depth+anything%3A+Unleashing+the+power+of+large%2Dscale+unlabeled+data%2E+In+Proceedings+of+the+IEEE%2FCVF+Conference+on+Co)
91. Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao, Xiaogang Xu, Jiashi Feng, and Hengshuang Zhao. Depth anything v2. arXiv preprint arXiv:2406.09414, 2024b. — [arXiv:2406.09414](https://arxiv.org/abs/2406.09414) [find](https://scholar.google.com/scholar?q=Lihe+Yang%2C+Bingyi+Kang%2C+Zilong+Huang%2C+Zhen+Zhao%2C+Xiaogang+Xu%2C+Jiashi+Feng%2C+and+Hengshuang+Zhao%2E+Depth+anything+v2%2E+arXiv+preprint+arXiv%3A2406%2E09414%2C+2024b%2E+%E2%80%94+%5BarXiv%3A2406%2E09414%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F24)
92. Yang Ye, Xianyi He, Zongjian Li, Bin Lin, Shenghai Yuan, Zhiyuan Yan, Bohan Hou, and Li Yuan. Imgedit: A unified image editing dataset and benchmark. arXiv preprint arXiv:2505.20275, 2025. — [arXiv:2505.20275](https://arxiv.org/abs/2505.20275) [find](https://scholar.google.com/scholar?q=Yang+Ye%2C+Xianyi+He%2C+Zongjian+Li%2C+Bin+Lin%2C+Shenghai+Yuan%2C+Zhiyuan+Yan%2C+Bohan+Hou%2C+and+Li+Yuan%2E+Imgedit%3A+A+unified+image+editing+dataset+and+benchmark%2E+arXiv+preprint+arXiv%3A2505%2E20275%2C+2025%2E+%E2%80%94+%5BarXiv%3A25)
93. Qifan Yu, Wei Chow, Zhongqi Yue, Kaihang Pan, Yang Wu, Xiaoyang Wan, Juncheng Li, Siliang Tang, Hanwang Zhang, and Yueting Zhuang. Anyedit: Mastering unified high-quality image editing for any idea. In Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 26125–26135, 2025. [find](https://scholar.google.com/scholar?q=Qifan+Yu%2C+Wei+Chow%2C+Zhongqi+Yue%2C+Kaihang+Pan%2C+Yang+Wu%2C+Xiaoyang+Wan%2C+Juncheng+Li%2C+Siliang+Tang%2C+Hanwang+Zhang%2C+and+Yueting+Zhuang%2E+Anyedit%3A+Mastering+unified+high%2Dquality+image+editing+for+any+idea%2E+I)
94. THUKEG Z.ai. Cogview4, 2025. URL [https://github.com/THUDM/CogView4](https://github.com/THUDM/CogView4). [↗](https://github.com/THUDM/CogView4)
95. Biao Zhang and Rico Sennrich. Root mean square layer normalization. Advances in neural information processing systems, 32, 2019. [find](https://scholar.google.com/scholar?q=Biao+Zhang+and+Rico+Sennrich%2E+Root+mean+square+layer+normalization%2E+Advances+in+neural+information+processing+systems%2C+32%2C+2019%2E)
96. Kai Zhang, Lingbo Mo, Wenhu Chen, Huan Sun, and Yu Su. Magicbrush: A manually annotated dataset for instruction-guided image editing. Advances in Neural Information Processing Systems, 36:31428–31449, 2023. [find](https://scholar.google.com/scholar?q=Kai+Zhang%2C+Lingbo+Mo%2C+Wenhu+Chen%2C+Huan+Sun%2C+and+Yu+Su%2E+Magicbrush%3A+A+manually+annotated+dataset+for+instruction%2Dguided+image+editing%2E+Advances+in+Neural+Information+Processing+Systems%2C+36%3A31428%E2%80%9331449%2C)
97. Zechuan Zhang, Ji Xie, Yu Lu, Zongxin Yang, and Yi Yang. In-context edit: Enabling instructional image editing with in-context generation in large scale diffusion transformer. arXiv preprint arXiv:2504.20690, 2025. — [arXiv:2504.20690](https://arxiv.org/abs/2504.20690) [find](https://scholar.google.com/scholar?q=Zechuan+Zhang%2C+Ji+Xie%2C+Yu+Lu%2C+Zongxin+Yang%2C+and+Yi+Yang%2E+In%2Dcontext+edit%3A+Enabling+instructional+image+editing+with+in%2Dcontext+generation+in+large+scale+diffusion+transformer%2E+arXiv+preprint+arXiv%3A250)
98. Canyu Zhao, Mingyu Liu, Huanyi Zheng, Muzhi Zhu, Zhiyue Zhao, Hao Chen, Tong He, and Chunhua Shen. Diception: A generalist diffusion model for visual perceptual tasks. arXiv preprint arXiv:2502.17157, 2025. — [arXiv:2502.17157](https://arxiv.org/abs/2502.17157) [find](https://scholar.google.com/scholar?q=Canyu+Zhao%2C+Mingyu+Liu%2C+Huanyi+Zheng%2C+Muzhi+Zhu%2C+Zhiyue+Zhao%2C+Hao+Chen%2C+Tong+He%2C+and+Chunhua+Shen%2E+Diception%3A+A+generalist+diffusion+model+for+visual+perceptual+tasks%2E+arXiv+preprint+arXiv%3A2502%2E17157%2C)
99. Haozhe Zhao, Xiaojian Shawn Ma, Liang Chen, Shuzheng Si, Rujie Wu, Kaikai An, Peiyu Yu, Minjia Zhang, Qing Li, and Baobao Chang. Ultraedit: Instruction-based fine-grained image editing at scale. Advances in Neural Information Processing Systems, 37:3058–3093, 2024. [find](https://scholar.google.com/scholar?q=Haozhe+Zhao%2C+Xiaojian+Shawn+Ma%2C+Liang+Chen%2C+Shuzheng+Si%2C+Rujie+Wu%2C+Kaikai+An%2C+Peiyu+Yu%2C+Minjia+Zhang%2C+Qing+Li%2C+and+Baobao+Chang%2E+Ultraedit%3A+Instruction%2Dbased+fine%2Dgrained+image+editing+at+scale%2E+Advan)
100. Yanli Zhao, Andrew Gu, Rohan Varma, Liang Luo, Chien-Chin Huang, Min Xu, Less Wright, Hamid Shojanazeri, Myle Ott, Sam Shleifer, et al. Pytorch fsdp: experiences on scaling fully sharded data parallel. arXiv preprint arXiv:2304.11277, 2023. [find](https://scholar.google.com/scholar?q=Yanli+Zhao%2C+Andrew+Gu%2C+Rohan+Varma%2C+Liang+Luo%2C+Chien%2DChin+Huang%2C+Min+Xu%2C+Less+Wright%2C+Hamid+Shojanazeri%2C+Myle+Ott%2C+Sam+Shleifer%2C+et+al%2E+Pytorch+fsdp%3A+experiences+on+scaling+fully+sharded+data+parallel)
101. Dewei Zhou, Ji Xie, Zongxin Yang, and Yi Yang. 3dis: Depth-driven decoupled instance synthesis for text-to-image generation. arXiv preprint arXiv:2410.12669, 2024. — [arXiv:2410.12669](https://arxiv.org/abs/2410.12669) [find](https://scholar.google.com/scholar?q=Dewei+Zhou%2C+Ji+Xie%2C+Zongxin+Yang%2C+and+Yi+Yang%2E+3dis%3A+Depth%2Ddriven+decoupled+instance+synthesis+for+text%2Dto%2Dimage+generation%2E+arXiv+preprint+arXiv%3A2410%2E12669%2C+2024%2E+%E2%80%94+%5BarXiv%3A2410%2E12669%5D%28https%3A%2F%2Farxiv%2Eo)
102. Le Zhuo, Ruoyi Du, Han Xiao, Yangguang Li, Dongyang Liu, Rongjie Huang, Wenze Liu, Xiangyang Zhu, Fu-Yun Wang, Zhanyu Ma, et al. Lumina-next: Making lumina-t2x stronger and faster with next-dit. Advances in Neural Information Processing Systems, 37:131278–131315, 2024. [find](https://scholar.google.com/scholar?q=Le+Zhuo%2C+Ruoyi+Du%2C+Han+Xiao%2C+Yangguang+Li%2C+Dongyang+Liu%2C+Rongjie+Huang%2C+Wenze+Liu%2C+Xiangyang+Zhu%2C+Fu%2DYun+Wang%2C+Zhanyu+Ma%2C+et+al%2E+Lumina%2Dnext%3A+Making+lumina%2Dt2x+stronger+and+faster+with+next%2Ddit%2E+Advan)

*Updated 24 October 2026*