Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models
Ronghuan Wu, Wanchao Su, Jing Liao
Abstract
A car with lights emitting from it, on a road."
"A salmon sushi with wooden chopsticks and a dish of soy sauce." "A dog wears a chef's hat."
"A sunflower in bloom with grass and a butterfly hovering above."
"A red apple with green leaves, a worm in a hole, and a juice box with a straw."
"A pig wearing a backpack and a cowboy hat is standing on a skateboard." "An astronaut is riding a horse." "A sandcastle with a bucket, shovel and two seagulls flying above."
that Chat2SVG outperforms existing methods in visual fidelity, path regularity, and semantic alignment. Additionally, our system enables intuitive editing through natural language instructions, making professional vector graphics creation accessible to all users. Our code is available at https://chat2svg.github.io/.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 24a7948c-e464-4240-983a-306d0cb80737Cited by top-tier papers16
- OmniSVG: A Unified Scalable Vector Graphics Generation ModelYiying Yang, Wei Cheng, Sijin Chen, Xianfang Zeng et al.NeurIPS 2025 · 90 citations
- GeoGramBench: Benchmarking the Geometric Program Reasoning in Modern LLMsShixian Luo, Zhu zezhou, Yu Yuan, Yuncheng Yang et al.ICLR 2026 · 15 citations
- VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector AnimationGuotao Liang, Zhangcheng Wang, Chuang Wang, Juncheng Hu et al.ICML 2026 · 11 citations
- LottieGPT: Tokenizing Vector Animation for Autoregressive GenerationJunhao Chen, Kejun Gao, Yuehan Cui, Mingze Sun et al.CVPR 2026 · 10 citations
- MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D MeshShuangkang Fang, I-Chao Shen, Yufeng Wang, Yi-Hsuan Tsai et al.ICCV 2025 · 8 citations
Builds on25
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Adding Conditional Control to Text-to-Image Diffusion ModelsLvmin Zhang, Anyi Rao, Maneesh AgrawalaICCV 2023 · 6,759 citations
- SDEdit: Guided Image Synthesis and Editing with Stochastic Differential EquationsChenlin Meng, Yutong He, Yang Song, Jiaming Song et al.ICLR 2022 · 2,128 citations
- ImageReward: Learning and Evaluating Human Preferences for Text-to-Image GenerationJiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong et al.NeurIPS 2023 · 1,310 citations
- DreamFusion: Text-to-3D using 2D DiffusionBen Poole, Ajay Jain, Jonathan T. Barron, Ben MildenhallICLR 2023 · 463 citations
Related papers
- Empowering Vector Graphics with Consistently Arbitrary Viewing and View-dependent VisibilityYidi Li, Jun Xiao, Zhengda Lu, Yiqun Wang et al.CVPR 2025
- SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG GenerationHanqi Chen, Zhongyin Zhao, Ye Chen, Zhujin Liang et al.ACM MM 2025 · 3 citations
- TextCraftor: Your Text Encoder can be Image Quality ControllerYanyu Li, Xian Liu, Anil Kag, Ju Hu et al.CVPR 2024
- Exploring Sparse MoE in GANs for Text-conditioned Image SynthesisJiapeng Zhu, Ceyuan Yang, Kecheng Zheng, Yinghao Xu et al.CVPR 2025
- Breathing Life Into Sketches Using Text-to-Video PriorsRinon Gal, Yael Vinker, Yuval Alaluf, Amit Bermano et al.CVPR 2024
