OmniSVG: New AI Model Generates Complex SVGs Using Vision-Language Models; Code Release Pending

GitHub - OmniSVG/OmniSVG: OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from simple icons to intricate anime characters.

Official repo for OmniSVG OmniSVG: A Unified Scalable Vector Graphics Generation Model 🏃 Intro OmniSVG OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from simple icons to intricate anime characters. 🚩 News [2025/04/09] Release MMSVG-Icon and MMSVG-Illustration 🤗Dataset. [2025/04/09] Upload paper and init project. To Do List Code and Pretrained Models Release MMSVG-Cha...