ximinng/LLM4SVG
[CVPR 2025] Official implementation for "Empowering LLMs to Understand and Generate Complex Vector Graphics" https://arxiv.org/abs/2412.11102
This project helps graphic designers, illustrators, and visual content creators work with vector graphics more efficiently. It allows advanced AI models to understand and create Scalable Vector Graphics (SVG) descriptions based on textual instructions and visual input. You provide text prompts or images, and the AI generates or interprets SVG code, making it easier to automate complex design tasks.
617 stars. No commits in the last 6 months.
Use this if you need to train or fine-tune large language models to generate or interpret complex vector graphics (SVG) from text or visual inputs for design automation or content creation.
Not ideal if you are looking for a ready-to-use application for casual graphic design without needing to train or configure AI models.
Stars
617
Forks
13
Language
Python
License
MIT
Category
Last pushed
May 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/ximinng/LLM4SVG"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
KimMeen/Time-LLM
[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming...
om-ai-lab/VLM-R1
Solve Visual Understanding with Reinforced VLMs
bytedance/SALMONN
SALMONN family: A suite of advanced multi-modal LLMs
NVlabs/OmniVinci
OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.
fixie-ai/ultravox
A fast multimodal LLM for real-time voice