18
top 5 comments
sorted by: hot top controversial new old
[-] notfromhere@lemmy.one 4 points 3 days ago* (last edited 3 days ago)

StarVector is a foundation model for generating Scalable Vector Graphics (SVG) code from images and text. It utilizes a Vision-Language Modeling architecture to understand both visual and textual inputs, enabling high-quality vectorization and text-guided SVG creation.

I was just thinking about an img2svg generator. I was tying to get Claude to do it earlier today with poor results.

[-] morrowind@lemm.ee 3 points 3 days ago

Claude frequently draws svgs to illustrate things for me (I'm guessing it's in the prompt) but even though it's better at it than all the other models, it still kinda sucks. It's just fudamentally dumb task to do for a purely language model, similar to the arc-agi benchmark , just makes more sense for a vision model and trying to get an llm to do is a waste

[-] HappyFrog 1 points 3 days ago

It doesn't look to be that much more effective than a simple autotracer.

[-] morrowind@lemm.ee 1 points 1 day ago

autotracers can't generate svgs from text

[-] HappyFrog 1 points 1 day ago

True, I was only looking at the img to svg part.

this post was submitted on 24 Mar 2025
18 points (100.0% liked)

LocalLLaMA

2766 readers
14 users here now

Welcome to LocalLLama! This is a community to discuss local large language models such as LLama, Deepseek, Mistral, and Qwen.

Get support from the community! Ask questions, share prompts, discuss benchmarks, get hyped at the latest and greatest model releases! Enjoy talking about our awesome hobby.

As ambassadors of the self-hosting machine learning community, we strive to support eachother and share our enthusiasm in a positive constructive way.

founded 2 years ago
MODERATORS