I have tried to use ChatGPT and Google's Gemini to make SVG from simple logos bitmaps but its still a daunting task for them, so I guess tools like this one will still be needed for a while.
You can get pretty decent initial results if you explicitly tell them to first make a detailed description with exact coordinates and then feed the description back into them to build the SVG.
If you search for ‘vectorization AI’ there are a handful of specialized tools and apis that can do it. It worked well for a handful of logos I wanted to convert. Nano banana generated the raster logos, and these other tools vectorized them
I haven't seen one that worked properly—can you list a couple examples? Some of the ones that say they're "AI" are just VTracer / Potrace and don't give nice control points.
I liked the results of vectorizer.ai and recraft.ai
Input image is important too. When working with the generalist LLM on the raster art, give it context that you are making a logo, direct it to use strokes and fills and minimal color palette, readable at small sizes, etc.
vectorizer.ai is amazing. It's worked great for like over 10 years (back when it had a name like vector magic or something). I'm super curious how it's implemented
Try Claude code. I have built so many. Entire pitch decks for my startup. It is the best. Tell it to use animation libraries gsap framer motion etc to build svg.
Others have mentioned SVG AI tools... I've tried 3-4 over the previous days and eventually ended up with svgai.org (after I've used Google Gemini for bitmap).
You can instruct it to make edits, or say "Use SVG gradients for the windows" and so on and you can further iterate on the SVG.
It can be frustrating at times, but the end result was worth it for me.
Though for some images I've done 2-3 roundtrips manual editing, Nano Banana, svgai.org ...
The advantage is that it produces sane output paths that I can edit easily for final manual touches in Inkscape.
Some of the other "AI" tools are often just simply algorithms for bitmap->vector and the paths/curves they produce are harder to work with, and also give a specific feel to the vector art..
It seems like the problem of pushing pixels around in an exact way and iterating on visual design is a problem that needs very specialized tools, regardless whether there is LLM support.
Yes, these AI tools are good at drawing JPGs or PNGs, but not so good at generating SVGs. I searched for several image-to-SVG tools, and the best one was this Adobe tool: https://www.adobe.com/express/feature/image/convert/svg. After converting to SVG, I used Figma to fine-tune it.
Free idea: turn this into an MCP server. Give the agent the ability to virtually "hover" a path and see which part of the final render it corresponds to
The problem isn't really SVG but the more complex problem of looking at a, possibly noisy, image with continuous color variations and identifying the cutoff point where you contain one part in a border and a different part in another border. That can be judgement call that is made better if you actually understand what is represented but harder if you are working at the pixel level.
Same! My use case is 2d splines for use in openSCAD, stuff that eventually arrives at my doorstep from a 3d printing service. I just love the ability to overlay reference bitmaps, super valuable for the parts I've been making.
Before stumbling upon this tool, I've spent a lot of time tweaking SVP paths in "mostly manual" files in other projects, it's a recurring theme for me. I was delegating the more interesting paths to Inkscape or similar, but keeping the basic structure handwritten. This tool would have made my life so much easier!
I keep trying to generate SVG using LLMS when I feel mermaidjs does not work. There has to be a better option here? I just want slightly more control than mermaidjs sometimes, but it seems its the de-facto default we are stuck with.
This isn't a web service. It's a browser-based tool that runs entirely on your device. It's published as a static site on GitHub Pages, and ("but"?) everything it's doing is all happening fully in-browser.
I tried it in Firefox and Chrome, but changing the SVG shape did not change the favicon displayed on the tab. I don't think I understand what you meant.
PS: This submission of mine is at least a day old, but it now shows as posted about 3 hours ago; I presume this is because it is from the second-chance pool.
Input image is important too. When working with the generalist LLM on the raster art, give it context that you are making a logo, direct it to use strokes and fills and minimal color palette, readable at small sizes, etc.
You can instruct it to make edits, or say "Use SVG gradients for the windows" and so on and you can further iterate on the SVG.
It can be frustrating at times, but the end result was worth it for me.
Though for some images I've done 2-3 roundtrips manual editing, Nano Banana, svgai.org ...
The advantage is that it produces sane output paths that I can edit easily for final manual touches in Inkscape.
Some of the other "AI" tools are often just simply algorithms for bitmap->vector and the paths/curves they produce are harder to work with, and also give a specific feel to the vector art..
A dedicated or fine tuned model for just SVGs would be pretty wild.
Before stumbling upon this tool, I've spent a lot of time tweaking SVP paths in "mostly manual" files in other projects, it's a recurring theme for me. I was delegating the more interesting paths to Inkscape or similar, but keeping the basic structure handwritten. This tool would have made my life so much easier!
albeit, it is heavy tool that comes with lots of feats.
Save the file and run it at will, just like any other local app.
The app runs in an interpreter which is a browser instead of python and a load of libraries, which is no distinction at all.
Well and I can eat the cake as well, make it some native app that has proper performance.
It just uses a browser as the interpreter environment and super effortless one-click instantaneous install process.
This is open source, so whether or not it's a web app should make no difference here
PS: This submission of mine is at least a day old, but it now shows as posted about 3 hours ago; I presume this is because it is from the second-chance pool.