NeuralSVG: An Implicit Representation for Text-to-Vector Generation • Hacker News Board

Re: NeuralSVG: An Implicit Representation for Text-to-Vector Generation

#61

Post by niemandhier » Thu, Jan 09, 2025, 7:37 AM UTC

It looks as if this is not autoregressive.

It would be interesting to see a similar approach that incrementally works from simpler ( fewer curves ) to more complex representations.

That way one could probably apply RLHF along the trajectory too.

Re: NeuralSVG: An Implicit Representation for Text-to-Vector Generation

#62

Post by nbzso » Thu, Jan 09, 2025, 8:09 AM UTC

So designers, artist, musicians we are done, right? Who's next, I wonder?

Re: NeuralSVG: An Implicit Representation for Text-to-Vector Generation

#63

Post by thomasfl » Thu, Jan 09, 2025, 9:10 AM UTC

Finally something that can benefit artists as a sketching tool.

Re: NeuralSVG: An Implicit Representation for Text-to-Vector Generation

#64

Post by lewisjoe » Thu, Jan 09, 2025, 9:16 AM UTC

airstrike wrote: post #12

This opens up lots of opportunities for document authoring tools. Really cool stuff, can't wait to try out the code once it's available.

Curious how this can augment document authoring! Can you toss some ideas?

Re: NeuralSVG: An Implicit Representation for Text-to-Vector Generation

#65

Post by nikolayasdf123 » Thu, Jan 09, 2025, 10:09 AM UTC

very nice. had this idea for awhile, but never had time to implement it.

glad someone actually did it! great work!

Re: NeuralSVG: An Implicit Representation for Text-to-Vector Generation

#66

Post by Jean-Papoulos » Thu, Jan 09, 2025, 10:36 AM UTC

This is the kind of image generation I've been waiting for. No more messing around in Inkscape (or at least, less of it) when I need a specific icon.

Re: NeuralSVG: An Implicit Representation for Text-to-Vector Generation

#67

Post by cyp0633 » Thu, Jan 09, 2025, 11:17 AM UTC

Claude has been doing a good job generating SVGs compared to its rivals, happy to see new models bringing image generation even further

Re: NeuralSVG: An Implicit Representation for Text-to-Vector Generation

#68

Post by zidad » Thu, Jan 09, 2025, 12:28 PM UTC

vipshek wrote: post #26

This is excellent! I think the utility of generating vectors is far, far greater than all the raster generation that's been a big focus thus far (DALL-E, Midjourney, etc). Those efforts have been incredibly impressive, of course, but raster outputs are so much more difficult to work with. You're forced to "upscale" or "inpaint" the rasters using subsequent generative AI calls to actually iterate towards something use…

I always imagine how useful Sora.ai could be if it would generate 3D models to render their animations from instead

Re: NeuralSVG: An Implicit Representation for Text-to-Vector Generation

#69

Post by _1 » Thu, Jan 09, 2025, 1:51 PM UTC

jonathaneunice wrote: post #21

Nice! Looking forward to similar textual generation of diagrams. (The Pic/Pikchr for the LLM age.)

I've had some success with converting SQL to Mermaid Markdown diagrams.

Re: NeuralSVG: An Implicit Representation for Text-to-Vector Generation

#70

Post by spyder » Thu, Jan 09, 2025, 2:08 PM UTC

zidad wrote: post #68

vipshek wrote: post #26

This is excellent! I think the utility of generating vectors is far, far greater than all the raster generation that's been a big focus thus far (DALL-E, Midjourney, etc). Those efforts have been incredibly impressive, of course, but raster outputs are so much more difficult to work with. You're forced to "upscale" or "inpaint" the rasters using subsequent generative AI calls to actually iterate towards something use…

I always imagine how useful Sora.ai could be if it would generate 3D models to render their animations from instead

I agree, that's the future of these video models. For professional use you want more control and the obvious next step towards that is to generate the full 3D scene (in the form of animated gaussian splats since that's more AI friendly than the mesh based 3D). That also helps the model to be more consistent but also adds the ability for the user to have more control over the camera or the scene.