Hey, computer, make me a font
41–50 of 150 posts
Re: Hey, computer, make me a font
#42This is interesting but i think generating the next letter from the letters before may not be the best way to do it. As you mentioned they degrade with each letter. Maybe creating one long image of a whole font would work better. edit: in the above am misunderstanding what is happening here. But i still think there must be another way to structure this so the attention mechanism doesn't have to work so hard.
Since the first three letters are good, and generated only with the context of the preceding letters, shouldn’t just using the first three (instead of the preceding three) as context for every other one be good enough?
Re: Hey, computer, make me a font
#43Earlier quoted context omitted.
So, if I understand you correctly, it was less a question "does it do x?" and more an indirect form of "hey OP, would be cool if it did X" ?
This is not the place for starting a discussion about whether context and subtext should be implicit or explicit in written English. That's what https://philosophy.stackexchange.com is for.
I don't want to start a discussion, I wanted to know if I misread your original comment, and whether you meant something different from what I thought you meant.
From your answer, tho very indirect, I now suspect that I did misunderstand your initial comment, and answering your question was missing the point.
That is all I wanted (after at first wanting to be helpful).
Re: Hey, computer, make me a font
#44> To train the model, I assembled a dataset of 71k distinct fonts. I give it a week before Monotype sues your face off.
Font law is almost as complex and fascinating as Tree law.
Given how complex font licensing can be, a generative use case that produces usable fonts would be a huge threat to the foundaries and I expect they will be very litigious, just as Getty and others are in the image space.
Re: Hey, computer, make me a font
#45I found a few months ago that the gpt-4 code interpreter is capable of converting a black and white png of a glyph to an svg https://twitter.com/lfegray/status/1678787763905126400 It would be cool to combine a script like the one gpt-4 gave me with an image generation model to generate fonts. The approach from this blog post is way more interesting though. On a separate note it reminds me of this suckerpinch video :)…
That's amazing.
One of my favorite things to do with copilot is to comment something like "//white arrow pointing right" and then start "<svg" and have it complete it. If it doesn't get it right the first time I update my comment. Saves me time searching for the right SVG and digging through free but really paid image sites.
Re: Hey, computer, make me a font
#46Earlier quoted context omitted.
This is not the place for starting a discussion about whether context and subtext should be implicit or explicit in written English. That's what https://philosophy.stackexchange.com is for.
I don't want to start a discussion, I wanted to know if I misread your original comment, and whether you meant something different from what I thought you meant. From your answer, tho very indirect, I now suspect that I did misunderstand your initial comment, and answering your question was missing the point. That is all I wanted (after at first wanting to be helpful).
Fair enough, I thought you were trolling, but you've made it clear you weren't. I wrote my comment as a question that would hopefully engage the author on the capabilities (both concrete, as well as hypothetical) of this approach to font generation.
Re: Hey, computer, make me a font
#47Inevitable in a good way. Keep going! There's gold here.
Re: Hey, computer, make me a font
#48I’ve tried out some work on generating vector fonts too, in the format of Bezier curves and a seq2seq model. The problem was that fonts outputted by ML models were imprecise. Lines were not perfectly parallel, corners were at 89°, and curves were kinked. It’s not too difficult to get fonts that look good enough, but the imperfections are glaring as fonts are normally perfectly precise. These imperfections are evident in OP’s output too, and in my opinion make these types of models unusable for actual typesetting.
A 1% error in a raster output would be pixel colors being slightly off, but a 89° corner in a vector image is immediately noticeable, making this a hard problem to solve. I haven’t looked into this problem too much since, but I’m interested to hear about possible solutions and reading material.
Re: Hey, computer, make me a font
#49Kinda funny how it works well at this whereas diffusion models go to die when it comes to drawing text but of course it works in a completely different manner.
SDXL can do text kind of. Also isn't DALLE-3 a diffusion model?
But yeah overall diffusion has not generally been able to do it at all before.
Re: Hey, computer, make me a font
#50Everyone knows that AIs can't draw sans...