Hey, computer, make me a font • Hacker News Board

Re: Hey, computer, make me a font

#21

Post by dleeftink » Tue, Oct 03, 2023, 2:29 PM UTC

matsemann wrote: post #16

dleeftink wrote: post #3

Although I would be sad to see the handcrafting that goes into designing custom fonts go, some iterations down the line a model like this would greatly aid tedious glyph alignment and consistency tasks when designing CJK, hiragana, katakana and kanji fonts. Inspiring stuff.

It's already so that writing on computers is quite US-centric (at least English-centric). While this might help on some of the shortcomings, I'm also a bit afraid it will make it so that even more focus is put only on the US part, and the rest of the world get a "good enough" implementation made by AI that kinda erases some heritage.

Maybe, but the Latin font market is quite saturated, whereas the CJK space has ample opportunity for innovating and is likely even in need of it, cf. [0][1][2]

[0]: https://qz.com/522079/the-long-incredibly-tortuous-and-fasci...

[1]: https://fonts.google.com/knowledge/type_in_china_japan_and_k...

[2]: https://stackoverflow.com/a/14573813

Re: Hey, computer, make me a font

#22

Post by scarygliders » Tue, Oct 03, 2023, 2:38 PM UTC

Okay I can't try it out anyway. "Blocksparse is not available: the current GPU does not expose Tensor cores"

My "best" GPU is an RTX 2070 Super, Turing architecture.

I've seen similar messages when using stable-diffusion... either with -webui or with automatic, can't exactly remember, but they both run fine on that RTX 2070 Super, so I can only guess that they revert to some other method than Blocksparse on seeing that it doesn't support Turing. Or something. I haven't looked into how they deal with it.

I've submitted an Issue [0] for it. I don't have enough knowledge to know if there's some way of saying "don't use Blocksparse" for fontogen.

[0] https://github.com/SerCeMan/fontogen/issues/2

Re: Hey, computer, make me a font

#23

Post by artursapek » Tue, Oct 03, 2023, 2:40 PM UTC

7moritz7 wrote: post #11

scarygliders wrote: post #5

Hmmm. The model is a ckpt instead of a safetensor. Pondering on whether to keep proceeding trying this out or not... EDIT: a scan with picklescan[0] found nothing.. exciting. [0] https://github.com/mmaitre314/picklescan

Haven't seen a single maliscious ckpt file so far. Sure, there is a possibility, but huggingface scans pickled weights automatically so the likelihood of someone using that site to spread malware in this form is super low

“pickled weights”?

serious question, how on Earth should someone like me, who has completely missed the last 12 months of AI development, catch up with the state of the art?

Re: Hey, computer, make me a font

#24

Post by TheRealPomax » Tue, Oct 03, 2023, 2:42 PM UTC

Neat! Does it have prompt capabilities for things like FVAR, GSUB, and GPOS? E.g. "okay now include a many-to-one ligature that turns the word 'chicken' into an emoji of a chicken in the same style" or "now make a second, sans-serif, robotic style and add an axis called interpol that varies the font from the style we just made to this new style"?

Re: Hey, computer, make me a font

#25

Post by scarygliders » Tue, Oct 03, 2023, 2:48 PM UTC

artursapek wrote: post #23

7moritz7 wrote: post #11

Earlier quoted context omitted.

Haven't seen a single maliscious ckpt file so far. Sure, there is a possibility, but huggingface scans pickled weights automatically so the likelihood of someone using that site to spread malware in this form is super low

“pickled weights”? serious question, how on Earth should someone like me, who has completely missed the last 12 months of AI development, catch up with the state of the art?

Just know that the .ckpt format has more or less been replaced by .safetensors these days.

tl;dr .ckpt files can contain Python pickles containing runnable Python code, which means a Bad Guy could create a .ckpt model containing malicious python code. Basically.

Re: Hey, computer, make me a font

#26

Post by lawlessone » Tue, Oct 03, 2023, 2:50 PM UTC

This 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.

Re: Hey, computer, make me a font

#27

Post by simbolit » Tue, Oct 03, 2023, 2:51 PM UTC

TheRealPomax wrote: post #24

Neat! Does it have prompt capabilities for things like FVAR, GSUB, and GPOS? E.g. "okay now include a many-to-one ligature that turns the word 'chicken' into an emoji of a chicken in the same style" or "now make a second, sans-serif, robotic style and add an axis called interpol that varies the font from the style we just made to this new style"?

Not OP, but the answer is "no".

What exactly made you suspect such abilities?

Re: Hey, computer, make me a font

#28

Post by ballenf » Tue, Oct 03, 2023, 2:55 PM UTC

philipwhiuk wrote: post #18

> To train the model, I assembled a dataset of 71k distinct fonts. I give it a week before Monotype sues your face off.

Copyright around fonts may not support such a suit in the same as way as works of art.

Wikipedia says: "In the United States, the shapes of typefaces are not eligible for copyright but may be protected by design patent (although it is rarely applied for, the first US design patent that was ever awarded was for a typeface).[1]"

So just scanning the rendered font (as opposed to the code that generates it), may be harder to stop than scanning of artwork.

https://en.wikipedia.org/wiki/Intellectual_property_protecti...

Re: Hey, computer, make me a font

#29

Post by simbolit » Tue, Oct 03, 2023, 2:55 PM UTC

artursapek wrote: post #23

7moritz7 wrote: post #11

Earlier quoted context omitted.

Haven't seen a single maliscious ckpt file so far. Sure, there is a possibility, but huggingface scans pickled weights automatically so the likelihood of someone using that site to spread malware in this form is super low

“pickled weights”? serious question, how on Earth should someone like me, who has completely missed the last 12 months of AI development, catch up with the state of the art?

I suppose you being here means that you are already fluent in some programming languages. If so, I would start here:

Conway & Miles - Machine Learning for Hackers: Case Studies and Algorithms to Get You Started

Once you read and understood this, I'd do an online course...

Re: Hey, computer, make me a font

#30

Post by TheRealPomax » Tue, Oct 03, 2023, 2:57 PM UTC

simbolit wrote: post #27

TheRealPomax wrote: post #24

Neat! Does it have prompt capabilities for things like FVAR, GSUB, and GPOS? E.g. "okay now include a many-to-one ligature that turns the word 'chicken' into an emoji of a chicken in the same style" or "now make a second, sans-serif, robotic style and add an axis called interpol that varies the font from the style we just made to this new style"?

Not OP, but the answer is "no". What exactly made you suspect such abilities?

Odd phrasing, but: the part where I've worked on OpenType parsing for decades and love seeing people with a passion for digital typefaces make new and creative tools in that space. Typically folks don't stop working on a cool tool after they write a blog post, they're still refining and extending, so you never know how far someone is trying to take a tool without asking them.