Explaining myself and Mixfont, an AI font generation model

2»

Comments

  • Eko Bimantara
    Eko Bimantara Posts: 13
    I've tried creating a font on the site, and it does seem to be more geared towards "quick-to-create" fonts. I'm hoping to explore more of the generated results to help speed up my font-making workflow, but there are still many obstacles and need lot of addition for it, as discussed. For example, is it possible to have additional tools for refining outlines or adjusting kerning/spacing?

    This refining technicality is important because it needed to achieve specific appropriateness of the work, for example in a text font family; How do you adjust vertical metrics and set up hinting? How about consistency between styles? How about optical balance and type color? In minimum level: How to make the generated extended styles not looks like faux bold? Adjusting all these needs seems difficult using prompts; it's still more comfortable to use hands with the font editor feature.

    There's also concerns about impact of quick-to-create fonts like this site's do: Some people might worry that, not only AI-generated works, but genuine works which is not involving AI, can be "visible" or "labeled" as being AI-generated.

    In automated writing, its easy to make apparently "smart" writtings, but there are often certain language patterns or diction that strongly suggest they're AI-generated. If we take it raw, without editing, by someone who's not used to write and doesn't have a personal expressive language, it's not hard to guess it was created by AI, especially by someone who used to read.

    This font generator also produces similar results. On the one hand, it can generate seemingly complex and well-thought-out letterforms or typographic concepts, but on the other hand it's flawed and needed a lot of refining
  • Dave Crossland
    Dave Crossland Posts: 1,575
    I should point out that Andrés Torresi is the primary author of the ht Letterspacer project, and he'll present it at the Typographics 2027 TypeLab next week - it's one of those attempts Simon Cozens mentioned. 

    I also want to say that I think it's nice Eric bothered to engage this forum...

    The lack of reckoning with the current and rapidly developing situation at Western type events ha struck me as peculiar. I think it's important that this topic is discussed. 

    First I should preface that... In https://ethanmarcotte.com/wrote/all-tomorrows-parties/ (the designer famous for cooking and promoting the idea of "responsive web design", iiuc) says that the phrase "what will happen next?" lacks agency, but per "Autonomous Technology: Technics-out-of-Control as a Theme in Political Thought" from Langdon Winner in 1977, it's unclear to me we-human-society have any. 

    Back to my point... I believe the majority of computer scientists who developed typefaces generators don't bother; I expect their number to increase exponentially upwards as the difficulty of doing this goes exponentially downwards; and I expect those two trends to continue such that the next 10, 100 Eric's won't post here at all.

    Impallari appears to have been the first. Eric's become second. I hope there'll be a third. 
  • Carl Crossgrove
    Carl Crossgrove Posts: 14
    Eric, Simon has said something that is a bit of a mantra for me with typeface design, and a couple examples may help: Objects that also require a bizarrely microscopic level of detail awareness: Eyeglass frames, and Automobile bodies. There are likely many others. Compare the eleventy-something midsize family SUVs available, or the shape of the category of eyeglass frames popular for a long time known as "rectangular" - Or any of the sub-categories. Peruse the literal hundreds of options.

    What exactly are the differences? When we try on several pairs, the differences "show up" when combined with a face, but how could one of dozens of similar pairs be so wrong, so awkward, when another pair, seemingly "the same," will pair perfectly with one human's face shape, eye positions, forehead, etc. The answer is the same with tiny, "imperceptible" flaws in typefaces: Your eyes have to be trained to SEE finer and finer differences in shape. The top of the lenses might angle down just slightly in one pair, but be perfectly level in another. The two lenses might be the tiniest bit smaller in the vertical direction but bigger horizontally. The bridge length, the frame thickness, the sharpness of curves, the lens size, every variable you can describe affects the appearance of an eyeglass frame and a typeface. This skill is necessary for those tasks, mentioned above, to be meaningfully and successfully accomplished.

    I don't want this to sound exclusionary or elitist. I think people in other fields with this kind of trained perception would agree: if you can't see (or hear) the difference, how would you improve it? Because some type designers have shaky hands (me), or very unreliable motor control, they may not be able to "draw" the exact shapes they envision. Bezier [and other outline] tools have absolutely helped me to get control of shapes to a satisfactory degree. Technology has always been blended into the creative parts of type design or type making, so you can trust that probably nobody on this thread or this forum is threatened by "technology". Having the wonderful assistance of perfectly-smooth bezier shapes allowed me to take the steps of building a character set, adding different weights, italics, and then printing them out.

    With a lot of guidance from my mentors, over time, with a lot of testing and looking and refining, I learned to SEE things that are nearly imperceptible. THIS is the most important, consequential skill in type design. The ability to really see finer and finer and finer levels of detail does not happen quickly. It requires a fair amount of training and critique, which I was lucky to get. Success in typeface design is primarily learning to see. 
  • Nick Shinn
    Nick Shinn Posts: 2,396
    edited June 21
    Ultimately, the difference between text commands that create visual images (i.e. gen-AI prompts) and shapes made directly with a pen (whether shaky or not) is that such line-drawing engages more areas of the brain than typing. This was discovered in recent research. Presumably this is the result of the constant, real-time feedback loop of hand-eye co-ordination involved. 

    However, if that were to result in more sophisticated designs, as one might expect, would they even be appreciated by a populace that was keyboard-centric? At least learning to read and “write” (make visible text) still incorporates hand-writing, putting all readers on the same page, as it were.
  • Thomas Phinney
    Thomas Phinney Posts: 3,185
    edited July 3
    @ericlu
    I just wanted to point out that some of the “quality” problems people (including me) have been pointing out… are things that have been solved by non-AI automation ages ago. Adding points at extrema and removing redundant points have been automated functions in desktop font editors forever, now.

    I don’t see why you wouldn’t either:

    1) Run some such processes as post-op procedures on the generated fonts.
    and/or...
    2) Do that post-processing, and then feed the before-and-after results into your AI to train it on what it needs to do better.

    Same goes for spacing and kerning, I think.

    The more general visual curve quality issues are more tricky. Those are the main way that I was able, on my second go at it, to correctly ID 11 out of 12 of your “is it AI?” test cases. I did have to enlarge to the maximum 84 px size, though.
  • Abdurrahman Hanif
    Abdurrahman Hanif Posts: 22

    Hi Eric, the Latin font market is already crowded, and AI is putting even more pressure on independent foundries.

    I’d suggest using AI where it’s genuinely needed, like developing Hanzi/Chinese fonts, where drawing 5,000+ glyphs is a huge task. That would also be a real challenge since there is less Chinese font data available, so you’d have to figure out more on your own rather than relying on the massive amount of existing Latin font data 😉

    Latin fonts have far fewer glyphs, so I think we can still enjoy the process ourselves without AI 😄

  • Dave Crossland
    Dave Crossland Posts: 1,575
    Abdurrahman Hanif said:

    Latin fonts have far fewer glyphs, so I think we can still enjoy the process ourselves without AI 😄

    Many Latin fonts that support US English do not have a Rupee currency character, making them less useful in India. So I think as A.I. type design technology becomes perfected, probably first as a proprietary service and then as libre software, Latin fonts will soon have a lot more glyphs as a baseline expectation - and this may be a good thing for users and readers, who character needs have been neglected. 
  • Maurice Meilleur
    Maurice Meilleur Posts: 64
    So the model does the fun design part and the human is left with the grunt work. That is the very opposite of reducing tedium.

    This by the way is what Cory Doctorow calls a ‘reverse centaur’—the idea is a centerpiece of his critique of LLM GPT models and the subject of his most recent book about AI. An early piece of his on the subject is here.

  • kunstx
    kunstx Posts: 31
    I commented on your "anti robot font" post, which is clearly not as presented. In regards to "steeling" font, these people are delusional. Most of the fonts are reproductions of old type foundries and n-th versions of the same typeface. So I don't think AI will create more slop. Only problem "AI" can create, is non-technical slop. Even in second world war, USA type designers made a 1:1 knockoffs of German typefaces, calling to abolishing usage "Nazi typefaces", and using their knockoffs. The worlds is a circus.
  • Justmytype76
    Justmytype76 Posts: 12
    Igor Petrovic said:
    Is Mixfont legal?
    For one I think that at least there should be a terms of use pop-up on the site, when you try to upload an image,  stating that any image you upload to the platform you have to own the rights to do so. At least people would then understand that they were doing something wrong by uploading another artists image that they have no right doing  so. Uploading anothers artwork to 'derivativley' produce software that's commercially sellable using that artwork is not legal.
  • John Savard
    John Savard Posts: 1,256
    edited September 10
    kunstx said:
    Even in second world war, USA type designers made a 1:1 knockoffs of German typefaces, calling to abolishing usage "Nazi typefaces", and using their knockoffs. The worlds is a circus.

    I don't understand. What on Earth is wrong with avoiding giving money to an enemy in wartime? Particularly an enemy this wicked. Of course, though, if you are referring to typefounders being asked to melt down and replace their stocks of Fraktur type from Germany purchased long ago, before hostilities, that would be silly.
  • Nadine Chahine
    Nadine Chahine Posts: 149
    Justmytype76 said:
    Igor Petrovic said:
    Is Mixfont legal?
    For one I think that at least there should be a terms of use pop-up on the site, when you try to upload an image,  stating that any image you upload to the platform you have to own the rights to do so. At least people would then understand that they were doing something wrong by uploading another artists image that they have no right doing  so. Uploading anothers artwork to 'derivativley' produce software that's commercially sellable using that artwork is not legal.
    We need foundries to update their EULAs to specifically prohibit AI training.
  • kunstx
    kunstx Posts: 31
    John Savard said:
    kunstx said:
    Even in second world war, USA type designers made a 1:1 knockoffs of German typefaces, calling to abolishing usage "Nazi typefaces", and using their knockoffs. The worlds is a circus.

    I don't understand. What on Earth is wrong with avoiding giving money to an enemy in wartime? Particularly an enemy this wicked. Of course, though, if you are referring to typefounders being asked to melt down and replace their stocks of Fraktur type from Germany purchased long ago, before hostilities, that would be silly.
    One thing is to not use their typefaces no more, other is to make exact same copies and just name them different. It was just a false reason mentioned to ripoff German designs. In regards to the "enemies" I believe you follow a childish school idea of "World against the Nazis", instead of "A special membership group orchestrating world politics, economy and wars".
  • Dave Crossland
    Dave Crossland Posts: 1,575
    edited September 14
    "A special membership group orchestrating world politics, economy and wars".

    What sources could you recommend to learn more about this, that you imply is not a childish idea? :)

  • John Hudson
    John Hudson Posts: 3,795
    I don’t know, Dave: would you want to be a member of a global cabal that would have you as a member?
  • Dave Crossland
    Dave Crossland Posts: 1,575
    I am a member of several! 


  • Thomas Phinney
    Thomas Phinney Posts: 3,185
    Ah, that explains a lot.  >:)

    I was going to say, various people seem to believe that various of us are in assorted font conspiracies, sometimes with overlapping members. But some of the supposed conspiracies are truly daft.

    And of course there are genuine secret plans... the early planning of OpenType was big and complicated and secret.

    As was the (re-)introduction of variable fonts in 2015–16. (I took photos at one of the late meetings for that. Something like 20 people around a big conference room table, plus a few on video.)
  • kunstx
    kunstx Posts: 31
    edited September 15
    @Dave Crossland Nazis forbade fonts designed by Jews (or as their believed they are as so), but they had some self-respect not to copycat same, and just give the different names, while Allies did the thing you complain about in this whole thread.

    In regards to the sources, if that is a real question and not an ironic digression from the subject, if in 2026 as a grown man. you don't understand that TV news and school are not quite a reality reference, then you probably should grow up. Maybe start with learning about money and how financial system works as the first subject.
  • kunstx
    kunstx Posts: 31
    John Savard said:
    kunstx said:
    Even in second world war, USA type designers made a 1:1 knockoffs of German typefaces, calling to abolishing usage "Nazi typefaces", and using their knockoffs. The worlds is a circus.

    I don't understand. What on Earth is wrong with avoiding giving money to an enemy in wartime? Particularly an enemy this wicked. Of course, though, if you are referring to typefounders being asked to melt down and replace their stocks of Fraktur type from Germany purchased long ago, before hostilities, that would be silly.
    I don't personally care about it, but just giving an example how biased acceptance of "copyright" issues is overlooked.
  • kunstx
    kunstx Posts: 31
    edited September 15
    Simon Cozens said:
    Love it. At risk of verging further off topic, but I think it's a very useful metaphor: I got a robot vacuum cleaner. For a few weeks I was pretty impressed. It was doing grunt work for me! Then it started sending me notifications on my phone: "Robot is stuck." "Robot is lost." "Robot needs repositioning." Then I realised: I'm at this bloody thing's beck and call now. I've become the janitor's janitor.

    Any push of AI into font design that "won't replace humans!" and "still needs human involvement!" needs to make sure that doesn't mean that humans are cleaning up the robot's crap.
    As if anywhere "AI" generation would be beneficial, it would be with digitizing old typefaces, but with clear parameters set, and in any case the manual quality control would be necessary. Who ever believes that machine can become creative decision maker, believes that a human can create human, which is a belief that a man can be a God.

    They still can't create proper skeleton references and construction parameters for glyphs and wasting resources to try accomplish a nonsense. Automatization in certain workflows is welcomed, but with proper problem solving pipelines.
  • Dave Crossland
    Dave Crossland Posts: 1,575
    I was hoping you would give us something like Carroll Quigley, or be explicit you are an avowed antisemite; the ad hominem merely disappoints. 

Categories