This looks aesthetically pleasing but this is not ASCII Art it seems, where’s ascii? All those differently sized dots are not ascii chars, are they? Perhaps this is unicode-art?
The point is that what you've described is no longer a useful definition of "ASCII art". That's now "art with dots". The fact that it's "technically" ASCII is as irrelevant as it is unimpressive.
"ASCII art", defined honestly, means "limited set ASCII art".
Well, it's technically PETSCII art, but the model can be trained on any bitmap charset. So you can make ATARIART or SPECCYART or whatever.
It's not correct to say that most of the information is in the color, though.
I can't remember if it's explained in the readme or not, but what makes this different from other converters is that it matches 1bit 8x8 blocks from the source image to the best matching character, increasing the perceived resolution of the output image.
It's a dumb idea I wanted to implement to amuse myself, and it's not better or worse than any similar tools, but AFAIK it uses a novel approach: fast by using a custom trained NN and uniquely looking output, similar to what a human artist might create by hand.
This is interesting sloproject but in spite of all verbosity I still didn’t parse how do you interface with it when it’s running on intended hw rather than in browser.
ESP32-S3 is a great USB host. I have a custom version where I use a Daisy Seed 3 as the ADC/DAC (it uses I2S for audio, not USB) that I built with around 4ms total latency. If you turn off the amp model (which is pointless, but) it's around 2.6ms. I also patched the iRig HD X firmware so its analog latency is around 1.2ms, practically achieving the same performance as the custom Daisy Seed 3 interface.
Nit: TALA could be another layout engine for graphviz but its not a format itself (I suggested this in comments above). Graphviz also doesn’t imply specific layout unless you mean “dot” that is default. So conversion is somewhat undefined. Maybe you mean graphviz language to d2, afaik there is no official, 100% loss-less automatic translator because of some subtle differences in these declarative languages
The funny thing is that these days they would make it a lot worse with LLMs, perhaps post lots of wins on LinkedIn too. It’s not impossible to steer that ship but it’s never gonna be one shotted in “do refactor, make no mistake” way