Viewing profile — liuru

The first iteration of our model was built off of this amazing public dataset: https://www.gwern.net/Danbooru2020 Though now we have made our own :)

This one has some rough-looking ones! They're a bit rarer than most.

read the bottom! The part about creativity is on the bottom :D

In the future, perhaps! This is a popular request, so we are thinking about ways we can do this.

1) It was mostly manual, though AIs were useful in certain filtering tasks. 2) Depends on the quality you are seeking. If you only want one run of a similar, off-the-shelf model, a…

Haha, this is something that constantly ponder, while I am developing this product. Though, the conclusion I've come to is that that hand-drawn art will always meaningful for human…

Indeed, we spent 2 years working on this!!! It's an extremely hard research problem, because darker skin tones account for only about 0.3% of all anime art produced in the world. W…

Thank you for the typo! Indeed, it contributes to the variations problem. also: If the discriminator starts off perfect, then the generator can't learn to be better. Sort of like a…

Not at the moment in our tool, though this is an area of great curiosity and research for us!

Ah yes, the fine line between charming anime character and lovecraftian horror There was such popular demand for these "horror" images that we made them part of the generation in V…

Welcome back! We're currently working on the data migration from V1! As long as you are using the same email as you did in 2019, you'll be able to see the image again! As for a V2 …

Got it! Thank you! :D

While our model is not public, there are good resources online for playing with your own images! Like this one by fast.ai! https://docs.fast.ai/vision.gan.html

Yes, your understanding is correct! You can think of it like coordinates on a many-dimensional vector grid. We craft the functions the functions that will illuminate sets of those …

Not at the moment! A similar project that I really admire is public, though! https://www.thiswaifudoesnotexist.net/

2 weeks to train the model! Development took on-and-off roughly 2 years to achieve the quality you see today.

Hey HN, one of the team members here! I hope you all enjoy playing with the new and improved generator! We've been hard at work improving the model quality since the last time the …

Nothing specific so far. We did this because we thought it would be very cool :)

Haha, not a plagiarist at all :) Please do! That's exactly what this is for: turning data into an extra bit of inspiration.

https://imgur.com/a/ZFrliiO Here's one that's somewhat "annoyed" but not quite "disgusted" hm.