# pranksyland deepdreamgenerator ddgart digitalart styletransfer neuralstyle neuralnetworks transfer artificialintelligence daily everyday eye pancakes wineglass stylegan2
画質 高画質

Today's reverse toonification experiments with art from for Incredibles 2, Up, & Coco.

This framework from and quickly finds a "real" human face in the FFHQ latent space. Adding some style randomness too.

More Pixar in thread! ⬇️

5094 30166
2020-10-16

stylegan2-ada anime n=1k finetuning

2 24
2020-10-10

stylegan2 cartoonset is now on runwayml
link: https://t.co/z12PR034qy

7 54
2020-09-25

(1) Alex, (2) Agaricalic Horror, (3) Apprehension, and (4) Aqueous, Not Acquiescent from my adversarial AI art series "Artifice & Insight" are now available on .

Evocative portraits born of StyleGAN conjuring faces whence there were none.

50 - 300 swap.hive each.

2 2
2020-09-15

After many, many months, has finally cracked “stylegan on complex datasets”. Look how good these are! Trained on 2M danbooru photos, I think.

I can’t overstate how much work this took. There are so many variants to try that I basically gave up.

2 61
2020-09-08

Taking layer swapping further: Resolution dependant interpolation between StyleGAN models lets you transplant My Little Pony eyes into anime faces. https://t.co/6iNX3Oxmqv

0 11
2020-08-25

My build is a podium with 7 of my artworks showcased. These were AI generated (StyleGAN) from a custom water-colour dataset that I curated. Do read about the full project at:
https://t.co/PMlb8TC4SO
Thanks my friend for this opportunity.

6 12
2020-08-16

what i've been messing with most recently: creating 3D texture maps out of the 'GANime girl' (my own name for them) images generated from gwern's "this waifu does not exist" styleGAN

9 53
2020-08-02

人工知能が作ったキャラ
私はこれの少女漫画ヒロイン版を作りたいけど、styleganのやり方が分からずに断念

0 1
2020-07-21

After all, StyleGAN's architecture is quite similar to BigGAN. So it must be due to one of the "bells and whistles" that StyleGAN comes with.

I'll just give the answer: Style mixing on (left, step 26k), style mixing off (right, 24k). Note how much more cohesive the bodies are.

1 18
2020-07-16

Following up, another interpolation video of the same model much later in training. It really seems that, despite this one being trained on random cropping, StyleGAN2 prefers generating centrally-placed objects (especially evident in comparison with BigGAN...) https://t.co/XQwTEb7NbY

4 25
2020-05-13

I always love applications of the styleGAN projects like this!

I was actually trying to train something exactly like this for a while but labored the compute power and py understanding

It can for sure make some cool sona's though and I hope those rp accounts move to these now!

0 5
2020-05-07