from Hacker News

AnimeGANv2: Convert Face Portraits into Anime

by aliabd on 11/9/21, 2:34 PM with 65 comments

by ksec on 11/9/21, 5:59 PM
May be those examples should have instant results? I guess most people are just clicking them to see what it looks likes instead of waiting 100s.
Most of them look like photoshop filter as per other comments, but IU and Billie Eilish definitely looks good.
by webmaven on 11/9/21, 5:49 PM
Like many other comments, I don't see much resemblance to anime styles, but dismissing the results as a Photoshop filter is nuts.
The animation style this does look like is that of 2006's A Scanner Darkly, or 2019's Undone.
by aliabd on 11/9/21, 3:59 PM
This was built on top of the Pytorch implementation [0] of AnimeGANv2, using gradio [1] and HuggingFace Spaces [2]. See the 100s of examples [3] posted by users.
[0]: https://github.com/bryandlee/animegan2-pytorch [1]: https://gradio.app [2]: https://huggingface.co/spaces [3]: https://twitter.com/ak92501/status/1457033482115420160/retwe...
by coldacid on 11/9/21, 6:25 PM
Tried a headshot of myself framed like the example pictures and all I got was something that looked like it was bombed by effects out of Paint.NET. Definitely looked nothing like an anime character.
by snvzz on 11/9/21, 3:53 PM
A gallery of examples would be nice.
Else, it's too much effort. People are gonna just close the browser tab, like I did.
by amelius on 11/9/21, 4:42 PM
Nice, but the problem I have with this and similar techniques is that if you zoom out sufficiently far, then you don't see a difference with the original image. This is not how "anime" is supposed to work.
by kroltan on 11/9/21, 9:51 PM
Great, now I can generate random cartoon portraits by combining this with https://www.thispersondoesnotexist.com/
I do second the observation that this isn't nearly "Anime" style by any definition or sample of the style I've ever seen. I would expect to see these results in a GTA 5 loading screen.
by DrSiemer on 11/10/21, 5:02 AM
Excellent, I was hoping something as accessible as this would appear to play around with this type of model!
Those that dismiss this as nothing more than a few filters are missing the finer details of what it actually does. There is a lot of targeted tweaking, like removing double chins and other old age artefacts. There are small embellishments, like adding a twinkle to the eyes or lip gloss where none was present before. The direction of a gaze is fixed towards the camera. And of course, although it's more cartoon style than anime, the eyes do become bigger.
The quality of your results depends on how appropriate your input is. Try something that has the potential to be Disney and you will get great results.
Sure, you could (with enough practice) get similar results by manually editing a photo. But the beauty of this type of conversion is that it allows for near instant effortless experimentation and (after some other improvements) application to sequenced frames.
The active model does lean towards feminizing and westernizing the subject. Mustaches are removed and an Asian subject will receive wide open blue eyes every now and then.
by grammarnazzzi on 11/10/21, 1:40 AM
Viewing these images remind me a lot of caricature portraiture.
As with real artwork, the eye is drawn to embelishments, exagerations, and simplification and directed by composition.
In pieces by a competant artist, these add a new level of interest and dimension to the piece.
With these images, following what makes each image is always a dead end. There is no composition and the embelishments are mechanical, random and uninteresting.
For example, I find myself wondering why the the artist chose to paint the mouth so asymetrical. Is the artist trying to express an emotion? Who is the subject, and why have the been rendered as they have. It's confusing and a challenge to critique the artwork... until I realize its just bit of randomness generated by algorithm incapable of any creativity beyond how the programmer applied generic and randomizing programming methods.
There isn't and cannot be anything unique to any of the images. Once you've studied any one of them, you've really experienced most of what the programmer/artist has contributed.
by esjeon on 11/10/21, 2:24 AM
One big mistake is that this is not anime. This is obviously comic-style, which is more realistic, and, in turn, closer to automated filtering.
Note that Japanese anime normally uses a much simplified style to increase the production speed. This naturally results in a highly distorted(?!) depictions that even humans often find disturbing. This makes anime-style difficult to mimic.
by bj-rn on 11/9/21, 7:19 PM
Remided me of "Waifu Synthesis- real time generative anime": http://everyoneishappy.com/portfolio/waifu-synthesis-real-ti...
by Pxtl on 11/9/21, 9:09 PM
Ugh, it doesn't properly respect EXIF rotation tags so if I try to post from my phone it gets mangled. EXIF rotation has got to be the most absurdly poorly supported feature of a common file type like jpeg.
by messo on 11/9/21, 8:58 PM
The example with Bill Gates at the bottom is wild! The "teardrop" under one of his eyes makes it slightly gangster, and the smooth face and awkward smile reminds me of a much younger Bill. Fascinating.
by ur-whale on 11/9/21, 4:34 PM
I'd be curious to see how well / stable this behaves under animation.
by dryst on 11/9/21, 10:36 PM
Lol @ the Bill Gates to middle aged woman with teardrop tattoo.
by chillingeffect on 11/9/21, 9:22 PM
at first the result disappointed me (emotionally, not technically), but after a few minutes I went back to it and was struck by the feel the image brought out. It really reflected some of the wistfulness and sadness I feel with a tiny touch of optimism. I'm not well-versed in anime, but that does seem to be a little bit of the feel that I get from it. bravo.
by Mumps on 11/10/21, 3:32 PM
Not anime _per se_, but the toon-me [0] project gives much more stylistic outputs. I've really enjoyed making some home art with it (and the prior ArtLine).
[0] https://github.com/vijishmadhavan/Toon-Me
by wintermutestwin on 11/10/21, 3:17 AM
I found that it did an awesome job on some photos and messed up some. When it messed up, it generally made mouths look way too distorted. I also thought it was funny that it turned obviously green eyes blue. Overall, I think it is a fun implementation, but it would be much better to have a larger output file.
by remram on 11/9/21, 4:12 PM
Waited 10min then got an error.
by wodenokoto on 11/9/21, 9:43 PM
I thought the selfie to waifu generator created much more interesting and anime like results.
It does look like it doesn’t work anymore though.
https://waifu.lofiu.com/
by rbobby on 11/10/21, 5:51 AM
I did my "corporate" picture and it came out looking like I had been badly beaten and with really bad teeth (100 years of coffee and cigarettes). Bit of a blow to the self-esteem.
Just not anime material I guess.
by peterthehacker on 11/9/21, 5:33 PM
Tried with Elon and Gates, but both threw this error
```
  Error occured while trying to proxy: hf.space/
```
by GhettoComputers on 11/9/21, 6:55 PM
Who decided this was anime? It doesn't look like any anime I have ever seen, it just looks like a smoothing filter. It looks more like a toonme but not as good and maybe more private? For referece look at this waifu generator, nobody would call these portrait conversions anime. http://thiswaifudoesnotexist.com/
by rbobby on 11/10/21, 5:42 AM
Bill Gates comes out looking a bit like Ellen DeGeneres.
by codein on 11/9/21, 7:03 PM
Did not manage to get any result. Is the service down?
by bobobob420 on 11/9/21, 8:17 PM
Unless this is open source and I can run all of the code locally with no internet connection I am not doing this. Am I too paranoid?
by TulliusCicero on 11/9/21, 10:17 PM
Interesting, you can see how it feminizes faces quite clearly in the examples of Bill Gates and Elon Musk. Gates looks kind of like Ellen DeGeneres to me in the anime version.