[HN Gopher] AI Gahuku: AI Generator Will Turn Your Photos into R...
       ___________________________________________________________________
        
       AI Gahuku: AI Generator Will Turn Your Photos into Renaissance
       Paintings
        
       Author : superasn
       Score  : 95 points
       Date   : 2020-04-13 20:32 UTC (1 days ago)
        
 (HTM) web link (ai-art.tokyo)
 (TXT) w3m dump (ai-art.tokyo)
        
       | samcheng wrote:
       | Someone should do this with the "Getty Museum Challenge" photos
       | that are circulating social media right now!
        
       | DeathArrow wrote:
       | This is what I've got using chimp pics:
       | 
       | https://imgur.com/a/hkG0rJg
       | 
       | https://imgur.com/a/YZ3oWUm
        
         | imhoguy wrote:
         | That is creepy and genious. So who is the author of the artwork
         | now? AI?
        
           | qchris wrote:
           | There's actually been some litigation around this topic
           | recently. The general consensus seems to be that authorship
           | gets assigned to closest version of the person who initiated
           | the creation process of the resulting artwork. So, in this
           | case, I believe it would be the person that selected and
           | uploaded the photo to the service would have authorship--the
           | actual process is considered to be more of a blackbox tool
           | being used by that person. A (way more) sophisticated digital
           | paintbrush, if you will.
        
             | ajmarcic wrote:
             | Does anyone have cites on litigation specific to generative
             | works?
             | 
             | The nearest neighbor precedent I'm aware of is the
             | dismissal of Authors Guild v Google
        
               | qchris wrote:
               | I'm not sure about links directly to court cases, but
               | here's a couple different general-consumption articles
               | from the last few years that address this sort of thing.
               | I'm hopeful I didn't convey that the consensus on the
               | subject is particularly solid...
               | 
               | [1] https://qz.com/1054039/google-deepdream-art-if-an-ai-
               | creates...
               | 
               | [2] https://www.scmp.com/tech/start-
               | ups/article/3042811/legal-ex...
        
             | dylan604 wrote:
             | Wouldn't this be similar to using Photoshop or any other
             | image manipulation tool? Adobe does not get ownership of
             | output of their software. Why would we think some random
             | website offering image manipulation would be different? As
             | you say, the software is just a tool in the image creation
             | process.
        
             | thatguy0900 wrote:
             | Presumably this chimp image wasn't his, so would the new
             | picture be owned by him still?
        
         | maxander wrote:
         | That is extremely Hieronymous Bosch.
        
         | retSava wrote:
         | Holy smokes - the second one was unnerving to say the least!
        
       | superfamicom wrote:
       | Tips for best results: no teeth, no beards, no dark skin, looking
       | directly at the camera tends to make one of the eyes perfect and
       | the other wonky.
        
         | mensetmanusman wrote:
         | Tips for hilarious results: lots of teeth, lots of beard
        
         | basch wrote:
         | This worked pretty well as a test picture.
         | 
         | https://upload.wikimedia.org/wikipedia/commons/7/7d/Glynn_S....
         | 
         | OR, REO look good. RE1 turned him into David Tomlinson.
        
       | babo wrote:
       | It clearly shows a strong bias, practically turns a woman into a
       | man.
        
       | imhoguy wrote:
       | It is not me! To guillotine! :)
        
       | tomc1985 wrote:
       | Can they not use the word "masterpiece" on the site? A
       | masterpiece is supposed to be superlative.
       | 
       | You can't call every single output a "masterpiece"
        
       | ElonsMosque wrote:
       | I mean I'm aware there probably weren't many black people during
       | the renaissance. But it would be even cooler if this worked for
       | people with different shades?
        
       | amiantos wrote:
       | Maybe this should be titled "nightmare generator" because most of
       | the pictures I have tried, especially of my wife, have ended up
       | with very frightening distortions. Might be cooler to pair this
       | with cubist paintings instead, so the facial defects seem more
       | like features.
        
       | hobs wrote:
       | Service seems to be overwhelmed.
        
       | leogout wrote:
       | I wear glasses. I've tried with many photos of me with glasses
       | and it always looks like it can't handle it. Do you think it is
       | because it was trained with paintings at a time when glasses
       | weren't common ?
        
       | drcode wrote:
       | It really captured the personality of our president well:
       | https://firebasestorage.googleapis.com/v0/b/ai-gahaku.appspo...
        
       | jw887c wrote:
       | Yeah this doesn't work for non-white folk. Just makes us look
       | like white folk
        
         | johnzim wrote:
         | That's almost for the best. The representation of non-European
         | ethnic facial features / skin tones in renaissance art appeared
         | to mostly be one of two groupings:
         | 
         | 1) Accurate, naturalistic portrayals that almost certainly had
         | an actual human sitting and;
         | 
         | 2) Color choices / features that are to humans of other skin
         | tones, what that picture of a cat in the still life painting is
         | to our feline friends:
         | https://twitter.com/chelsesaurusrex/status/99512793958585139...
         | 
         | There are some really interesting examples in this article
         | (although explicitly African):
         | 
         | https://thewalters.org/wp-content/uploads/revealing-the-afri...
        
           | ggggtez wrote:
           | It's not really kosher to suggest that it's "for the best"
           | that it doesn't work well for other people. :)
           | 
           | It's not like paintings of darkskinned people don't exist for
           | the AI to learn from, even if you don't like the style that
           | was used at that time.
        
         | amrrs wrote:
         | This is mentioned in their site. Seems they've identified it.
         | 
         | >Currently, we are confirming that the output of the AI artist
         | has been biased. We hope to use a wide variety of learning data
         | and increase the diversity of output in the future.
        
       | kristopolous wrote:
       | Great work, calling it The Hapsburger would be amazing.
        
       | ipsum2 wrote:
       | Does anyone have an example to look at? The ones in the header
       | are small and darkened.
       | 
       | Edit: here's Trump and Obama, using their official Whitehouse
       | portraits: https://imgur.com/a/iWeX9tl. Pretty funny results.
        
         | basch wrote:
         | Try this. It's interactive so after you submit, you can choose
         | your style.
         | 
         | https://upload.wikimedia.org/wikipedia/commons/7/7d/Glynn_S....
        
           | ipsum2 wrote:
           | Thanks - I didn't want to contribute to HN's hug of death,
           | doing inference is probably very expensive for them.
        
             | wenc wrote:
             | I wonder about that? In most cases once an algorithm is
             | trained, running inference is just a function evaluation,
             | which is usually computationally inexpensive.
             | 
             | (the training is the heavy compute part)
        
         | notduncansmith wrote:
         | One of those exposes a pretty clear bias in Renaissance
         | painting subjects.
        
           | mattigames wrote:
           | Yeah, it doesn't do blonde hair.
        
             | dylan604 wrote:
             | Which is odd because didn't everyone wear powdered wigs?
             | Seems like everyone would have a blonde wig (which should
             | make things easier).
        
       | hkmurakami wrote:
       | Ah title is misspelled, page says "Gahaku", which is a slightly
       | archaic term in Japanese for artist/Painter with a connotation of
       | being a highly skilled and respected master of the craft.
       | 
       | There's also a sarcastic net slag meaning to the term as well but
       | the creators are probably not using the term with that intent.
        
       | cwoolfe wrote:
       | Great work! Although it is interesting to me how it doesn't work
       | very well for non-white faces. Which totally makes sense given
       | that renaissance art training data reflects the time and place in
       | which it was created.
        
         | dylan604 wrote:
         | From someone that is not an ML/AI evangelist, how is this great
         | work? None of the images I've seen remotely look good. I have
         | yet to see something that a real life painter not suffering
         | from a stroke would be willing to have released.
        
       | smitty1e wrote:
       | This is the sort of great work that invites the question of
       | whether "can" == "should".
       | 
       | It's awesome that the work of great artists can be reduced to an
       | algorithm. That effort is its own kind of art, and will see
       | application (e.g. restoration work) far and wide. It could help
       | with tutorials for students to get into these older styles.
       | 
       | Despite all of the intermediate goodness, I still want the no-
       | kidding product I buy to have had some actual human imperfection
       | and idiosyncrasy injected.
       | 
       | As explored by Rick Beato in the musical context here =>
       | https://www.youtube.com/watch?v=L-8EbHkc8tc
        
         | new2628 wrote:
         | I think you give these projects too much credit. They do not
         | reduce the work of great artists to an algorithm and they do
         | not turn user's photos into renaissance paintings. These
         | projects are technically impressive and interesting, but art is
         | not going anywhere.
        
       | kumarm wrote:
       | Nice. Worked well for me for several photos. Is this model open
       | source?
        
       ___________________________________________________________________
       (page generated 2020-04-14 23:01 UTC)