[HN Gopher] Build Your Own Imagen Text-to-Image Model
       ___________________________________________________________________
        
       Build Your Own Imagen Text-to-Image Model
        
       Author : SleekEagle
       Score  : 85 points
       Date   : 2022-08-17 15:22 UTC (7 hours ago)
        
 (HTM) web link (www.assemblyai.com)
 (TXT) w3m dump (www.assemblyai.com)
        
       | isoprophlex wrote:
       | Very lucid explanation of the internal workings of this Imagen-
       | like model. Thanks, I haven't seen things explained this clearly
       | before!
        
         | SleekEagle wrote:
         | Thanks so much! I learned a ton with this project so it's great
         | to hear that I communicated it well :)
        
       | neodypsis wrote:
       | Cool write-up. I'm currently interested in learning about
       | Diffusion Models and found your other article [0] to be a nice
       | introduction to the topic.
       | 
       | [0] https://www.assemblyai.com/blog/diffusion-models-for-
       | machine...
        
         | SleekEagle wrote:
         | That's great! I'm glad you're enjoying them :)
        
       | abriosi wrote:
       | Great post.
       | 
       | I'm eager to see what the next 5 years will bring us
        
         | upupandup wrote:
         | In 5 years I expect text-to-porn to start replacing xvideos
         | 
         | - we will surely see sequential image synthesis by then
         | 
         | - we will surely see matching motion audio synthesis
         | 
         | - we will surely see single image to 3D reconstruction
         | 
         | - we will surely see haptic feedback and VR progress
         | 
         | - we will win.
        
           | Enginerrrd wrote:
           | I suspect it will take more like 10 years at least to produce
           | convincing video. The technology isn't too far off except
           | that the compute requirements are pretty extreme without some
           | clever work. Lots of clever stitching needs to be done too.
           | You need models that can take a description of a scene and
           | produce a story-board like series of low res images. (And
           | maybe vice versa). Then, you need a model that can infer
           | semantics and movement in logical ways between those panels
           | to generate images to fill in the gaps. Then lots and lots of
           | clever cleanup and resolution enhancement both of individual
           | frames and the changes between neighboring frames without
           | introducing all kinds of weird, fuzzy, moving, dream-like
           | artifacts.
           | 
           | ...Then you've got to somehow add audio that ALSO understands
           | semantics in the same way as the story board. Maybe something
           | that can generate an audio clip to go with the storyboard.
           | ....And then fill in the gaps based on the generated video.
           | Making those match seems like a really hard, but not
           | impossible problem. In the short term, a bunch of moaning at
           | appropriate times to mouths moving and whatnot seems feasible
           | though.
           | 
           | Although, I expect fairly high quality text-to-image porn is
           | likely only a few months to a year away.
           | 
           | The technology is there, someone just needs to pay to train
           | the model... and then the cost of compute is what, like 300
           | grand? A few hundred more should get you enough engineering
           | to apply existing techniques. Say $1 million in costs for a
           | product that seems like incentive enough to get a bunch of
           | members to pay a monthly fee.
        
             | cercatrova wrote:
             | At the rate AI image generation is going, I highly doubt
             | it'll take another 10 years. Only 10 years ago did AlexNet
             | come onto the scene and blow away image recognition
             | contests.
        
         | SleekEagle wrote:
         | Appreciate it! And I know ... I feel like we're really hitting
         | a watershed moment with ML/DL. It looks like artists on
         | DeviantArt have already objected to AI-generated art being
         | allowed on the website or suggested a mandatory watermark at
         | the very least.
         | 
         | A very interesting time we're living in
        
           | O__________O wrote:
           | Do you have a source for the claim artist on DeviantArt (in
           | any significant form) are making demands related to ML
           | generated text-to-images?
           | 
           | (Few quick Google searches turned up nothing.)
        
             | SleekEagle wrote:
             | Maybe I'm wrong that it was DeviantArt, but I read
             | something about this. Sorry I don't have a source, I
             | should've checked before mentioning it. The closest thing I
             | could find were rules only for specific groups!
             | 
             | https://www.deviantart.com/rtnightmare/journal/New-Group-
             | Rul...
        
               | O__________O wrote:
               | Thanks, appears one of the nine admins posted a message
               | to a group that has less than two hundred members; to me,
               | that neither significant, nor representative of
               | DeviantArt. Also appears they got push back from the
               | group.
               | 
               | While I didn't review much of the "art" from the group,
               | looked like clip art memes with text; if so, little odd
               | that admin would take issue with anything being made
               | using text-to-image generated art.
        
           | Bluecobra wrote:
           | Seems a bit daft to me. Who are they to say that AI generated
           | art isn't art? Couldn't you say the brush has been replaced
           | keystrokes? Someone still needs to type in inputs and decide
           | what is good/bad. I can understand banning bots that are
           | automatically generating/uploading stuff. Also I wonder how
           | they can prove if a human vs. AI made something if the
           | quality is good enough.
        
             | SleekEagle wrote:
             | I think for a creative website like that is intended to
             | showcase artists it makes sense. Unfortunately I don't
             | think there's much they can do about losing in the market
             | to text-to-image models in the long run... the costs are
             | essentially zero
        
             | rchaud wrote:
             | Who's to say a monkey picking stocks by throwing darts at a
             | wall can't be a portfolio manager?
             | 
             | "AI Art" all looks the same to me. Just enough fuzziness in
             | the style so you can't see the hard edges of what they
             | copied, or rather indexed in memory as part of the training
             | dataset, then created a small variation of that.
             | 
             | That might be good enough for replacing Pexels, Unsplash or
             | any of those stock photo sites that blogs pull from. But
             | not much else.
        
               | SleekEagle wrote:
               | You don't think in a few years AI art will be
               | indistinguishable for human generated? In 2012, self
               | driving cars were a funny joke. A decade later, here they
               | are. I think AI is somehow chronically both overestimated
               | and underestimated
        
               | rchaud wrote:
               | Everything on Stock photo sites is human generated, free
               | and effectively infinite. In other words, commodified to
               | the point of having its market value be $0.
               | 
               | I'm sure this can be monetized to generate convincing AI
               | porn, but for non-porn uses, what will it replace? Deep
               | fried memes?
               | 
               | The only photos worth money are those of real people
               | photographed at real moments in time. Nobody ever bought
               | a Getty subscription for photorealistic clipart.
        
               | dougmwne wrote:
               | Stock images are not free. Hiring an artist to create a
               | concept or illustration based on your instructions is
               | also not free. Creating art assets for games is not free.
               | Copyright is a pretty big thing and these models
               | currently seem to sidestep it wonderfully.
               | 
               | Also I can generate a photo of Leonardo DiCaprio picking
               | his nose with a French fry, so that has some value for
               | me.
        
               | donkarma wrote:
               | self driving cars are still a funny joke
        
               | axg11 wrote:
               | You're going to be proven wrong in weeks to months. Just
               | a couple of years ago the consensus was that
               | DALL-E/Imagen/Stable Diffusion quality image generation
               | was impossible. Now it's very real and quality is
               | improving every month.
        
               | SleekEagle wrote:
               | This is the first time I've seen Stable diffusion. Is it
               | a new model or diffusion paradigm?
        
               | lucidrains wrote:
               | It is from the Heidelberg giants, Patrick Esser and Robin
               | Rombach
               | 
               | They continued building off their latent diffusion
               | direction (encode with vqgan-vae and then diffusion in
               | latent space)
               | 
               | All roads lead to rome
               | 
               | https://github.com/CompVis/stable-diffusion
               | https://arxiv.org/abs/2112.10752
        
               | SleekEagle wrote:
               | Interesting, thanks for the link. It seems that CLIP
               | encodings aren't as useful as frozen encoders from the
               | textual domain, which is a little unintuitive imo. Can't
               | keep up with all these advancements!
        
               | lucidrains wrote:
               | Ikr! Hang on, this ride is about to get crazy :)
        
               | ZetaZero wrote:
               | Agreed. I liken this to computer chess, and later
               | computer go. It was long believed both were impossible.
        
           | TulliusCicero wrote:
           | How would you even enforce a mandatory watermark? How do you
           | prove the work was AI-generated, at least for ones with no
           | obvious flaws?
        
             | SleekEagle wrote:
             | Exactly, it's just not feasible. Maybe they will train a
             | discriminator to determine which ones are generated, but I
             | don't think that would work very well. Also, DALL-E 2
             | images come with a watermark but I'm pretty sure there are
             | already tools to remove that...
        
               | mlsu wrote:
               | Imagine if they did manage to train a good discriminator!
               | 
               | That would lead to even higher quality images.
               | 
               | I support this effort.
        
               | stu2b50 wrote:
               | Creating a GAN feedback loop in real life
        
               | SleekEagle wrote:
               | Haha great point! AI always wins
        
               | bongoman37 wrote:
        
           | Baeocystin wrote:
           | I remember the stink-eye cast by (some) artists who grew up
           | with traditional media at how digital painting didn't count,
           | and was somehow 'cheating'. As if the masters of the past
           | wouldn't have loved having layers and control-z!
           | 
           | Same situation now. I know working artists thrilled with the
           | idea of being able to iterate in hours what previously would
           | have taken weeks to test composition, form, and the like as
           | they focus in on what they have in mind. I can't wait to see
           | what they come up with.
        
             | acomjean wrote:
             | I think Digital media is ok for most artists. Almost all
             | the commercial science visualization folks are using it
             | (based on a web-mini conference panel), and a fair number
             | of artist in the nonprofit I help out with use digital
             | tools.
             | 
             | I think this is different than machine generated art.
             | 
             | I know a few of us who have dabbled in creating
             | procedurally generated art have found it fun and useful for
             | some things, but kinda soulless, and less satisfying. AI
             | art gets around that by using huge training sets of human
             | generated stuff and mimicking. Its good and getting better,
             | but its not like you get exactly what you had envisioned
             | (though you get what you asked for)..
        
           | abriosi wrote:
           | I understand that artists are scared. Personally I look at it
           | as freedom. Having a tool like this in your artists toolkit
           | will augment performance by a stretch
        
             | SleekEagle wrote:
             | And, of course, these models learn in part from the art
             | generated by these artists. If we stop having humans create
             | art, we're no longer generating data to train the next
             | generation of models and so in some sense the "creativity"
             | of these models would seem to necessarily be hindered.
        
       | MuffinFlavored wrote:
       | Maybe put a screenshot of a few examples of what this homegrown
       | text-to-image model can produce at the end of the article?
        
         | SleekEagle wrote:
         | We'll be training it over the coming weeks and releasing a
         | checkpoint! Right now it is just the model source code
        
           | mbushey wrote:
           | Please let me know - it seems impossible to get trained
           | checkpoints for text to image.
        
             | SleekEagle wrote:
             | I'll be sure to post an update! It's not a Diffusion Model,
             | but I believe this VQGAN-CLIP implementation has weights
             | available - https://github.com/nerdyrodent/VQGAN-CLIP
        
       | ttul wrote:
       | Thank you for providing a git repo to go along with the
       | exceptionally detailed commentary!
        
         | SleekEagle wrote:
         | My pleasure! Thanks for the kind words :)
        
       ___________________________________________________________________
       (page generated 2022-08-17 23:02 UTC)