Earlier quoted context omitted.
Also good for society. Less evil, more nice people. Respect Google for these traits.
Oh, they don't even want to create/release a usable image search... Respect, of course.
Implementation of Imagen, Google's text-to-image neural network, in PyTorch
61–70 of 123 posts
Re: Implementation of Imagen, Google's text-to-image neural network, in PyTorch
#62Earlier quoted context omitted.
Training an AI requires high quality, clean/normalized data, which is very difficult to do at millions/billions of data points and is very frequently done incorrectly with silent failures.
There's a section of the internet where you can easily find billions of images or can be generated from moving pictures. Even upscaled. I really didn't expect to have to spell it out. hint: they are all about one thing and there are a lot of eager volunteers to help on those websites. It would be easy to "normalize/clean/classify" because the pictures would have a consistent theme, thus reducing the amount of paramet…
Re: Implementation of Imagen, Google's text-to-image neural network, in PyTorch
#63What is the reason Google published their research details about Imagen? Why don't they just keep their findings to themselfes and build products on top of them? Public companies can't do stuff just for the fun of it, right? So there must be some commercial reasoning behind it?
Re: Implementation of Imagen, Google's text-to-image neural network, in PyTorch
#64What is the reason Google published their research details about Imagen? Why don't they just keep their findings to themselfes and build products on top of them? Public companies can't do stuff just for the fun of it, right? So there must be some commercial reasoning behind it?
Two reasons: 1) Even though it's all technically very impressive, so far there's not a huge amount of commercialization potential here. OpenAI is charging for its GPT-3 model but its revenue is probably negligible next to the hardware costs (sunk + ongoing) to train it in the first place, let alone the researcher salaries they're paying 2) Most of the stunning examples are cherry-picked. These things fail much more o…
Rule 1 of working in this field, recruit a mid level member of the other company's research group biannually to get the latest gossip.
It's impossible to keep a 1 page or shorter "algorithm" secret, when the creators are geniuses and they hop jobs every year or so.
Fellas with more IQ than games in a baseball season, they just don't forget.
Re: Implementation of Imagen, Google's text-to-image neural network, in PyTorch
#65Earlier quoted context omitted.
Two reasons: 1) Even though it's all technically very impressive, so far there's not a huge amount of commercialization potential here. OpenAI is charging for its GPT-3 model but its revenue is probably negligible next to the hardware costs (sunk + ongoing) to train it in the first place, let alone the researcher salaries they're paying 2) Most of the stunning examples are cherry-picked. These things fail much more o…
I'm currently working fulltime on AI-powered design suite Accomplice ( https://accomplice.ai ) and if you ask me on a good day I would tell you I do think there's already huge commercial potential. On a bad day, though ;) My current approach is a "model marketplace" ( https://accomplice.ai/models ) where the most popular open source text-to-image models (VQGAN+CLIP, Disco Diffusion, DALL-E Mega coming soon…), sit alo…
What does that link do?
Re: Implementation of Imagen, Google's text-to-image neural network, in PyTorch
#66Earlier quoted context omitted.
Two reasons: 1) Even though it's all technically very impressive, so far there's not a huge amount of commercialization potential here. OpenAI is charging for its GPT-3 model but its revenue is probably negligible next to the hardware costs (sunk + ongoing) to train it in the first place, let alone the researcher salaries they're paying 2) Most of the stunning examples are cherry-picked. These things fail much more o…
I'm currently working fulltime on AI-powered design suite Accomplice ( https://accomplice.ai ) and if you ask me on a good day I would tell you I do think there's already huge commercial potential. On a bad day, though ;) My current approach is a "model marketplace" ( https://accomplice.ai/models ) where the most popular open source text-to-image models (VQGAN+CLIP, Disco Diffusion, DALL-E Mega coming soon…), sit alo…
Re: Implementation of Imagen, Google's text-to-image neural network, in PyTorch
#67Re: Implementation of Imagen, Google's text-to-image neural network, in PyTorch
#68What's it going to take to train this on porn? This is something that can be crowdfunded. Look deepnude is a thing and somebody is making money off it: https://app.deepnude.cc/upload
What you describe is already illegal on many jurisdictions.
Re: Implementation of Imagen, Google's text-to-image neural network, in PyTorch
#69What's it going to take to train this on porn? This is something that can be crowdfunded. Look deepnude is a thing and somebody is making money off it: https://app.deepnude.cc/upload
How can this be the most upvoted comment? What you describe is already illegal on many jurisdictions.
Are you talking about porn? Or using potential copyright material in an infringing manner? Or perhaps the possibility of "deepfake" porn?
Re: Implementation of Imagen, Google's text-to-image neural network, in PyTorch
#70Earlier quoted context omitted.
I'm currently working fulltime on AI-powered design suite Accomplice ( https://accomplice.ai ) and if you ask me on a good day I would tell you I do think there's already huge commercial potential. On a bad day, though ;) My current approach is a "model marketplace" ( https://accomplice.ai/models ) where the most popular open source text-to-image models (VQGAN+CLIP, Disco Diffusion, DALL-E Mega coming soon…), sit alo…
I wanted to try your site, but after clicking on the link in the email, it tries to send me through some redirectingat.com link which is blocked by my ad blocker. What does that link do?
The confirmation link should only be going to accomplice.ai unless Sendgrid is doing some link tracking that I've just forgotten about. Could you forward that email to adam at accomplice dot ai if you get a chance. Thanks for letting me know!