31–40 of 123 posts
What'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
Earlier quoted context omitted.
In my experience, scraping the data is the easy part. Once you've scraped it you've got to get rid of all the garbage, which is where the issues arise, especially if you're just blindly scraping everything you can find. For example, in a generative model I'm working on, I have a dataset consisting of ~5M images just blindly scraped from a website. After filtering, this drops down to ~500k images, yet a model trained…
Which is why porn is such a great dataset for crowdsource: - lots of people are stimulated by it - lots of people want DALL-E-2 for porn - and lots of people are willing to work towards that common goal The beauty of this is that people are just going to keep coming and coming to it. Like I'm trying to be mature and serious about this. What's it going to take? - Community responsible for scraping dataset, generating…
I guess the primary concern with a porn model would be the ethics of it, which might turn off any company from helping out on training resources (for example, Google's TPU Research Cloud requires you to follow their code of ethics on AI, which would be very difficult to do with a topic as sensitive to people as porn).
What'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
And what is going to take to generate videos, not pictures?
What 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?
I guess the stock photos industry will be disrupted by this.
How much would it cost to train something like this? Is there even a good dataset for it?
There is a dataset of 5 billion image-text pairs (laion-5b) scraped by various parties. This can then be filtered and used to train these models. Cost is a bit of an issue but there are orgs that have provided compute for open model training. And Imagen is nice because the text encoder part is already available and doesn't need more training, so it would just be the diffusion model components being trained. I'd guess…
Earlier quoted context omitted.
And what is going to take to generate videos, not pictures?
To run we must learn to walk first. To walk we must learn to be erect. To be erect we must master crawling. I don't think the leap is too crazy if we are talking short moving pictures without sound. However, when sound gets involved, this is where it would become very tricky.
Earlier quoted context omitted.
Publishing high impact research gives credibility to the ML teams, which helps recruiting and prestige. It's less cynical, more incentive alignment.
Also good for society. Less evil, more nice people. Respect Google for these traits.
Open source is pretty meaningless here