I get the impression that maybe DALL-E 2 produces slightly more diverse images? Compare Figure 2 in this paper with Figures 18-20 in the DALL-E 2 paper.
Imagen, a text-to-image diffusion model
241–250 of 661 posts
Re: Imagen, a text-to-image diffusion model
#242Earlier quoted context omitted.
Very certainly not, since use is individual and thus a function of competence. So, adherence to meaning depends on the user. Conflict resolution? And anyway - contextually -, the representational natures of "use" (instances) and that of "meaning" (definition) are completely different.
Humans overwhelmingly learn meaning by use, not by definition.
> Humans overwhelmingly learn meaning by use, not by definition
Preliminarily and provisionally. Then, they start discussing their concepts - it is the very definition of Intelligence.
Re: Imagen, a text-to-image diffusion model
#243Earlier quoted context omitted.
it isn't woke enough. Lol.
In discussions like this, I always head for the gray-text comments to enjoy the last crumbs of the common sense in this world.
... and to witness the downvoters so that their cowardly disgust towards truth could buy them some extra time in hell :)
Re: Imagen, a text-to-image diffusion model
#244Earlier quoted context omitted.
it isn't woke enough. Lol.
In discussions like this, I always head for the gray-text comments to enjoy the last crumbs of the common sense in this world.
Get offline and talk to people in meat-space. You're likely to find them to be much more reasonable. :)
Re: Imagen, a text-to-image diffusion model
#245Interesting and cool technology - but I can't seem to ignore that every high-quality AI art application is always closed, and I don't seem to buy the ethics excuse for that. The same was said for GPT, yet I see nothing but creativity coming out from its users nowadays.
GTP-3 was an erotica virtuoso before it was gagged. There's a serious use case here in endless porn generation. Google would very much like to not be in that business.
That said, you can download Dream by Wombo from the app store and it is one of the top smartphone apps, even though it is a few generations behind state of the art.
Re: Imagen, a text-to-image diffusion model
#246Earlier quoted context omitted.
I wonder why they don't like the idea of autogenerated porn... They're already putting most artists out of a job, why not put porn stars out of a job too?
Copenhagen ethics (used by most people) require that all negative outcomes of a thing X become yours if you interact with X. It is not sensible to interact with high negativity things unless you are single-issue. It is logical for Google to not attempt to interact with porn where possible.
> Copenhagen ethics (used by most people)
The idea that most people use any coherent ethical framework (even something as high level and nearly content-free as Copenhagen) much less a particular coherent ethical framework is, well, not well supported by the evidence.
> require that all negative outcomes of a thing X become yours if you interact with X. It is not sensible to interact with high negativity things unless you are single-issue.
The conclusion in the final sentence only makes sense if you use “interact” in an incorrect way describing the Copenhagen interpretation of ethics, because the original description is only correct if you include observation as an interaction. By the time you have noted a thing is “high-negativity”, you have observed it and acquired responsibility for it's continuation under the Copenhagen interpretation; you cannot avoid that by choosing not to interact once you have observed it.
Re: Imagen, a text-to-image diffusion model
#247Earlier quoted context omitted.
In discussions like this, I always head for the gray-text comments to enjoy the last crumbs of the common sense in this world.
Get offline and talk to people in meat-space. You're likely to find them to be much more reasonable. :)
Yep, the meat-space is generally a bit less woke than HN, so thanks for the reminder ))
Re: Imagen, a text-to-image diffusion model
#248Earlier quoted context omitted.
Translation: AI has the potential to transform society. When we release this model to the public it will be used in ways we haven’t anticipated. We know the model has bias and we need more time to consider releasing this to the public out of concerns that this transformative technology further perpetuate mistakes that we’ve made in our recent past.
> it will be used in ways we haven’t anticipated Oh yeah, as a woman who grew up in a Third World country, how an AI model generates images would have deeply affected my daily struggles! /s It's kinda insulting that they think that this would be insulting. Like "Oh no I asked the model to draw a doctor and it drew a male doctor, I guess there's no point in me pursuing medical studies" ...
It's not meant to prevent offence to you. It is meant to be a "good product" by the metrics of their creators. And quite simply, everyone here incapable of making the thing is unlikely to have an image of what a "good product" here is. More power to them for having a good vision of what they're building.
Re: Imagen, a text-to-image diffusion model
#249Interesting and cool technology - but I can't seem to ignore that every high-quality AI art application is always closed, and I don't seem to buy the ethics excuse for that. The same was said for GPT, yet I see nothing but creativity coming out from its users nowadays.
You're aware of nothing but creativity from its users. The people using the technology unethically intentionally don't advertise that they're using it.
There's mountains of ai-generated inauthentic content that companies (including Google) have to filter out of their services. This content is used for spam, click farms, scamming, and even state propaganda operations. GPT-2 made this problem orders of magnitude worse than it used to be, and each iteration makes it harder to filter.
The industry term is (generally) "Coordinated Inauthentic Behavior" (though this includes uses of actual human content). I think Smarter Every Day did a good videos (series?) on the topic, and there are plenty of articles on the topic if you prefer that.
Re: Imagen, a text-to-image diffusion model
#250Interesting and cool technology - but I can't seem to ignore that every high-quality AI art application is always closed, and I don't seem to buy the ethics excuse for that. The same was said for GPT, yet I see nothing but creativity coming out from its users nowadays.
That only lasts until the community copies the paper and catches up. For example the open source DALLE-2 implementation is coming along great:
https://github.com/lucidrains/DALLE2-pytorch