Impressive results no doubt, but I’m reserving judgment until beta access is available. These are probably the best images that it can generate, but what I’m most interested in is the average case.
Dall-E 2
31–40 of 511 posts
Re: Dall-E 2
#32Some freely available models GLID-3: https://colab.research.google.com/drive/1x4p2PokZ3XznBn35Q5B... and a new Latent Diffusion notebook: https://colab.research.google.com/github/multimodalart/laten... have both appeared recently and are getting remarkably close to the original Dall-E (maybe better as I can't test the real thing...) So - this was pretty good timing if OpenAI want to appear to be ahead of the pack. Of…
They're also not censored on the dataset front and thus produce much more interesting outputs.
OpenAI has a low resolution checkpoint for similar functionality as this - called GLIDE - and the output is super boring compared to community driven efforts, in large part because of similar dataset restrictions as this likely has been subjected to.
Re: Dall-E 2
#33Is this bringing us closer to combining image and language understanding within one model?
Re: Dall-E 2
#34What confusing pricing[1]: > Prices are per 1,000 tokens. You can think of tokens as pieces of words, where 1,000 tokens is about 750 words. This paragraph is 35 tokens. Further down, in the FAQ[2]: > For English text, 1 token is approximately 4 characters or 0.75 words. As a point of reference, the collected works of Shakespeare are about 900,000 words or 1.2M tokens. > To learn more about how tokens work and estima…
This is for their GPT models, not Dall-E. I don't think they have released any pricing information for Dall-E yet, as it is still in waitlist mode.
Re: Dall-E 2
#35Very cool stuff. For me, the most interesting was the ability to take a piece of art and generate variations of it. Have a favorite painter? Here's 10,000 new paintings like theirs.
Well, one of my favorite painters is Henri Rousseau, and one of his great paintings is War, 1984:
https://www.henrirousseau.net/war.jsp
However, this painting has themes of violence and politics plus some nude dead bodies, so it violates the content policy: "Our content policy does not allow users to generate violent, adult, or political content, among other categories."
So what you'd get is some kind of sanitized watered-down tepid version of Rossueau, the kind of boring drivel suitable for corporate lobbies everywhere, guaranteed not to offend or disturb anyone. It's difficult to find words... horrific? dystopian? atrocious? No, just no.
Re: Dall-E 2
#36The timing of the Dall-E 2 launch an hour ago seems to correspond with a recent piece of investigative journalism by Buzzfeed News about one of Sam Altman's other ventures, published 15 hours ago and discussed elsewhere actively on HN right now: https://news.ycombinator.com/item?id=30931614 I point this out because while Dall-E 2 seems interesting (I'm out of my depth, so delegating to the conversation taking place h…
Maybe I’m naive, but I see this as a coincidence. If it was an hour later, then maybe there would be something.
Re: Dall-E 2
#37This is incredible work.
From the paper:
> Limitations > Although conditioning image generation on CLIP embeddings improves diversity, this choice does come with certain limitations. In particular, unCLIP [Dall-E 2] is worse at binding attributes to objects than a corresponding GLIDE model.
The binding problem is interesting. It appears that the way Dall-E 2 / CLIP embeds text leads to the concepts within the text being jumbled together. In their example "a red cube on top of a blue cube" becomes jumbled and the resulting images are essentially: "cubes, red, blue, on top". Opens a clear avenue for improvement.
Re: Dall-E 2
#38Am I the only one to think that the AI world is divided into 2 groups: 1. Deepmind, who solved go, protein folding, and that seems really onto something. 2. Everyone else, spending billions to build machines that draw astronauts on unicorns, and smartish bot toys.
OpenAI is one of the leading companies in AI that makes models with real world applications. I don't see their efforts as misdirected or futile in anyway. If anything I'm always impressed with their announcements because it's always mind blowing what their models can do!
The same technology that is drawing cute unicorns can be used for endless other use cases. Perhaps the PR side of the launch and the subject matter they show unveil their product is just that, PR.
It's like Apple Memoji thing (not sure if I'm spelling it correctly). You can think of as trivial and waste of talent to use their Camera/FaceID to animate cute animals based on facial expression, but that same tech will enable lots other things to come.
Re: Dall-E 2
#39The timing of the Dall-E 2 launch an hour ago seems to correspond with a recent piece of investigative journalism by Buzzfeed News about one of Sam Altman's other ventures, published 15 hours ago and discussed elsewhere actively on HN right now: https://news.ycombinator.com/item?id=30931614 I point this out because while Dall-E 2 seems interesting (I'm out of my depth, so delegating to the conversation taking place h…
What's the idea here? They quickly put out this to somehow hide other stories?
Yes, especially given there's no actual product release, only a waitlist.
Easy to put together a marketing piece on short notice or potentially even push a pending marketing page out to production with a waitlist rather than links to production or even beta quality services.
Re: Dall-E 2
#40Something about this makes me nauseous. Perhaps is the fact that soon the market value for creatives is going to fall to a hair about zero for all but the most famous. We will be all the poorer for it when 95% of images you see are AI generated. There will be niches of course but in a few short years it'll be over for a huge swathe of creative professionals who are already struggling. Some of the images also hit me w…
Can I opt-out from ever seeing AI generated images please?