Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

DALL·E: Introducing Outpainting

openai.com

Post reply on HN
Print view View original

211–220 of 302 posts

Re: DALL·E: Introducing Outpainting

#211

Post by skybrian »

Tepix wrote: post #108
skybrian wrote: post #85

Earlier quoted context omitted.

Running this at home is only free like mining cryptocurrency is free if you didn't buy your computer and don't pay for the electricity. Plus you can only run it on the computer that has the good graphics card, which probably isn't your laptop. I expect most people aren't going to be generating images all day, so using a cloud-based service for occasional use will still make a lot of sense. Stable Diffusion offers a p…

It does run on Apple silicon. 55 seconds in M1 Pro (vs 15 seconds on RTX 3070).

That's pretty good, but with that level of latency, I can still see people paying to use an online service that's faster. Maybe they'll speed it up more, though?

Re: DALL·E: Introducing Outpainting

#212

Post by Blackthorn »

ItsTooMuch wrote: post #204
aabhay wrote: post #33

Earlier quoted context omitted.

Their research is closed -- they don't release model weights, nor in most cases the training or model scripts. Certain things they release, just like any other for-profit research firm.

As the sibling says, in academia this is already more than open...

Open means something. It is a, for lack of a better phrase, virtue signal. When you do that but don't actually represent the virtue you are trying to signal, people will understandably get pretty upset about that.

Re: DALL·E: Introducing Outpainting

#213

Post by nomel »

bergenty wrote: post #209
nomel wrote: post #110

Earlier quoted context omitted.

> I can only guess either safety from misuse I still don't understand what this would mean. Where are all of the terrible things that were supposed to happen, now that Stable Diffusion is available? We've been able to create completely photorealistic fiction for decades now. See any movie with CGI for an example of whole worlds, and people, that don't exist. The bar has gradually been lowering (see the amazing CGI th…

It’s been a week, there is going to be an explosion of believable fake items that are going to be used to lure people in to even more unbelievable conspiracy theories than there currently exist. Your average conspiracy nut didn’t have the skills or know how before, but they sure do now. Also you’re probably not seeing all the pedo content that people are already generating for themselves.

> be an explosion of believable fake items

I think that's a good thing. A slow creep is dangerous, because people may not notice, and would be tricked. An explosion of insanity makes everyone realize they can't believe everything they see on the internet.

Re: DALL·E: Introducing Outpainting

#214

Post by ItsTooMuch »

Blackthorn wrote: post #212
ItsTooMuch wrote: post #204

Earlier quoted context omitted.

As the sibling says, in academia this is already more than open...

Open means something. It is a, for lack of a better phrase, virtue signal. When you do that but don't actually represent the virtue you are trying to signal, people will understandably get pretty upset about that.

The notion of open in software and in academia is different, that for sure. But does that make one or the other wrong? My friends doing physics or math don't understand the hate at all when I discuss it with them. From their point of view, you don't have to pay hundreds of dollars to read it = it's open. The research is there, code is left as exercise to the reader - that's also normal to them... And the notion of giving away free compute time is funny to them. Run your own cluster, they say.

I'm not saying I agree with them, I'm a software person and open means to me what it means to you. I'd prefer if it was truly open by our definition. But I don't think we can bash the choice of the word so easily.

Re: DALL·E: Introducing Outpainting

#215

Post by astrange »

astrange wrote: post #116

I cannot get this to work properly (in Safari). It just won't regenerate anything above or to the left of the image; it acts like I selected the opposite sides if I try it.

Looks like they pushed a fix. Now I'm getting funny "you get what you asked for" issues; if my prompt mentions a face, then using outpainting to create a 16:9 background behind it doesn't work so well - it just starts making more faces.

Re: DALL·E: Introducing Outpainting

#216

Post by bergenty »

nomel wrote: post #213
bergenty wrote: post #209

Earlier quoted context omitted.

It’s been a week, there is going to be an explosion of believable fake items that are going to be used to lure people in to even more unbelievable conspiracy theories than there currently exist. Your average conspiracy nut didn’t have the skills or know how before, but they sure do now. Also you’re probably not seeing all the pedo content that people are already generating for themselves.

> be an explosion of believable fake items I think that's a good thing. A slow creep is dangerous, because people may not notice, and would be tricked. An explosion of insanity makes everyone realize they can't believe everything they see on the internet.

It will be all of the above so it doesn’t really matter since it’s all going to be indistinguishable from the real thing.

Re: DALL·E: Introducing Outpainting

#217

Post by canoebuilder »

nomel wrote: post #110
nabakin wrote: post #101

Earlier quoted context omitted.

Doesn't make sense to me why OpenAI has kept DALL-E closed source for so long. I can only guess either safety from misuse or leveraging it for money. At this rate though, Stable Diffusion is going to dwarf it

> I can only guess either safety from misuse I still don't understand what this would mean. Where are all of the terrible things that were supposed to happen, now that Stable Diffusion is available? We've been able to create completely photorealistic fiction for decades now. See any movie with CGI for an example of whole worlds, and people, that don't exist. The bar has gradually been lowering (see the amazing CGI th…

(see the amazing CGI that YouTubers do these days)

Any favorite examples?

Re: DALL·E: Introducing Outpainting

#219

Post by fleddr »

dsmmcken wrote: post #44

The UX is evolving around AI image generation so fast, everyday is something new. There's so much greenfield exploration space for new interaction models. 6 months from now, how we interact with these models will probably look entirely different.

Comments made just 3 days ago, "well...it can't do that", are already obsolete. I've never seen innovation at this breakneck speed. We're talking a WEEK since release.

Re: DALL·E: Introducing Outpainting

#220

Post by bottlepalm »

bottlepalm wrote: post #192
boppo1 wrote: post #131

Earlier quoted context omitted.

I actually paint and spend a lot of time looking at 'serious' paintings. AI hasn't even scratched the field to a trained eye. Doesn't mean I'm not excited though. This kind-of feels like I'm watching the camera or printing press being invented. Everyone is comparing it to fine art, but I think ultimately it's going in a different and bigger direction.

I've heard this a lot, luckily it's not that hard to test if you can really tell the difference. We need someone to create the 'AI Pepsi challenge' for artists to settle this.

That was fast, looks like artists can't tell, AI wins first prize in an art competition!

https://www.vice.com/en/article/bvmvqm/an-ai-generated-artwo...

Post reply on HN