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

DALL·E now available in beta

openai.com

Post reply on HN
Print view View original

331–340 of 579 posts

Re: DALL·E now available in beta

#331

Post by erikpukinskis »

bequanna wrote: post #220
scifibestfi wrote: post #67

Earlier quoted context omitted.

The latter. Here's what we, a small number of people, think the world should look like according to our own biases and information bubble in the current moment. We will impose our biases upon you, the unenlightened masses who must be manipulated for your own good. And for god sakes, don't look for photos of the US Math team or NBA Basketball or compare soccer teams across different countries and cultures.

> Here's what we, a small number of people, think the world should look like according to our own biases and information bubble in the current moment. You're being quite charitable. It is much more likely that optics and virtue signaling is behind this addition.

If I search for “food” I don’t want to see a slice of pizza every time, even if that’s the #1 food. I want to see some variety.

I think you’re jumping to quickly to bad intentions. Injecting diversity of results is a sane thing to do, totally irrespective of politics.

Re: DALL·E now available in beta

#332

Post by c0decracker »

andybak wrote: post #87
c0decracker wrote: post #43

Interesting. I got access couple weeks ago (was on waitlist since the initial announcement) and frankly as much as really want to be excited and like it, DALL-E ended up being a bit underwhelming. IMHO - often results that produced are of low quality (distorted images, or quite wacky representation of the query). Some styles of imagery are certainly a better fit for being generated by DALL-E, but as far as commercial…

I also got access a couple of weeks ago and I can't fathom how anyone could be underwhelmed by it. What were you expecting?

Fundamentally I have two categories of issues I see with DALL-E, but please don't get me wrong -- I think this is a great demonstration of what is possible with huge models and I think OpenAI work in general is fantastic. I will most certainly continue using both DALL-E and OpenAI's GPT3. (1) Between what DALL-E can do today and commercial utility is a rift in my opinion. I readily admit that I am have not done hundreds of queries (thank you folks for pointing that out, I'll practice more!) but that means that there is a learning curve, isn't it? I can't just go to DALL-E, mess with it for 5-10 minutes and get my next ad or book cover or illustration for my next project done? (2) I think DALL-E has issues with faces and human form in general. Images it produces are often quite repulsive and take the uncanny valley to the next level. I absolutely surprise myself when I noticed thinking that images with humans DALL-E produced lack of... soul? Cats and dogs on the other hand it handles much better. I done tests with other entities --- say cars or machinery -- and it generally performs so so with them too, often creating disproportionate representations of them or misplacing chunks. If you're querying for multiple objects on a scene it quite often melds them together. This is more pronounced in photorealistic renderings. When I query for painting-style it works mostly better. That said every now and then it does produce a great image, but with this way of arriving at it, how fast I'll have to replenish those credits?.. :)

All in all though I think I am underwhelmed mostly because my initial expectations were off, I am still a fan of DALL-E specifically and GPT3 in general. Now when is GPT4 coming out? :)

Re: DALL·E now available in beta

#333

Post by zerocrates »

bpicolo wrote: post #197
redox99 wrote: post #177

Earlier quoted context omitted.

DALL-E 2 isn't good enough for such photorealistic pictures with humans as of yet however.

https://twitter.com/TobiasCornille/status/154972906039745331... Unless I'm missing something, these seem pretty darn good

Woof, that bias "solution" that that thread is actually about though...!

Re: DALL·E now available in beta

#334

Post by speedgoose »

smusamashah wrote: post #286
xnx wrote: post #76

I fully expect stock image sites to be swamped by DALL-E generated images that match popular terms (e.g. "business person shaking hands"). Generate the image for $0.15. Sell it for $1.00.

They won't. DALL-E images are mostly not as high quality. The high quality stuff which everyone has been sharing is result of lots of cherry picking.

In my experience it doesn’t require that much cherry picking if you use a carefully crafted prompt. For example: “ A professional photography of a software developer talking to a plastic duck on his desk, bright smooth lighting, f2.2, bokeh, Leica, corporate stock picture, highly detailed”

And this is the first picture I got: https://labs.openai.com/s/lSWOnxbHBYQAtli9CYlZGqcZ

It got it a bit strong on the depth of field and I don’t like the angle but I could iterate a few times and get a good one.

Re: DALL·E now available in beta

#335

Post by pwillia7 »

slavak wrote: post #311
zanderwohl wrote: post #294

Earlier quoted context omitted.

Somehow these articles are more readable than typical AI-generated search engine fodder... Is it because I'm entering the site with an expectation of nonsense?

Probably because, by the creator's own admission, the articles are heavily cherry-picked to make sure the output is decent, which is probably a lot more human effort than goes into the aforementioned search engine fodder. http://dailywrong.com/sample-page/

I would guess that most Spam farms are not using openAI davinci model which is really really good, but expensive. Just a guess.

Re: DALL·E now available in beta

#336

Post by drusepth »

bemmu wrote: post #58

I was supposed to be making a video game, but got a bit sidetracked when DALL·E came out and made this website on the side: http://dailywrong.com/ (yes I should get SSL). It's like The Onion, but all the articles are made with GPT-3 and DALL·E. I start with an interesting DALL·E image, then describe it to GPT-3 and ask it for an Onion-like article on the topic. The results are surprisingly good.

Haha, I was in a very similar boat when I built https://novelgens.com -- I was also supposed to be making a video game, but got a bit sidetracked with VQGAN+CLIP and other text/image generation models.

Now I'm using that content in the video game. I wonder if you could use these articles as some fake news in your game, too. :)

Re: DALL·E now available in beta

#337

Post by jug »

isoprophlex wrote: post #296

Wait until someone trains a model like this, for porn. There seems to be a post-DALLE obscenity detector on openAI's tool, as so far I've found it to be entirely robust against deliberate typos designed to avoid simple 'bad word lists'. Ask it for a "pruple violon" and you get purple violins... you get the deal. "Metastable" prompts that may or may not generate obscene (content with nudity, guns, violence as I've fou…

I’ve thought about this and in fact porn generation sounds like a good thing?? It ensures that it’s victimless. Of course, there is a problem with generation of illegal (underage) porn but other than this, I think it could be helpful for this world.

Re: DALL·E now available in beta

#338

Post by astrange »

educaysean wrote: post #275
bequanna wrote: post #269

Earlier quoted context omitted.

You would presumably input “South Korean CEO”. DALL-E would then unhelpfully add “black” “female” without your knowledge.

I just tried it out and it looks like DALL-E isn't as inept as you imagined. Exact query used was 'A profile photo of a male south korean CEO', and it spat out 4 very believable korean business dudes. Supplying the race and sex information seems to prevent new keywords from being injected. I see no problem with the system generating female CEOs when the gender information is omitted, unless you think there are?

I don't think they "randomly insert keywords" like people are claiming, I think they probably run it through a GPT3 prompt and ask it to rewrite the prompt if it's too vague.

I set up a similar GPT prompt with a lot more power ("rewrite this vague input into a precise image description") and I find it much more creative and useful than DALLE2 is.

Re: DALL·E now available in beta

#339

Post by astrange »

andybak wrote: post #239
throwaway0x7E6 wrote: post #217

Earlier quoted context omitted.

I've only seen this thing https://huggingface.co/spaces/dalle-mini/dalle-mini is it not dall-e?

It's a reimplementation. It's a long way off in terms of quality (at the moment anyway)

It's a model inspired by DALLE 1 but it's not even very close to that.

But it does seem to know a lot of things the real DALLE2 doesn't.

Re: DALL·E now available in beta

#340

Post by astrange »

mensetmanusman wrote: post #131
daemoens wrote: post #115

Earlier quoted context omitted.

It's not a political standard though. There is actual diversity in this world. Why wouldn't you want that in your product?

Fix the data input side, not the data output side. The data input side is slowly being fixed in real time as the rest of the world gets online and learns these methods.

That wouldn't necessarily fix the issue or do anything. A model isn't a perfect average of all the data you throw into its training set. You have to actually try these things and see if they work.
Post reply on HN