Live data from Hacker News

Adventure game graphics with DALL-E 2

hpjansson.org

51–60 of 162 posts

Re: Adventure game graphics with DALL-E 2

#51
>rustic mexican mansion with a grassy area sports car parked in front surrounded by small houses on a sunny day, high quality atmospheric high renaissance oil on canvas

The picture related to that one looks more like Provence /Marseille aera than truly Mexico.

Basically there is a small mount nearby Marseille that looks exactly like that and obviously was used in many paints.

The house and pine tree really looks like villa in Provence, and with that small mount in the background... Yeah I feel at home :o

While the paint is largely different, I have seen much closer look alike in the past but from a famous French painter https://fr.m.wikipedia.org/wiki/Paul_C%C3%A9zanne#/media/Fic...

Re: Adventure game graphics with DALL-E 2

#52
post #44

Earlier quoted context omitted.

It's not about what we need. Scientific research in this case has been the result of looking around and seen what can be done with the technology at hand without caring if it was what we need or don't. If you feel like "we" should be automating other stuff, you are free to make your own contribution, it's not like OpenAI owns the keys to the field.

But the people at OpenAI aren’t doing it as a hobby, they’ve got a lot of money to conduct this research (from Wikipedia: “The organization was founded in San Francisco in late 2015 by Elon Musk, Sam Altman, and others, who collectively pledged US$1 billion.” [1]) This is the misallocation of resources I’m referring to. [1] https://en.wikipedia.org/wiki/OpenAI

I don't understand where the misallocation of resources is. OpenAI is no longer a non-profit organization. Its goal is not to automate what is most needed now. But to advance the field of AI.

Re: Adventure game graphics with DALL-E 2

#54

Here are a couple I did: >looking up at a massive art deco archway with huge beautifully ornate door, tessellated like the ceilings of Iranian holy mosques with the dimensions symbolizing sacred geometry and celestial lighting 8k detail* https://imgur.com/gallery/QulgbtM - https://imgur.com/gallery/GNgZ4hu https://imgur.com/gallery/TIBALCT

These are subtly nightmarish to me, especially the first. The beauty of such ornate mosaics (in the real world) is the clean, symmetric geometry. Ironically, that's the sort of thing you might naively think a computer could be especially good at (compared to more "organic" subject matter). These are evocative of tiles Islamic mosques if you squint at them, but if you look closely they're a blurry tangled mess. I woul…

DALLE can’t render fine detail at a distance of more than a meter or so. Possibly because OpenAI limits how many diffusion steps are used for each image.

Re: Adventure game graphics with DALL-E 2

#56
post #26

I started off feeling hopeful/excited by OpenAI, GPT-3, DALL-E, etc, as a creator/writer. As time has progressed and I've used these tools and other machine learning tools to create media, I've become disillusioned. It feels as if this is about to explode an existing problem, namely, there's too much content in the world already. Lowering the effort bar for content creation and generation is, in some ways, going to c…

We're at the beginning of a rapidly evolving situation where out of the blue it is now possible to direct an AI to produce imagery that is interesting using just language. From there to moving animations is a relatively small step and already being worked on. From there to photo realistic scenes directed by just words not that big of a leap either and also something that is being worked on. Are there constraints, gli…

The quality of the upper echelon of art may be raised, but there's still a discovery problem there. Having to sift through stuff to find the gems is already an issue imo. The OP makes a decent (pessimistic) point

Re: Adventure game graphics with DALL-E 2

#57
I’m concerned about the precedent DALL-E 2 is setting. Learning skills, whether it be drawing, painting, or otherwise, should not be a “problem” that needs to be solved with AI. The joy of creating is in the journey, not the destination. I can’t imagine any fulfillment from glueing together auto-generated content. It’s the art equivalent of a CRUD app.

Re: Adventure game graphics with DALL-E 2

#58
post #48

DALL-E is next level. I'm still waiting for the day where I'd get to play a fully AI generated game with a generated story line; one that rapidly changes according to the decisions made by the player. That would be insane.

Maybe you are already playing it. Or am I?

Re: Adventure game graphics with DALL-E 2

#59
post #57

I’m concerned about the precedent DALL-E 2 is setting. Learning skills, whether it be drawing, painting, or otherwise, should not be a “problem” that needs to be solved with AI. The joy of creating is in the journey, not the destination. I can’t imagine any fulfillment from glueing together auto-generated content. It’s the art equivalent of a CRUD app.

I’m a non-creative person. Sometimes I need to ask artist for an art. Dalle would help me to give and idea.

Re: Adventure game graphics with DALL-E 2

#60
post #44

Earlier quoted context omitted.

It's not about what we need. Scientific research in this case has been the result of looking around and seen what can be done with the technology at hand without caring if it was what we need or don't. If you feel like "we" should be automating other stuff, you are free to make your own contribution, it's not like OpenAI owns the keys to the field.

But the people at OpenAI aren’t doing it as a hobby, they’ve got a lot of money to conduct this research (from Wikipedia: “The organization was founded in San Francisco in late 2015 by Elon Musk, Sam Altman, and others, who collectively pledged US$1 billion.” [1]) This is the misallocation of resources I’m referring to. [1] https://en.wikipedia.org/wiki/OpenAI

And that's all highly speculative, betting on money to somehow show up, for reasons impossible to predict, if only enough games are changed sufficiently hard. If it can be done it will be done, unless we fundamentally change the way we run the economy.

Conclusions:

(1) Perhaps we should, winning at net zero games is very much a thing in the current way

(2) Didn't know it when I started writing this reply (not at all!), but I guess I agree with you

(3) I really miss Old Google, and how we happily trusted them (deservedly or not)

Post reply on HN