Live data from Hacker News

Adventure game graphics with DALL-E 2

hpjansson.org

91–100 of 162 posts

Re: Adventure game graphics with DALL-E 2

#91
post #72

Earlier quoted context omitted.

The direct application is instant illustration. It's called "art" because it has less requirements and can't be objectively judged. There is a long way to becoming useful, but it can have a very real world impact in everyday jobs. Lots of people losing their jobs over this also means more available workforce for those more important jobs of yours

I wasn’t seriously expecting investment to change, just kinda funny/sad that in this case the thing getting automated is something humans enjoy doing (illustrating) rather than many things they both don’t enjoy and need more (street cleaning, construction work, menial physical labor in general). So you think in your example illustrators taking up street cleaning work will result in an overall improvement of life for…

This is what I'm thinking as well. I would go so far to say that it's directly evil to automate away illustration and other forms of creativity. Sure, many people will think it's cool and useful, but so many people will see their reason to live taken away from them. This is not only about making a living, creative arts is something much deeper and meaningful for lots of people.

I wish we could spend our collective brainpower applying AI to fight disease, climate change and poverty instead. That would make life better.

Re: Adventure game graphics with DALL-E 2

#92

Earlier quoted context omitted.

The first thing I thought when reading this was "wow, someone must have fed Infocom games' location descriptions into an AI". Would still like to see that.

So frustrating that there's no way to access this tech without putting your name on a list and waiting an unspecified amount of time (months?). It's the sort of thing many people would pay well for, even at its current stage of development.

My wait was only 2-3 weeks FWIW.

Re: Adventure game graphics with DALL-E 2

#93
post #68

Earlier quoted context omitted.

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…

> 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. I don’t think DALL-E can even persist a single 2d object between scenes. For example, if you create an animated character you like, I don’t think it’s possible to ask DALL-E to render that same ch…

Competitors like Midjourney and Stablediffusion already allow you to re-use an image seed, which makes it much easier to persist style and character across images.

3D can often be inferred by 2D data, 3D training data could also be generated, etc. Think how fast the space has moved just in the last 3 years and extrapolate from that, don't focus too much on today's shortcomings.

Re: Adventure game graphics with DALL-E 2

#94
post #66
post #55

i keep thinking these kind of tools are very dangerous and can lead to a lost generation of artists, who won't develop their skills because they can't compete with the garbage output of "ai" algorithms.

Exactly my thoughts as well. We're now starting to automate our own culture away: stories, art, music... Why would you spend the years building skills to create something in a sea absolutely flooded by automated algorithms? As these AIs get better, it will be more and more difficult to distinguish the output from human minds. I keep wondering what the endgame here is. Once everything can be algorithmically created, w…

Think outside the box. The human element just moves up in the abstraction stack. Don't have to spend time manually arranging words anymore, now you just direct settings, character motivations etc. Don't need to manually set pixels to certain colours, now you can quickly create complex images and combine them, remix them, create something bigger.

Re: Adventure game graphics with DALL-E 2

#95
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…

I understand your fear, especially because a very similar, if not the same, thing happened with Unity, where our allowed the creation of just what you're talking about a massive amount of low to mid quality games. I even remember reading articles about how the Unity splash screen has become recognised as a mark for low quality games...

Re: Adventure game graphics with DALL-E 2

#96
post #2

These sort of complex 2D environments are a nightmare to work with in adventure games, since you have to manually detail where the player character can go, how the character should grow/shrink to simulate perspective, etc. I checked a video of Milkmaid of the Milky Way (2017) and sure enough, the environments are 3D with heavy stylization. Characters are animated in 2D but positioned and rendered as billboards or sim…

I don't think it'll be long before there's a 3D modeling version of DALL-E. There's already a bunch of programs that can turn 2d images into 3d models - definitely a lot to improve - but they exist.

In Westworld season 4 there are scenes were Christina works with an AI editing tool that generates 3D visuals based on prompts:

https://www.youtube.com/watch?v=3uGLjmrPorg

Re: Adventure game graphics with DALL-E 2

#97
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 question is, should everyone calling themselves "artist" be able to make a living off their creations? Based on your predictions there will be only a subset which can be professional artists... and I think it's okay this way. Everybody can produce art and call themselves artists, but only a few can also make a living from their art - because by definition art needs a consumer and the (paying) consumers pool is limited.

Re: Adventure game graphics with DALL-E 2

#98

Earlier quoted context omitted.

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…

I wonder how tweakable those generated images are. The most important requirement for 'game art creation' is that it is created in a tight feedback loop between an artists, an art director who needs to enforce an overall artistic vision, and the cold, hard requirements of the game design. Can I tell the AI "that looks great, keep the trees and house, but I need the door on the right side, and the sky a bit less cloud…

I’ve been on the beta testing for Stable Diffusion and one thing that they have is give you the seed of the image with which the space is populated. What this enables is enabling you to tweak the image, as you can keep the ‚base‘ image and iterate on the prompt.

It’s not as sophisticated as you described, yet, but close.

In addition I can imagine that it is a matter of the training set. As of now, the AIs seem like jack-of-all-trades, so they know a bit of a lot of different styles and topics. But with Stable Diffusion being able to run locally, you could specialize it by training it with high detail on, let’s say, landscape photography. So then one might be able to direct the AI more precisely.

Re: Adventure game graphics with DALL-E 2

#99

Why not feed all the descriptions from say, original Colossal Cave Adventure game into DALL-E 2? "YOU ARE STANDING AT THE END OF A ROAD BEFORE A SMALL BRICK BUILDING. AROUND YOU IS A FOREST. A SMALL STREAM FLOWS OUT OF THE BUILDING AND DOWN A GULLY."

Decided to try it out: https://labs.openai.com/s/nHmjLYmVPdDQzUU5DvGT2JgK

Wow, existing text-adventure could be very interesting with this kind of semi real-time illustrations. Maybe we'll finally know what is Grue like. Also, Table RPGs with Dall-E illustrations generated semi-realtime by the game master.

Re: Adventure game graphics with DALL-E 2

#100
post #66

Earlier quoted context omitted.

Exactly my thoughts as well. We're now starting to automate our own culture away: stories, art, music... Why would you spend the years building skills to create something in a sea absolutely flooded by automated algorithms? As these AIs get better, it will be more and more difficult to distinguish the output from human minds. I keep wondering what the endgame here is. Once everything can be algorithmically created, w…

Think outside the box. The human element just moves up in the abstraction stack. Don't have to spend time manually arranging words anymore, now you just direct settings, character motivations etc. Don't need to manually set pixels to certain colours, now you can quickly create complex images and combine them, remix them, create something bigger.

Yeah, but anybody can do those things and create interesting content without much training.
Post reply on HN