The first guitar has one of the strings end at the sound hole, and six tuning knobs for five strings.

The second has similar problems: it has tuning knobs with missing winding posts, then five strings becoming four at the bridge. It also has a pickup under the fretboard.

Are these considered good capability examples?

  > Are these considered good capability examples?

Compared to a human?

No. Or at least not what I'd expect from one. Maybe if you hired a cheap artist. But I'm pretty sure a cheap artist would just take an existing scan.

Compared to other works?

Yeah. That's the context I'm judging under.

Though the more I'm playing with it the more I'm seeing weirdness.

I think we should be clear (and I wish even the research community would take this point to heart): research is not product development.

The two are related and research is on the early path to product development but one thing I hate is that papers are often evaluated as if they are products. Tons of papers aren't even about the demonstration, but the demonstration is just a good experimental platform. Like I've done some stuff where my focus was actually on information gain but the experiments are showing image generation. If we were to solely look at the output of the images we'd miss the point of the paper (that said, it is quite common for reviewers to do this too!). If we were developing products, then really all the best papers would be determined by who has the most compute as you can often just hyperparameter tune your way to the top of any benchmark (oh wait...). I mean others might, but that's not how I evaluate research and it's not something I want to promote because it is destructive to the progress of research. We'd never get anywhere if the new thing had to outperform the old thing on the first go (the old thing which has been studied in much more detail and benefited from a lot of optimizations).

So really, by "pretty good" I mean "looks like progress"

Thanks for this. The results are quite impressive, after trying it myself.

Ops ran out of edit time when I was posting my last two

  Prompt: A hawk flying in the sky
    PNG: https://0x0.st/8Hkw.png
         https://0x0.st/8Hkx.png
         https://0x0.st/8Hk3.png
    Note: This looks like it would need more work. I tried a few birds and generic too. They all seem to have similar form. 
  Prompt: A hawk with the head of a dragon flying in the sky and holding a snake
    PNG: https://0x0.st/8HkE.png
         https://0x0.st/8Hk6.png
         https://0x0.st/8HkI.png
         https://0x0.st/8Hkl.png
    Note: This one really isn't great. Just a normal hawk head. Not how a bird holds a snake either...

This last one is really key for judging where the tech is at btw. Most of the generations are assets you could download freely from the internet and you could probably get better ones by some artist on fiver or something. But the last example is more our realistic use case. Something that is relatively reasonable, probably not in the set of easy to download assets, and might be something someone wants. It isn't too crazy of an ask given Chimera and how similar a dragon is to a bird in the first place, this should be on the "easier" end. I'm sure you could prompt engineer your way into it but then we have to have the discussion of what costs more a prompt engineer or an artist? And do you need a prompt engineer who can repair models? Because these look like they need repairs.

This can make it hard to really tell if there's progress or not. It is really easy to make compelling images in a paper and beat benchmarks while not actually creating a something that is __or will become__ a usable product. All the little details matter. Little errors quickly compound... That said, I do much more on generative imagery than generative 3d objects so grain of salt here.

Keep in mind: generative models (of any kind) are incredibly difficult to evaluate. Always keep that in mind. You really only have a good idea after you've generated hundreds or thousands of samples yourself and are able to look at a lot with high scrutiny.

Yeah, this is absolutely light years off being useful in production.

People just see fancy demos and start crapping on about the future, but just look at stable diffusion. It's been around for how long, and what serious professional game developers are using it as a core part of their workflow? Maybe some concept artists? But consistent style is such an important thing for any half decent game and these generative tools shit the bed on consistency in a way that's difficult to paper over.

I've spent a lot of time thinking about game design and experimenting with SD/Flux, and the only thing I think I could even get close to production that I couldn't before is maybe an MTG style card game where gameplay is far more important than graphics, and flashy nice looking static artwork is far more important than consistency. That's a fucking small niche, and I don't see a lot of paths to generalisation.

Yeah the big problem I have with my field is that there seems to be stronger incentives to be chasing benchmarks and making things look good than there is to actually solve the hard problems. There is a strong preference for "lazy evaluation" which is too dependent on assuming high levels of ethical presentation and due diligence. I find it so problematic because this focus actually makes it hard for people to publish who are tackling these problems. Because it makes the space even noisier (already incredibly noisy by the very nature of the subject) and then it becomes hard to talk about details if they're presumed solved.

I get that we gloss over details, but if there's anywhere you're allowed to be nuanced and be arguing over details should it not be in academia?

(fwiw, I'm also very supportive of having low bars to publication. If it's void of serious error and plagiarism, it is publishable imo. No one can predict what is important or impactful, so we shouldn't even play that game. Trying to decide if it is "novel" or "good enough for <Venue>" is just idiotic and breeds collusion rings and bad actors)

Stable Diffusion and AI in general seems to be big in marketing at least. A friend decided to abandon engineering and move to marketing and the entire social media part of his job is making a rough post, converting it to corporate marketing language via AI and then generating an eye catching piece of AI art to slap on top.

When video generation gets easy he'll probably move to making short eye catching gifs.

When 3D models and AI in general improve I can imagine him for example generating shitty little games to put in banners. I've been using an adblocker for so long I don't know what exists nowadays but I remember there being banners with "shoot 5 ducks" type games where the last duck kill opens the advertisers website. Sounds feasible for an AI to implement reliably. If you can generate different games like that based on the interests of the person seeing the ad you can probably milk some clicks.

> been around for how long, and what serious professional game developers are using it as a core part of their workflow?

Are you in the game industry? If you’re not how would you even know they have not? As someone with some connections in the industry and may soon get more involved personally, I know at least one mobile gaming studio with quite a bit of funding and momentum that has started using a good deal of AI-generated assets that would have been handcrafted in the past.