AI art

[kyonides]

I simply  read a thread on the official forums the other day and I've been  wondering ever since if SavePoint should update its policies as to include its posture on AI generated art and related stuff.

[DerVVulfman]

“Art” and “intelligence” are two notoriously difficult terms to define. As such, it is no surprise that the boundaries of AI-generated art are unclear. This, an actual quote from the Harvard Journal of Law & Technology.

I recognize that Google's DeepDreams may have caused a stir, taking various animal photographs, using an AI algorithm to detect patterns, and create art that sold for $8000 in a gallery. Even moreso when J. Walter Thompson Amsterdam developed a system that studied Rembrandt's paintings and made its own!

AI systems generally (1) take input of various sources, (2) learn from the sources, (3) develop its own composition, and (4) render the composition in the form of audio or video art.

But, the questions would be if one was making AI art with their own innate work, or if they used public domain content, or if the art presented was even AI generated at all? If the creator/publisher chooses not to label the work as AI generated, of if the generation was solely based on their own content, how can it be enforced without worry about any other medium being submitted?

One could suggest that the generated music from a synthesizer may be partially AI, some soundfonts having been pre-recorded live content and converted. Or if not, then a live product digitally remastered by way of an AI system.

As it stands, there is quite little that can be done, even if the person posting admits producing it via AI.

[Kain Nobel]

Confession : I use semi-automated systems to generate graphics, dubbed KAD; Kain Assisted Drafting.

I do not consider this "AI" but it does utilize some machine learning. Also, it does more work than I do (at this point in time.)

Most screenshots posted after 2012 have utilized this system to assist in the design of tilesets (and other miscellaneous resources). Not all, but most. I use it more frequently than I use GraphicsGale. To be fair, most of that use is in perfecting the system and experimentation, but yes, I do use it as much as I can. It was designed to draw like Kain.


Pictured : KAD assisted trees.

Left sample is hand drawn (trunk only), KAD drew all the leaves and applied all the proper shading in regards to foliage.
Right sample is 95% KAD generated tree, based on a rules file and machine interpreted photographic tree foliage.

(Please note that not all samples wind up turning out this good; they usually need some sort of last minute touch up. These two samples are the most successful / least intervention, as far as trees go.)


Pictured : KAD generated dirt, extracted and reinterpreted from a megapixel photograph. In theory, these should each be a 32x32 seamless tile. This is what the system thinks dirt looks like. After extracting photograph RGB data from a race track, this is how the system would draw the dirt from the race track. It interprets highlights and shadows and attempts to make as many seamless 32x32 tiles as it can muster up from the resampled photo.

The data is actually stored internally as a marshalled table of generic number values (short integers) but, if converted into a grayscale PNG format, this is essentially what the data would look like visually.

This is not the result of noise generation and there are thousands of these tiles embedded within the data suite for which the system can use to generate colorized textures.

The KAD TextureMate system is only designed to interpret and re-create the most primitive of textures; grass, dirt, cement, blacktop, sand, rock, roof shingles, clouds, etc. This aspect of the system is not designed for abstract objects such as cars, trucks, dogs, cats, basketballs, mailboxes, etc. However, if you decided to draw an animated kitty cat, you could probably tell the system to texturize it using "Grass" (and point it to the Siamese color profile) and I think it would look good (or it might look "noisy"...)

Let's generate something...


Pictured : KAD generated Cave sample. Please note that we're borrowing RMXP's Cave02 wall texture in this sample only because it is something familiar to everybody here; however, I don't typically use RMXP resources with these systems. It took 0.0134 seconds to generate 64000 individual tiles for a complete tileset. In other words, this tileset is a complete tileset (but I've cut it down to just a small sample for example's sake.)

The "Cave" recipes are fairly mature, so all I have to do is fill in some data and hit "compile and run". Other resource types aren't as mature, but they're still effective too.


Video : Project BEAST Nagivation Demo. Tilesets used in this demo are KAD generated tilesets. Also, texture mismatches in one of the maps is user error, not system error.

KAD TextureMate was very lightly used in the creation of these tilesets, but it does have the capability to extract, examine and reinterpret primitive textures from megapixel photographs such as the dirt posted above. Some of that dirt from the earlier sample may or may not be present in this demo.

Is it AI? No, not in it's current state. Is it machine learning? Yes, absolutely. Does it still require human input? For now, yes, but in the future it should require it less and less.

This system would never be able to replace a human designer, but it does automate a great chunk of work. It would probably be an 80/20 split insofar as it could generate 80% of the RMXP default set of tilesets on it's own with no human assistance, but the other 20% would be adding all the little doodads such as signs, mailboxes, fencing, special windows, etc. which would need a human designer.

That could change (and, in the case of fences, is changing.)


Pictured : Precursor to training KAD how to make RMXP style picket fencing. This sample is hand-drawn, not KAD generated. Once it is properly trained, it should be able to generate fences with minimal human intervention. Once I've done some brainstorming, this image will be used to guide in the making of a json KAD recipe file (fence.json).

This is not a new system. This predates ChatGPT, Dall E, StyleGAN, TensorFlow, Project BEAST, RPG Maker VX Ace and even the 1st attempt at REGAL (Qt era). The system was started as a JavaScript project written in IntelliJ IDEA, but is now being re-written to C++ OpenGL standards (with ImageMagick).

Current Capabilities

• Examine and reinterpret texture profile chunks from megapixel photographs.
  
• Colorize learned texture styles based on user defined limited color palette profiles.
  
• Can generate animated water tiles (unreliable, I still recommend hand-drawn. Sometimes does well though.)
  
• Generates cave / mountain tilesets (very mature.)
  
• Generates house exterior tilesets (semi-mature.)
  
• Generates house interior tilesets (feature is currently in development / largely undefined.)
  
• Generates trees, bushes and foliage (experimental.)
  
• Generates targeted particle effects (such as the flames in the Belly of the Beast title screen. Experimental.)
  
• Generates prefabricated light and shadow effects (experimental.)
  

I don't consider it AI just as I don't consider RPG Maker's character generation suite to be AI. It is an automation tool and requires specialized training and plenty of image data. If I was to train it to draw fireworks, I would need to submit many stills from a video of fireworks in action. Maybe it could reverse engineer the animation of fireworks, maybe not. Haven't tried (yet) but I'm curious to see how well it would actually do. In the future, it may train on video, but it's only ever trained on still image photographs. As such, it can't interpret an animated GIF reliably or an MP4 or anything else but PNG and BMP (JPEG not recommended).

I have mixed feelings on AI, but I feel it would be way too risky to institute a ban on it. Policies like RPGMakerWeb are a slippery slope towards banning non-AI developments like this one. Systems like mine could be misconstrued and misinterpreted as AI, but it is not. Machine learning could be misconstrued and misinterpreted to be AI; again, it could be a component of AI, but it is not AI itself. Like a child, it needs training, supervision and intervention to be most effective.

(Much love to RPGMakerWeb, but I tend to disagree on certain things. I doth not protest though, let them institute whatever policy they feel they need to institute.)

However, once everything comes full circle, it designs very nice looking tilesets on par with what I would attempt to do by hand. Also, this is not intended to be part of the REGAL suite of software (but that may change as it becomes more mature.)

I never even intended to tell people about it but I figure it's time to come clean, especially now that AI is a mainstream topic. Special thanks to Poccil, Selwyn, and Raitame for early inspiration behind the system as they were experimenting with image manipulation via programming long before I ever attempted.

[Remi-chan]

I have no intention of banning AI art.

It's the thievery committed by systems that unapologetically steal other artists' work without consent or acknowledgement that is what i would like to see destroyed.

AI Generation isn't a problem so long as it's moderated by fair use.

[JayRay]

Agreed, and not all AI Imaging is generative by design. Sometimes, like well, with some of my work currently, a heavily pixelated sprite needs to be resized for a larger, more HD resolution, and in that moment, an AI script like Esreg is a huge timesaver.

And note, I say that with an AI generated image of a pose I did showing in my sig.

[Remi-chan]

Every time you're using the character generator in MV, you are doing image generation. You're just the brains behind it.

But the A.I is technically there, layering things and placing stuff in the right spot. Though at this stage that's basically mechanical obligation.

It's worth noting that the worst thing that can happen in A.I. art, plagiarism: is already listed as an absolute no-no in the forum rules.

Using sprites generated by FSM's tallsprite generator is fine, as long as you credit Mack. (this is why he so often appears in my game's credits.

The reason that's okay is because Mack has created and built up that generator from his own work, and has allowed the public to use it with credit. It's unfortunate that it recently was lost in the geocities breakdown.

Opting to ban A.I generated art wholesale would do more harm than good.

The more shady and scum-infested parts of the A.I. image generation scene are already under fire from the supreme court and many large bodies who they've stolen from in their reckless crusade. They will soon likely be in the same boat as A.I generated music.

Because yeah, this has happened before. Only the music industry clamped down on it, so it became a product of laws and regulations. This will likely be the fate of A.I generated art before long. This is just a phase where plucky opportunists will try their darndest to make a quick buck off of work that isn't theirs. They'll also likely end up filing for bankruptcy by years end due to the amount of lawsuits coming their way.