[flagged]
A sleep-deprived artist somewhere (not me): No, thank you, I need to get this for an ad tomorrow morning.
This kind of warping of 2D images is currently used extensively, but a lot more manually (See Live2d, the Photoshop mesh transform tool, or Adobe Illustrator). So, this does not replace 3D modelling; it replaces some 2D editing techniques where 3D modelling isn't even on the table as an applicable tool.
This kind of 2d image warping is useful in advertisements, game art, photo touchups, concept art, photo bashing and digital illustration.
Imagine telling the Toy Story team “or you can just draw each frame like normal”
Everyone should have the means of being able to express the ideas in their heads visually in front of others. It shouldn't require arcane and difficult to use tools. Nor should it cost millions of dollars and require a studio apparatus to tell stories to an audience.
Pretty soon creating worlds, filming movies, and sculpting images and three dimensional forms will be accessible to everyone.
Blockbuster movies will never get significantly cheaper, no matter what tools we invent. They will spend as much or more money on using the new tools to make more grandiose movies that individual people have no hope of doing themselves. There’s already a hundred year history of this happening, despite the tools having always been accessible to everyone.
I think this Gaussian splatting tool is great, and I’m in favor of forward progress in imaging tools, and I work in this field. But where is the line between having accessible tools, and putting time and effort into your craft to make something that’s high quality, or telling a story with images that are personal and new? And if you’re really talking about AI (even though this Gaussian splat tool isn’t really AI), where is the line between being able to express your ideas effortlessly and stealing the means to do that from artists who had to put it effort to produce the content that trained the AI?
The fact is that not everyone can do so.
What about an elderly grandparent that wants to paint their hometown as they remember growing up? Do we expect them to spend years learning illustration before they can show their grandchildren?
> But why shouldn’t it require difficult to use tools or cost a lot?
Would "640K" [1] be enough for you? What about if computers were still only housed in DoD facilities and in universities? Too giant, arcane, and expensive for you to use?
> Blockbuster movies will never get significantly cheaper, no matter what tools we invent.
The industry thinks otherwise [2].
I, for one, would like to tell an epic sci-fi adventure story without needing Disney's budget. I've spent tens of thousands of dollars on indie film production and it's incredibly expensive and time consuming.
While I don't have time to learn Blender, I do know how I want my explosions to look. Why should I have to outsource to someone else to do the VFX? Someone that might not deliver my work in time? (Read: waiting on post has been a serious hang-up for me in the past and caused me to miss several festival deadlines.)
> There’s already a hundred year history of this happening, despite the tools having always been accessible to everyone.
No, the reason this happens is because large budget films are predictably bankable and wind up eating up all of the screen distribution real estate. There's a reason you don't want to launch your movie opposite The Avengers or another tent pole feature.
The most ROI comes from breakout low budget successes, but those are harder to gamble on.
> I work in this field
Same.
> But where is the line between having accessible tools, and putting time and effort into your craft to make something that’s high quality, or telling a story with images that are personal and new?
Why not let the users and the artists show us what they'll make rather than predicting they can't do a good job? I know dozens of artists, myself included, using these tools incredibly effectively.
> being able to express your ideas effortlessly
This is probably the source of our disagreement. An effortless tool doesn't mean works of art don't take effort.
> stealing the means to do that from artists who had to put it effort to produce the content that trained the AI
This argument will be moot soon. Adobe has full rights to all of their training data. Soon we'll have enormous synthetic datasets from Unreal Engine and mechanized turn table photo rooms. Other organizations will follow.
[1] https://www.computerworld.com/article/1563853/the-640k-quote...
[2] https://www.hollywoodreporter.com/business/digital/jeffrey-k...
It’s true not everyone has the skills to make a movie. Why “should” they? You didn’t answer the question. I don’t expect people without any skills and without the will to learn to do anything, and that includes not expecting them to make movies. I don’t follow your point about 640K and the DoD, nobody is talking about making tools artificially difficult. Modern tools still require years of learning to paint or make movies, AI hasn’t changed that yet, and even if it does it will only raise the bar such that people with skills continue to produce things much better than people without skills, low effort art is going to remain crappy, same as it ever was.
A.I. art is for the lazy.
These are 2010-era tools. We're modernizing.
You wouldn't ask musicians today to stick to only pre-synthesizer, pre-DAW era tools to make their music. You wouldn't ask illustrators to ditch their tablets force them to mix their own cerulean unless that's what they wanted to do.
The tools that are coming are going to be fantastic and they're going to enable artists to do wild new things. That isn't subtractive, it's additive. There's more space to explore.
New tools don't even prevent folks from making music and media the old fashioned way: there are still people shooting on film to this day. And there's a vibrant community that embraces anachronistic tools to make new art.
I'm looking forward to a world where teenagers cut their teeth on making their own Marvel movies instead of just watching them. We'll have so many young Scorseses before they even graduate.
The almost violent anti-AI sentiment seen among art cohort is sometimes hard to understand to subgroups of tech literates without enough training epochs in human generative image data(especially the kind prevalent on the Internet), and I would understand that without grasp of rather subjective quality issues it could indeed look like an artificially incited luddite conspiracy.
Once someone makes an AI that would be additive and outputs entertainment worthy, then the "luddites" will change, they must. Until then, it's just a technically remarkable white noise generator.