Nvidia Canvas | Hacker News Reader

Nvidia Canvas

nvidia.com

614 pointsforgingahead177 comments

Incredible! They finally built a tool to 'Draw the Owl' [1]

[1] https://knowyourmeme.com/memes/how-to-draw-an-owl

As incredible as it looks this feat has been demonstrated since a few years ago.

IDK why this is being downvoted, it was indeed published two year ago, they just apparently repackaged this as an easier-to-use tool: https://arxiv.org/abs/1903.07291

Before there was a dense scientific paper. Now they've released an incredibly simple tool that lets anyone draw photorealistic images with simple strokes.

Saying that is repackaging something into an easier-to-use tool seems like quite a stretch. They didn't put a GUI on curl or something.

> They didn't put a GUI on curl or something

I don't think a GUI for curl would be as easy as you imagine. Curl has a lot of power with all the options and protocols it supports.

Isn't this a browser?

https://www.jensroesner.com/wgetgui/wgetgui.png

Here's an image of a wget gui. It's not quite a browser, interesting to look at nonetheless.

Fascinating, yes!

"The future is already here—it's just not very evenly distributed." ~ William Gibson

This is one of the best comments I read online :)

What a horrible website on mobile.

I hate the "download" button at the top that points to "#something" on the page that centers on an image that fills the whole screen (on a 4k laptop) so that you can't see the real download button below it.

It's cruel.

I am pumped to try it out however.

I think they mean Knowyourmeme

Don't worry, it's shit on the desktop too.

To all non Windows users

http://nvidia-research-mingyuliu.com/gaugan/

Looks like it has CORS issue.

It works for me. (FF Linux)

Compared to canvas, this looks more like a early 2010s style transfer tech demo :) Thanks for the link though!

Ah, that's kind of reassuring for canvas, because I was really disappointed when I' tried to play a bit with it. I was like: “meh, how is that even worth a press release?”

After painting for 5 minutes: This segmentation map may contain unsupported labels.

Whoa. Not just all non-Windows users but browser based. That's neat. I was interested in trying it out but didn't want to download the software.

It would be really interesting/fun to run this on a frame by frame output of classic 8 bit video games and see what it does. I know it wouldn't make the game look real within it's own concept, but the ordered/familiar inputs to the AI might generate some interesting video outputs.

You’d need some kind of inter frame consistency also, would probably jiggle quite a lot.

I'm not entirely sure how this would be achiveved.

When you draw in the app, you use a brush and have to pick materials from a palette (like "sky" or "ground" or "stone wall" etc). It doesn't seem to have any sort of "import an image" feature because what would that even mean in their model.

The approach I would probably consider is to use a modified ROM so that the different sprites in the game are different solid colors. Then I'd write some kind of mouse automation to use those captured images and draw the frame in the app, clicking on the various palette options based on color.

The next challenge is that the Canvas app doesn't let you set individual pixels, the smallest brush is ~10px across on its ~550px canvas. Maybe I'd have to settle for picking a Z-ordering and just drawing everything approximately, or maybe you could do some sort of attempt at a path routing algorithm to draw along the edges of the shapes and fill in the centers.

An example is here (using the same NVIDIA GauGAN model that backs this Canvas app): https://twitter.com/jonathanfly/status/1144735290591981568?l...

Jonathan has played with GauGAN quite a bit (search twitter for "from:@jonathanfly gaugan" to see more).

Cool! For anybody looking for Mario specifically, here it is: https://twitter.com/jonathanfly/status/1158846045285232641

The one with the Pole Position racing game looks pretty cool, with a surprising amount of stability between frames: https://twitter.com/jonathanfly/status/1146569133376573440

Nice, this is exactly what I imagined.

Tile-based 2D games should be fairly easily converted to provide semantic labeling. They already have a low-res grid that says "sky, stone, etc."

Anyone else remember when a 1.1GB download was a serious commitment?

Now it's a coffee break curiosity.

I remember when downloading 10MB was a serious commitment

shakes fist at clouds

When I got the first smartphone for my wife (then girlfriend) we set it up when we were in a hotel (without wifi). The 10mb mobile data used for setting up email etc. endet up costing more than the phone :(

I remember when downloading 10MB would sometimes take multiple tries.

Maybe the internet felt so much more exciting to me back then because it was so much slower.

GetRight download manager to your service.

I was trying to remember that name. Tried to look for a video of it on YouTube, there's some pickup artist who calls himself Mr. GetRight instead...

But hah, their website is still alive, and they're still selling it for $20: https://www.getright.com/screens.html

Indeed. I remember downloading a 3 MB mp3 file and it would take numerous tries and quite some time. Winamp would play the partial though so you could put it on repeat and get a few more seconds of the song on each run. This was back when you could find websites that just offered a collection of mp3s for direct download! The internet was a wild lawless place of free information back then.

Damn this makes me feel old. I'm not that old!

I remember when downloading 50KB was a serious commitment, over a phone line, of course. It took long enough that inevitably someone else in the house would try to use the phone and your download would get disconnected.

buries head in sand

Lol and it would be split up into 10 100mb rar files

And maybe a couple of par files

This brought back bad memories of spending days getting all those rar files, only for the final decompression to fail.

on a zip drive

For some of us it still is.

Yes I remember vividly, it was April 2021!

The code behind this is available here:

https://github.com/mcheng89/gaugan

https://nvlabs.github.io/SPADE/

https://github.com/NVlabs/SPADE

Looks like it is Windows only. The absence of nVidia GPUs on Macs is really making Macs a weaker dev machine for ML work.

And for artists as well since Canvas is for concept artists.

Was anyone really training ML models on Mac to begin with? Pretty sure most people run Jupyter on a Linux server somewhere and develop in their browser.

I wonder how difficult it would be to make something similar that generated 3D models. Most of the examples look like they'd make good video game levels.

Dungeon Alchemist seems really cool (I'm a backer), but I'm not entirely sure that it is related. DA is basically procedurally generated furnishing (with a few params), but it doesn't create 3D models from what I understand, it "just" shuffles around furniture.

First time I've heard of this. Is it for tabletop games like d&d? Or for game development? Looks really cool

I wondered the same. There is some solid competition in this area right now, without AI assisted asset generation.

Unreal 5 has a new, free, 3d model library integrated as Quixel Bridge. [1]

Kitbash 3D, a company selling modular 3D sets used regularly in Beeple’s 2d provides mid-res, theme-based sets for customized use.

Neither take into account the idea of fully featured 3d objects being built from basic primitive using ML.

It makes sense that it will go this direction though, because it means designers can get unique 3D assets customized to the size and dimensions with less work.

Couple this with Apple’s photogrammetry in iOS 15 it seems original 3D assets available for training data will swell greatly.

[1] https://youtu.be/d1ZnM7CH-v4 @ 4:34

I think the theory's all there, it just needs reference material on the one hand and the work to be put in on the other. With the new Unreal 5 engine, I think there is a lot of room for technology where an artist sketches out a rock and tools come in to generate the small details - much like there's tools like speedtree and co nowadays to procedurally generate content.

Well, I think there is enough interesting research to put things in place. Not in single model. But, we have

0. This neural thing, of course, to create landscape-like 2D projections of a plausible scene.

1. Wave-function collapse models that synthesize domain data quite nicely when parametrized with artistic care - this is a "simpler" example of the concept. https://github.com/mxgmn/WaveFunctionCollapse

2. Fairly good understanding how to synthesize terrain. Terragen is a good example of this (although not public research, the images drive the point home nicely) https://planetside.co.uk/

So, we could use the source image from this as a 2D projection of an intended landscape as a seed to a wave-function collapse model that would use known terrain parametrization schemes to synthesize something usable (so basically create a Terragen equivalent model).

I think that's it plausibly more or less. But it's a "research" level problem still, I think, not something one can cook up by chaining the data flow from a few open source libraries together.

Have a good read :) https://github.com/yenchenlin/awesome-NeRF

Do authors own the copyright of their generated images? I can't see any mention in the FAQ.

Related: Do authors of a digital camera own the copyright for their (preprocessed) images?

Why wouldn't they? It's just a tool. When I write something by pen, do I get the copyright or does the company that made the pen? Me, obviously.

But what if the pen draws by itself? You just say "draw a dog", and it does.

I do think you should always be the copyright owner, unless it's clearly stated in their terms that any image created using their tool is owned by nVidia.

But it's still just a tool that functions to your input. An IDE which insert a lot of boilerplate and autocompletions, does it get the copyright to your codebase? Nope.

Interestingly, if I employ an artist to produce a work (e.g. software code), usually the employment contract would say the copyright belongs to me and not that artist.

"Hey pen, sign this contract."...

I'd just like to point out that this line of inquiry is not some unanswered philosophical question. All of capitalism is focused on this question of ownership. Who owns the picture? The answer is always whoever the parties involved agreed would own it. Both options can exist and they'll have different prices.

This same question often comes up with self-driving cars and "fault", and it seems to regress into the same trap. Ownership of _risk_ is one of the primary concerns of capitalism. The question is not, "who should be at fault?", it is instead "what is the cost of this risk?" and then we buy and sell that risk like everything else (which is also how we determine that cost). If the self-driving advocates are right and self-driving is safer, then the risk will likely cost less than your current insurance.

Of course, it's not always clear. If the parties can't agree who owns a thing, they often use some legal mechanism to resolve their dispute.

The real question is "Who is the author?"

Because actually the user isn't. The AI is. AI's don't have a right to copyright. You making a few lines and the AI making the actual image does not make you the creator of the image.

Why not? Can a comparison not be made to writing source code and the output of a compiler?

While the analogy is correct, the binaries generated by compilers does involve integration of creative work beyond that in the code compiled. The binary as such is a 'derivative work' generated from creativity of the authors of the source code, compiler, and standard libraries. What happens is that the copyright licenses coming along with compilers and standard libraries explicitly grant generous permissions to the users of the compilers.

For algorithmic art, likewise the developers of the software typically provide permissive licenses to the users of the software.

AI makes this harder because the works are massively derivative works, which AFAIK, do not have much precedants in law. The question is not easy to answer unless the author (Nvidia in this case) owned copyright over all training data.

The trick.

Good artists copy, great artists steal.

AI does both :D

I believe the current understanding of GAN copyright is that the "minimum degree of creativity" happens when a human chooses the inputs/outputs and copyright is assigned to the human at that point. Drawing the input image for GauGAN probably suffices.

Fully automated outputs (like pulling an image at random from thispersondoesnotexist.com) would be public domain since non-humans cannot hold copyrights and no creativity was applied.

This is analogous to the "creativity" of a photo being the settings and framing done by the person who set up the shot and is why the famous "monkey selfie" fell under public domain[1].

[1] https://en.wikipedia.org/wiki/Monkey_selfie_copyright_disput...

See my comment below.

https://news.ycombinator.com/item?id=27635481

I think Monkey selfie copyright issue was subtly different.

Nice for a prototype,but given model bias, it will create a creativity bubble like the google search bubble but for visuals.

Would you mind elaborating a bit more on what you mean? It's very fashionable to be concerned about model bias at the moment, but it's not clear to me what the issue you're describing would be? Something like: trees would end up looking too much like the same tree?

The “worry” here is that everything produced will look similar and hence will become boring at some point.

Right, that was the assumption I was alluding to at the end of my comment. That said, it still doesn't fully resolve the question and unfortunately leaves the statement in handwaving territory still. 'boring' isn't really a measurement we can take and discuss super effectively, but we do have actual metrics across visual datasets that span basically all of what you might see as a human.

By chance, are you aware of any research on this topic?

I would say it leaves the statement in hypothesis territory, not hand-waving territory. If we can't discuss or measure "boring" effectively, that is a problem with our instruments and vocabulary, not the assertion.

"Boring" is an absolutely crucial thing to be worried about when it comes to anything remotely artistic.

It's not a hypothesis though, there's nothing that we can test in it. As presented, it's an assertion that has zero evidence to support it. That's the part I was hoping to get some actual clarification and precision on. When discussing machine learning, bias is a term that has a quantifiable definition in it's different contexts....boring doesn't. It's just FUD to snipe this kind of work with some kind of 'bias' fear without any additional evidence or thought.

You can easily generate a landscape and then do a paintover. People already do that with sketch up 3D models for backgrounds. I don’t think any professional would just literally copy and paste the thing.

There is also an online version here:

https://www.nvidia.com/en-us/research/ai-playground/

Someone used the version of this available online last year to create a 3D video version of the output, super interesting: https://www.youtube.com/watch?v=ZXFmZsv0Ddw

Interesting potential for dream journaling..

Heard someone say the other day they use an AI face generator to capture the faces of people they meet in their dreams.

You need an RTX card to run this, so don't bother with the "Driver update" prompt if you don't have one!

They implemented Bob Ross.

It's more like handing off Bob Ross paintings to an overachieving photorealist who promptly paints over them.

Does anyone know if the backend code for this is made opensource on github or something? So it can run without windows?

Given its deep integration with their RTX APIs, I imagine even if the source code were open, the only way to get at the RTX ML-specific stuff is via their Windows driver.

Hmm slightly disappointed. I thought I'd make a mashup video game short with generated art.

The output resolution is locked at 512x512. The "target style images" seem to be locked to that handful that come with the application. The brush materials don't include anything man-made.

Am I doing it wrong?

I am thinking if this Nvidia Canvas and the Apple Object Capture Capture [1] [2] will make Graphics or 3D Modelling cheaper or taking much less time. Instead of using tools on the computer which was never really good enough for human creation, they now create photos, painting, or models in real world and scan it in a computer for further editing.

[1] https://www.youtube.com/watch?v=88rttSh7NcM

[2] https://www.youtube.com/watch?v=SuNNyjs9BO8&t=1s

How did they create the model?

Did they take a bunch of reference pictures where they said "this part here is water, this part here is rocks, this part here grass, etc...", and somehow trained a model from that?

From their FAQ [1]:

  Q: How does the AI in Canvas work?
  NVIDIA Canvas uses a GAN (Generative Adversarial Network) to turn a rough painting of a segmentation map into a realistic landscape image. 5 million photographs of landscapes were used to train the network on an NVIDIA DGX.

  Q: Is Canvas related to GauGAN? 
  Canvas is built on the same research core that NVIDIA showed in GauGAN.

[1] https://nvidia.custhelp.com/app/answers/detail/a_id/5105

This is awesome, now have it automatically build a 3d world with 3d assets

I find the demo video terrible, though. Of course, it gets the general idea across but it's too fast-cut to see any details which - for something visual like painting - is kind of the whole point.

Good find, I think I'm going to take this out with me to go drawing this weekend and see what I can do.

Curious if this could be used to generate UI mocks. Pass in a whiteboard sketch and you get the mocks out.

https://sketch2code.azurewebsites.net/

This reminds me of my "Sketch to Art" project made in 2018: https://github.com/mtobeiyf/sketch-to-art

The idea is pretty much the same, except Nvidia is using a more complex model.

And 327 other projects around the same time. The beauty of open research.

of course you need an RTX GPU, how come i'm not allowed to run it on a 1650 Super ? sigh

Windows? Can we have linux support please!

The neural net was probably trained on Linux, they put in extra effort to package it for Windows.

https://nvlabs.github.io/SPADE/

This occurred to me, too. Might be able to get it running on Wine or even Proton [1]

[1] https://github.com/ValveSoftware/Proton/

This is Windows only, probably due to the lack of support for the relevant GFX stuff on Mac?

Incidentally, does anyone know of a straightforward and quick Windows-in-the-cloud solution? A bit like GeForceNOW but giving you an entire VM without setup et al?

Here you go, works for AWS, Azure, and GCP - https://github.com/parsec-cloud/Parsec-Cloud-Preparation-Too.... Parsec is similar technology to Geforce Now (only better imho)

Thanks!

this looks amazing! i wonder why the beta is windows only though...

Why wouldn't it be?

Because most real-world CUDA research happens on Linux with Python and Jupyter?

Most end-users are on Windows, however.

That may not be the case for much longer. The press release on their final financial report from last year:

https://nvidianews.nvidia.com/news/nvidia-announces-financia...

Data center revenue at $6.7 billion. Gaming at $7.7 billion. But data center grew 124%, gaming 41%. If that keeps up, data center passes gaming this year.

I don't think data centers count as end users. End users are human beings that use a system.

That doesn't make any sense to me. Human ML/AI researchers are also users and NVIDIA clearly intentionally targets them as a market segment. They don't only care about pleasing gamers running Windows.

in the context of a desktop app, it seems pretty clear 'alphachloride was referring to desktop users.

how is the existence of big datacenters relevant to what platforms nvidia will support for a desktop app?

and most artists who utilize CUDA use Windows.

The entire deep learning / AI industry relies on running GPU compute on Linux, mostly CUDA on Nvidia GPUs.

I'm using an Nvidia RTX 3090 on Linux with the proprietary drivers for machine learning and man it fucking sucks as a desktop lately.

So my best guess is nobody at Nvidia uses the Linux desktop as a workstation.

1) My HDMI screen hasn't been able to wake from sleep for over a year now, the only way to make it wake is to switch to a text tty and then back to X11.

2) Wayland still isn't supported. The default Ubuntu 18.04 gdm doesn't even work so on first boot with the proprietary driver everything seems broken.

3) Since Firefox 89 switched to accelerated rendering by default, windows randomly disappear and various video players have lock contention, drop frames at 60fps, and downscale video on a fucking $1600 video card.

4) HDMI audio crackles and pops with a 2 second delay after a few hours and I have to restart pulseaudio on the command line.

5) I file support tickets on Nvidia's website and the company never responds, they don't even dupe them with some other old ticket.

(1) works fine for me over DP, didn’t try HDMI. (4) sounds (heh) like a pulseaudio problem.

I recently switched to the 465 driver (on Ubuntu 20.04) and had issues: try downgrading back to 460 if you're in the same boat.

That happened to me yesterday on my work laptop. System 76's help documentation said to chroot in from rescue media, uninstall the drivers, then reinstall, and that worked fine, so it's now running 465 perfectly well. No idea why the straight upgrade path doesn't work.

But that's completely an Ubuntu problem, not NVIDIA. Like a (currently) higher up comment says, NVIDIA on Linux works fine as long as you're running the latest version of everything. My main desktop was built last April and I've been running Arch with RTX 2070 and the latest NVIDIA drivers ever since first boot and it has never given me any trouble, video or audio. My display is a 50 inch OLED connected via HDMI and audio a 5-channel soundbar with external subwoofer using eARC from the display. Everything is fine using GNOME defaults.

NVIDIA provides the nvidia-xconfig tool to autogenerate the X configuration, but you don't need it. It runs fine with no config. Wayland has worked for over a year, too. You can go look at the PKGBUILD file for Arch's PulseAudio installer and it isn't doing anything special, either, just applying the suggest default from PulseAudio's documentation making the ALSA default module pulse.

The only reason NVIDIA on Linux gives people so many problems is they're trying to run old versions of everything on enterprise-oriented Linux distros or "long-term support" without purchasing support. If you want the latest hardware, use the latest software.

The software focused teams all use Linux workstations afaik, look at their job boards and blind. Their embedded systems (robotics / av) are all Linux as well.

I simply do not believe that given how bad their drivers are.

I would not be surprised if most or all of their Linux engineers ssh into Linux from a Windows machine given how stable their command line stuff is in comparison to the graphics (once you figure out the correct permutation of userland/kernel pieces to get CUDA+cudnn+TF working anyways).

Their recommended method of installing cuda includes a 64-bit version, but not a 32-bit version. Nvidia's cuda packages are marked as incompatible with debian's nvidia-driver-* packages, so installing it uninstalls the 32-bit version. As a result, I need to choose between steam (which uses the 32-bit graphics library) and an updated cuda version (since Ubuntu 20.04's repo is pinned at 10.2).

Install the cuda-toolkit- package instead of the cuda- package in that usecase.

I ended up selling my Nvidia card for an AMD one. I was having so many problems with Linux like you're describing, and now they're all gone :)

Yeah I can't remember ever having any problems with Intel graphics on all the laptops I've owned.

It's night and day how much Intel cares about Linux compared to Nvidia.

Indeed it's night and day how Intel performs compared to Nvidia as well.

I'll never forget Intel for lying about OpenGL support in some old laptop drivers for Windows.

Yeah you’re right, even low power Intel gpus can render an X11 desktop with audio wayyyyy faster and with less artifacts than the proprietary nvidia driver.

“But everything just works” says the Linux enthusiast after fiddling with their xorg config in the morning.

That is true but I would like that point out that windows still has issues on my bog standard Intel/Nvidia rig - e.g. Linux can't sleep properly, but windows either fails to resume properly or randomly wakes me up at night by revving turning back on and revving the fans.

Similarly, my new iPad pro is great until you need to do something apple haven't approved of (e.g. I can't watch a bunch of movies I have had copies of for years due to apple not letting VLC ship certain codecs)

> The default Ubuntu 18.04 gdm doesn't even work

I mean, using ubuntu 18.04 means using ~4/5 years old software which only gets "security updates" (not even patch updates, e.g. they use a Qt LTS from 2017 and don't even update the patch version, it's still 5.9.5 while Qt's is 5.9.9), why would you expect things to work correctly with a 1 year old graphics card. On archlinux wayland with an nvidia card works pretty much fine.

Do they not port the HWE to older LTS releases?

This has been broken since 2019. I’m running Ubuntu 20.04 with the 5.11 kernel and the 460/465 drivers and all these problems are still happening.

And also, yes, I expect a 5 year old operating system to still work. Windows 10 does and it came out in 2015. These are professional tools for my fucking job.

> And also, yes, I expect a 5 year old operating system to still work. Windows 10 does and it came out in 2015.

but the windows 10 you run in 2021 is super different from the windows 10 you installed in 2015, there are ton of (sometimes fairly breaking) updates :

https://en.wikipedia.org/wiki/Windows_10_version_history

running an up-to-date win10 is basically equivalent to updating to every ubuntu release, LTS or not. Kernel is different, libc is different, system APIs implementations are different, everything is updated every few months - even the start menu pretty much changes all the time.

Perhaps other operating systems aren't advanced or powerful enough? Mac doesn't support NVIDIA.

Okay so this is like putting image segmentation data into a GAN and getting the opposite result, right? Or is there something I'm missing?

Abstract, abstract painting.

Clicks "Download" on a Mac

Me: "Why is it downloading an .exe?"

Wow. This is amazing! I'm not holding by breath for Mac OS support as Apple isn't very fond of Nvidia. I'm sure there will be clones in future for MacOs/IOS, Linux and Android.

The model itself is hardware-agnostic, so there's nothing preventing someone from building a frontend for their platform of choice.

Granted, powerful hardware is still required to run inference at acceptable speeds (or at all - I don't know the memory requirements).

mspaint to bryce 3d

Indistinguishable from magic.

I bet you could make some nice assets for games with this. Definitely will find a niche in the indie dev scene.

For the indie dev scene it would be more useful one that generates pixel art which is more common. Indie games rarely have realistic scenarios.

Just run it through Photoshop's Mosaic filter.

also pixel art is cheaper. realistic scenarios are more expensive. so more value here

Using realistic scenarios forces you to use realistic assets everywhere. If this tool only does backgrounds, it would raise costs for indie developers. Hence my previous comment.

This is almost as nice as going outside in nature.

Looks great!! Looking forward to Mac OS support!

sarcasm?

This requires RTX cards and afaik Apple hasn't supported Nvidia hardware since like maxwell?

I suspect they don't really need GPU to render it. It is usually training what requires a lot of GPU, not evaluation. So the Nvidia requirement is only to sell more cards.

Not true. Big neural nets like these are still dog-slow on CPUs.

Maybe they are. But I suspect 10 core i9 CPU is not much slower than the oldest Nvidia card they list as the requirement.

Don't know much about GPU performance though except random links I have found online which tell that GPU is 3-5 time faster for ML.

They list nvidia RTX as their minimum requirement.

i9-7980XE: 1.3 teraflops

RTX 2060: 52 teraflops

I think the flops comparison you’ve presented is not fair: for nvidia it is “tensor” floops, not generic float multiplication (which is 10 times smaller), while for intel it is any float multiplication.

So for i9 the number would be higher if fma operations used, no?

Tensor flops is significant since this is exactly the use case for which it was designed. So IMO the comparison is fair.

It doesn’t make sense. Why it is fair to compare matrix multiplication with generic float operations? It should be either comparison of matrix multiplication to matrix multiplication or generic float to generic float.

Well, one confounding factor is that CPU Flops are more generic, for any algorithm. GPU Flops as mentioned work better on tensor cases.

However, when we do have tensors, the GPU and CPU would both work to their full potential, and thus the flops comparison ought to be valid.

It wouldn't be a smooth app, but it would still render, which would be fun to play with.

solution looking for a problem?

though if anyone does know of problems this solves I'd love to hear about them, this is an incredibly cool solution.

Does every program need to be a solution to something? One might say the problem it solves is by satisfying one's desire for novelty.

Put another way: It's just really cool, and that can be enough.

I've often desperately wanted to put certain landscapes from my dreams into art, but I suck at drawing.

There are some dreams that I remember years later because of how beautiful they were, and how they made me feel. This would be a godsend if it works as well as the demo pictures show.

the problem is demand for stock images. i m not sure the quality here is good enough, but there's no reason why image-generating ANNs won't keep getting better

As of now maybe.. next version(s ?) will be probably animation to realistic movies.

but will it? my very limited experience with animation has been characterized by control: it's storytelling and creation where the creator is responsible for every fraction of a second. The value of this type of AI is in ceding control to an algorithm and letting it deal with the hard parts. My limited understanding is sort of pointing to a difference in goals of the two projects: one is for control, the other is for ease. And I don't think ease has a very stable place in animation.

Bro, they are letting you literally doodle children’s art and create solid photo manipulations. This kind of stuff took at least some creativity by hobbyist photoshoppers.

https://www.deviantart.com/high-quality/gallery/45794879/pho...

Believe it or not, it took some effort to take random scenery and create a solid composition. Take my job sure, but Jesus, not my hobby too. Now these people will have to compete against AI scrubs.

Concept art for games, movies, perhaps.

Digital matte painting is just about every single new film, tv show, game. Game of Thrones, marvel films, etc.

This is typically done by individual artists, and is time intensive.

See existing workflow here: https://youtu.be/V0qX7qmtMVw

https://conceptartempire.com/matte-painting/

I could see tech like this being a big hit for illustrations for low-budget self-publish book.

Stock photos are all good but sometimes you really need a visual of Illiyana the dragon vampire arriving at the three-towered mountain citadel with two moons overhead, on a budget of $10 or less.

This looks still dang hard for my cursed paws. I’m pretty sure it’s not easy for most people, and it still can’t beat google image search considering the amount of images.

Am I the only one who thinks this development is a bad idea?

Just extrapolate the obvious into the future. When everyone can create good art, despite being actually completely unskilled and untalented, then good art ceases to exist.

When everyone's an artist no one's an artist. It doesn't matter if we're not there yet, we will get there eventually and at that point it's too late.

... not that it's stoppable anyway.

That is very true my friend. I share the same opinion.

This AI art seems very menial to us, but not for the fresh minds.

This is same, and applies to our generation. When we were given tools to make art, our previous generations would have thought the same.

It's already happening. All these logos, designs and brochures looks the same now.

would you call them good art?

We'll just get different art instead. Compositions etc.

The same used to be said about photography. What is most important in true art is not being skilled with a paintbrush or Photoshop but ability to evoke different emotions and thoughts.

Exactly. Art has been past the point, where drawing photorealistic pictures was considered artistic talent, for over a century now.

How is "everyone can create art" a bad thing? That seems like gatekeeping.

It's like arguing against grammar and spell checking, because "if everyone can write good texts, then good texts cease to exist".

Also, imagine what actually talented people can do with tools like this.

When everyone can create good art

That is not what tools like this enable though? Will it not still require at least a bit of artistic sense to get something decent out of it? It just makes the technical aspect much easier. Some will benefit. Not everyone. Unless you're convinced there's a hidden artist in all of us?

It's just like with the introduction of small portable cameras decades ago (film/photo, doesn't matter) especially getting a lot better in the past decade: did we suddenly see great film/pictures being taken all over the place? No. We mainly saw a ton of crap, bad shots, bad home movies, you name it. And then some rather small fraction of people which earlier did not have the means to get quality material or were restricted in other ways, who got their hand on it and were able to deploy/discover their inherent talent. Which they could perhaps have done in other ways, but not as easy.

When photography appeared, it made a lot painters obsolete... It forced many to rethink their skills beyond reproducing faithfully nature.

That's the nature of progress and art.

Reply on news.ycombinator.com