Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Nvidia Canvas: AI for creating realistic landscape images

nvidia.com

Post reply on HN
Print view View original

11–19 of 19 posts

Re: Nvidia Canvas: AI for creating realistic landscape images

#11

Post by Wertigoyr »

axg11 wrote: post #6

Nvidia's approach to software is really interesting, and demonstrates that they have a hardware culture through and through. They could turn Canvas into a web app and charge a monthly subscription. Alternatively they could go the OpenAI GPT-3/DALL-E-2 route and give it away as a web app or API to generate a huge potential customer list. Instead, they're only interested in technology demonstrations. I'm not arguing th…

It demonstrate that they feel that the software is better free to push their GPUs and this has a higher return than otherwise.

I'm quite lost on what you think would pay for this kind of software?

Re: Nvidia Canvas: AI for creating realistic landscape images

#12

Post by ShamelessC »

SilverBirch wrote: post #2

Can I ask, was there an underlying reason that people deciding to pursue this image generation task, or is this literally just the result of throwing lots of tasks at different types of AI until you finally find one it seems to do well? I don't mean to denigrate this, the results are clearly interesting, but I just don't understand what problem this solves, it just seems to raise the noise floor on reality.

tl;dr - It’s a GAN, they have some interesting limitations but can output 1024px images in real time on a consumer gpu.

The training labels may have been “segmentation maps”. These are regions of an image with a known scene description such as “cloud”, “trees”, “sky”. I’m not certain what model they use, but I bet it is a Stylegan2/3 modified to generate an image from a given set of segmentation masks.

Indeed, without the research context, it’s a little strange “why” you would want a product like this. Nvidia has done a lot of research to get GAN to run very fast on their RTX cards due to being mostly convolutional, operating directly in pixel (or wavelet) space rather than an embedding space. On my RTX 2070, I can run Stylegan2 at 1024px at a somewhat reasonable 10 FPS.

Re: Nvidia Canvas: AI for creating realistic landscape images

#13

Post by Archit3ch »

axg11 wrote: post #6

Nvidia's approach to software is really interesting, and demonstrates that they have a hardware culture through and through. They could turn Canvas into a web app and charge a monthly subscription. Alternatively they could go the OpenAI GPT-3/DALL-E-2 route and give it away as a web app or API to generate a huge potential customer list. Instead, they're only interested in technology demonstrations. I'm not arguing th…

There is a large gap from tech demo to product, and it's even larger for AI products.

Re: Nvidia Canvas: AI for creating realistic landscape images

#14

Post by pedalpete »

SilverBirch wrote: post #2

Can I ask, was there an underlying reason that people deciding to pursue this image generation task, or is this literally just the result of throwing lots of tasks at different types of AI until you finally find one it seems to do well? I don't mean to denigrate this, the results are clearly interesting, but I just don't understand what problem this solves, it just seems to raise the noise floor on reality.

There is a real use case for this type of technology.

I'm the founder of https://ayvri.com, and we have a 3D virtual world where outdoor athletes watch their activities, and the activities of others.

As the resolution (and speed) of our 3D world improved, people got more interested and engaged with it.

I believe this is the future of video. Not volumetrically created through 20+ cameras, but with a single camera capturing the scene, and AI filling in the blanks based on what it knows.

Re: Nvidia Canvas: AI for creating realistic landscape images

#15

Post by oddity »

axg11 wrote: post #6

Nvidia's approach to software is really interesting, and demonstrates that they have a hardware culture through and through. They could turn Canvas into a web app and charge a monthly subscription. Alternatively they could go the OpenAI GPT-3/DALL-E-2 route and give it away as a web app or API to generate a huge potential customer list. Instead, they're only interested in technology demonstrations. I'm not arguing th…

The average consumer is more willing to pay for hardware than software, even if all the value is created by the software.

It's the reason why Apple no longer charges for OS updates. Nvidia has essentially the same business model.

It's very hard to sell software to $averageconsumer unless that software is "free"

Re: Nvidia Canvas: AI for creating realistic landscape images

#16

Post by YetAnotherNick »

axg11 wrote: post #6

Nvidia's approach to software is really interesting, and demonstrates that they have a hardware culture through and through. They could turn Canvas into a web app and charge a monthly subscription. Alternatively they could go the OpenAI GPT-3/DALL-E-2 route and give it away as a web app or API to generate a huge potential customer list. Instead, they're only interested in technology demonstrations. I'm not arguing th…

They have a monopoly on AI hardware, so it makes perfect sense for them to make people care about AI.

Re: Nvidia Canvas: AI for creating realistic landscape images

#19

Post by tinus_hn »

axg11 wrote: post #6

Nvidia's approach to software is really interesting, and demonstrates that they have a hardware culture through and through. They could turn Canvas into a web app and charge a monthly subscription. Alternatively they could go the OpenAI GPT-3/DALL-E-2 route and give it away as a web app or API to generate a huge potential customer list. Instead, they're only interested in technology demonstrations. I'm not arguing th…

It’s fun to play with but most people really don’t have a reason to spend money on this kind of software.
Post reply on HN