Imagen: An AI system that creates photorealistic images from input text • Hacker News Board

Re: Imagen: An AI system that creates photorealistic images from input text

#231

Post by tgv » Fri, Aug 26, 2022, 10:14 AM UTC

rhacker wrote: post #187

tgv wrote: post #121

Earlier quoted context omitted.

Indeed, you can't be trusted not do anything bad with it. Who's going to vet each and every user? Who's going to check every time it's used for the coming 10, 20, 30 years?

If he's racist he can already hire black people to take a photo for an "upcoming action movie" called evil baby. They will be asked to hold guns aiming it at a crib. Then release it on the internet and say he saw 3 black people about to shoot a baby. It would be called out as fake or staged just like an imagen/walle2/openai would be called out as fake. The thing that makes stories real is real people - actual events…

If he wants a picture of a dog with sunglasses in a boat, he can hire a dog, a handler, and a boat. He doesn't need this model for anything.

> The thing that makes stories real

Since when do the hordes care about stories being real? People get harassed over photoshopped images. People get killed over false rumors. These tools make it easier to trigger such reactions.

Re: Imagen: An AI system that creates photorealistic images from input text

#232

Post by taneq » Fri, Aug 26, 2022, 10:28 AM UTC

stevewatson301 wrote: post #17

colordrops wrote: post #14

Is Google going to share or do something other than better advertising with this? What do they plan to do with it? I'm frankly tired of these show-off blog posts by Google that neither make it into general hands nor are used for anything positive. This is just a link to their previous posted site btw, nothing new.

My guess is they're they'll use Imagen and LaMDA to build a "conversational" search experience of some kind. So, instead of providing a list of websites to go to, they'll synthesize an answer to the search query, with imagery to go along with it, and so on.

Plans to build conversational agents always seem to ignore Moravec’s paradox. The hard bit of building such an agent is in building a tolerably human-like conversational partner, not in searching and sorting data.

It’s like the “AI” projects that spend all their time building a fancy sci-fi-looking robot body, ignoring the fact that how much of a “person” a robot seems has almost nothing to do with how physically anthropomorphic it is. Johnny 5 and Wall-e are proof enough that the mind, not the geometry of the body, is what’s important.

Re: Imagen: An AI system that creates photorealistic images from input text

#233

Post by neurostimulant » Fri, Aug 26, 2022, 3:43 PM UTC

prophesi wrote: post #136

SXX wrote: post #84

Earlier quoted context omitted.

Fortunately we have Stability.AI and they release their image generation model already. Hopefully they'll follow with other projects too. https://stability.ai/blog/stable-diffusion-public-release

There's also a fork that requires a lot less VRAM. I was able to get this working with an Nvidia GTX 1070. https://github.com/basujindal/stable-diffusion You'd clone the fork, then download Stability AI's checkpoint, sd-v1-4.ckpt, from https://huggingface.co/CompVis/stable-diffusion-v-1-4-origin... Follow the instructions in the forked repo, and you should be good to go in a manner of minutes.

I'm able to make it works on my GTX 1650 LP. Had to use full precision though or else it generates green images. I also had to reduce the resolution to 320x320 and close every applications that uses vram because the GPU only has 4GB of vram. Took about 2 minutes to generate a single image with ddim sampling steps set to 50.