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

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

imagen.research.google

Post reply on HN
Print view View original

11–20 of 233 posts

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

#11

Post by culi »

bottlepalm wrote: post #7

Smart for Dalle, Midjourney, and Stable Diffusion to capitalize on this quickly. It looks like the technology is being commoditized at rapid speed. I wonder what’s next.

People are getting into "prompt-craft". People have also started pasting different AI tools together like putting these images into CogVideo[0] to generate actual videos (takes ages and usually the length of a gif currently). Others have realized you can run these images through GANs to make faces look extremely convincing

I think "what's next" is fitting these tools together in a larger system

[0] https://replicate.com/nightmareai/cogvideo

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

#12

Post by carrozo »

anshul wrote: post #2

Does anyone know if or when google intends to make this available for beta testing or public use?

Towards the bottom of the page they say: “The potential risks of misuse raise concerns regarding responsible open-sourcing of code and demos. At this time we have decided not to release code or a public demo. In future work we will explore a framework for responsible externalization that balances the value of external auditing with the risks of unrestricted open-access.”

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

#13

Post by bottlepalm »

culi wrote: post #11
bottlepalm wrote: post #7

Smart for Dalle, Midjourney, and Stable Diffusion to capitalize on this quickly. It looks like the technology is being commoditized at rapid speed. I wonder what’s next.

People are getting into "prompt-craft". People have also started pasting different AI tools together like putting these images into CogVideo[0] to generate actual videos (takes ages and usually the length of a gif currently). Others have realized you can run these images through GANs to make faces look extremely convincing I think "what's next" is fitting these tools together in a larger system [0] https://replicate.…

Ok I’m just going to list ideas, feel free to add more

* Text to 3d model

* Text to video clip

* Illustrations for newspapers

* Generating pictures for food menus

* Generating a music video from a song

* Generating pictures or even an entire movie for a book

* Interior design ideas

* Product design ideas

I have noticed that leveraging these tools isn’t easy. It requires a fair bit of creativity to come up with the prompts to create an image to really wow somebody.

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

#14

Post by colordrops »

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.

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

#15

Post by culi »

tomthe wrote: post #8

From the cherry-picked example-images on that page, it seems like Imagen more closely follows the prompt than the open Stable Diffusion model[0]. Stable Diffusion needs a lot of hints before it makes out of the ordinary pictures. In general, I think these models are a great and funny toy, but not a threat to stock-photos yet. This may change within a year or three years though. [0]: https://stability.ai/blog/stable-d…

Not a threat to stock photos? That's exactly what they are. Look at these photos from the Midjourney Discord today:

crystal dragon thing:

https://cdn.discordapp.com/attachments/951197655021797436/10...

https://cdn.discordapp.com/attachments/951197655021797436/10...

https://cdn.discordapp.com/attachments/951197655021797436/10...

davinci-style notebook of flying machines:

https://cdn.discordapp.com/attachments/1008049109338443829/1...

https://cdn.discordapp.com/attachments/1008049109338443829/1...

this person tried to show the life cycle of an alien:

https://cdn.discordapp.com/attachments/1010211132671275058/1...

https://cdn.discordapp.com/attachments/1010211132671275058/1...

https://cdn.discordapp.com/attachments/1010211132671275058/1...

https://cdn.discordapp.com/attachments/1010211132671275058/1...

cavemen taking a group selfie (lots of faces)

https://cdn.discordapp.com/attachments/1011408429170044928/1...

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

#17

Post by stevewatson301 »

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.

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

#18

Post by culi »

bottlepalm wrote: post #13
culi wrote: post #11

Earlier quoted context omitted.

People are getting into "prompt-craft". People have also started pasting different AI tools together like putting these images into CogVideo[0] to generate actual videos (takes ages and usually the length of a gif currently). Others have realized you can run these images through GANs to make faces look extremely convincing I think "what's next" is fitting these tools together in a larger system [0] https://replicate.…

Ok I’m just going to list ideas, feel free to add more * Text to 3d model * Text to video clip * Illustrations for newspapers * Generating pictures for food menus * Generating a music video from a song * Generating pictures or even an entire movie for a book * Interior design ideas * Product design ideas I have noticed that leveraging these tools isn’t easy. It requires a fair bit of creativity to come up with the pr…

Someone on the midjourney discord is making a comic with images generated by the bot. Another person is making a Magic The Gathering card pack with generated art (it looks good too!). People are already using it for stock photos

One murky area we're still far away from but I'm curious to follow the developments on: AI-generated movies. Once generated clips gets good, what if some movie buff can just generate a movie, scene-by-scene, just using these tools? What about "casting" certain celebrities? The comic I mentioned uses Zendaya (probably because she plays a character in the Dune movies) as a character

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

#19

Post by sh4rks »

culi wrote: post #15
tomthe wrote: post #8

From the cherry-picked example-images on that page, it seems like Imagen more closely follows the prompt than the open Stable Diffusion model[0]. Stable Diffusion needs a lot of hints before it makes out of the ordinary pictures. In general, I think these models are a great and funny toy, but not a threat to stock-photos yet. This may change within a year or three years though. [0]: https://stability.ai/blog/stable-d…

Not a threat to stock photos? That's exactly what they are. Look at these photos from the Midjourney Discord today: crystal dragon thing: https://cdn.discordapp.com/attachments/951197655021797436/10... https://cdn.discordapp.com/attachments/951197655021797436/10... https://cdn.discordapp.com/attachments/951197655021797436/10... davinci-style notebook of flying machines: https://cdn.discordapp.com/attachments/10080491…

The davinci ones are incredibly intricate

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

#20

Post by 8n4vidtmkvmk »

culi wrote: post #15
tomthe wrote: post #8

From the cherry-picked example-images on that page, it seems like Imagen more closely follows the prompt than the open Stable Diffusion model[0]. Stable Diffusion needs a lot of hints before it makes out of the ordinary pictures. In general, I think these models are a great and funny toy, but not a threat to stock-photos yet. This may change within a year or three years though. [0]: https://stability.ai/blog/stable-d…

Not a threat to stock photos? That's exactly what they are. Look at these photos from the Midjourney Discord today: crystal dragon thing: https://cdn.discordapp.com/attachments/951197655021797436/10... https://cdn.discordapp.com/attachments/951197655021797436/10... https://cdn.discordapp.com/attachments/951197655021797436/10... davinci-style notebook of flying machines: https://cdn.discordapp.com/attachments/10080491…

those were generated? those look dope
Post reply on HN