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

can someone in the field explain why this has exploded recently? there seems to be a lot of these tools released recently (text to image) was there a major breakthrough? a new idea that pushed everyone forward? a recent sharing of talent between groups?

edit: just another thought, are they just being posted to HN now, i don't see a date on the page for when it was released . I also don't know the general term to find a list of all of these to find all the release dates

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

#6

Post by Rebelgecko » Thu, Aug 25, 2022, 5:55 AM UTC

NationOfJoe wrote: post #5

i only have a passing curiosity in these projects personally. can someone in the field explain why this has exploded recently? there seems to be a lot of these tools released recently (text to image) was there a major breakthrough? a new idea that pushed everyone forward? a recent sharing of talent between groups? edit: just another thought, are they just being posted to HN now, i don't see a date on the page for whe…

Not in the field, but maybe diffusion models? They seem to be used by a lot of different image generation techniques.

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

#7

Post by bottlepalm » Thu, Aug 25, 2022, 5:56 AM UTC

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.

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

#8

Post by tomthe » Thu, Aug 25, 2022, 6:01 AM UTC

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-diffusion-announcement

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

#9

Post by derac » Thu, Aug 25, 2022, 6:01 AM UTC

NationOfJoe wrote: post #5

i only have a passing curiosity in these projects personally. can someone in the field explain why this has exploded recently? there seems to be a lot of these tools released recently (text to image) was there a major breakthrough? a new idea that pushed everyone forward? a recent sharing of talent between groups? edit: just another thought, are they just being posted to HN now, i don't see a date on the page for whe…

The first major projects were OpenAI's DALL-E, then DALL-E 2 a year later. DALL-E 2 was much much better. After that a few new projects have been released in rapid succession including the open source stable diffusion.

Here are some of the projects on GitHub: https://github.com/topics/text-to-image

Another good source is https://paperswithcode.com/task/text-to-image-generation

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

#10

Post by rapnie » Thu, Aug 25, 2022, 6:03 AM UTC

NationOfJoe wrote: post #5

i only have a passing curiosity in these projects personally. can someone in the field explain why this has exploded recently? there seems to be a lot of these tools released recently (text to image) was there a major breakthrough? a new idea that pushed everyone forward? a recent sharing of talent between groups? edit: just another thought, are they just being posted to HN now, i don't see a date on the page for whe…

I don't know. This 'explosion' in the public space may just be the technology crossing a threshold where big $$$ are on the table and competitors rushing in to get hold of good chunks of the emerging market. No tech breakthrough, but a marketing & sales assault.