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

TokenVerse: Multi-Concept Personalization in Token Modulation Space by Google

token-verse.github.io

Post reply on HN
Print view View original

11–20 of 24 posts

Re: TokenVerse: Multi-Concept Personalization in Token Modulation Space by Google

#11

Post by doctorpangloss »

rprwhite wrote: post #10
doctorpangloss wrote: post #8

Earlier quoted context omitted.

Yes. But. The reference photo is blurred. The smallest details matter for faces! That's the whole point. I have no doubt you can do a kind-of-looks-like faces. But this is the same issue since Dreambooth. All the IP transfer approaches, even the best like Ideogram's, are failing on faces.

There's two images where the face is transferred to the final image. The references images with blurred faces are all being used for a different reference; the pose, or "necklace", etc. The faces are blurred in every image unless they explicitly want the face transferred to the final image, at least that's how it seems.

I know. But there are no unblurred source images of faces. This isn't complicated.

Re: TokenVerse: Multi-Concept Personalization in Token Modulation Space by Google

#12

Post by danpalmer »

doctorpangloss wrote: post #11
rprwhite wrote: post #10

Earlier quoted context omitted.

There's two images where the face is transferred to the final image. The references images with blurred faces are all being used for a different reference; the pose, or "necklace", etc. The faces are blurred in every image unless they explicitly want the face transferred to the final image, at least that's how it seems.

I know. But there are no unblurred source images of faces. This isn't complicated.

https://token-verse.github.io/results/multi_concepts/25.png

https://token-verse.github.io/results/multi_concepts/06.png

Both of these show a man's face in a source image being used in a newly generated image. I agree that it isn't complicated, but you seem to be drawing different conclusions to everyone else here.

If your point is that it can't perform face transfer, you seem to be wrong - that's what's happening here. If your point is that the blurred photos used for other parts of the input mean that this suggests the model may get confused by other faces, then that's a fair point, but it seems clear they have demonstrated face transfer, and requiring blurring irrelevant faces seems a minor point compared to transferring the face that's intended. I'm not sure how that would really impact use-cases.

Re: TokenVerse: Multi-Concept Personalization in Token Modulation Space by Google

#13

Post by doctorpangloss »

danpalmer wrote: post #12
doctorpangloss wrote: post #11

Earlier quoted context omitted.

I know. But there are no unblurred source images of faces. This isn't complicated.

https://token-verse.github.io/results/multi_concepts/25.png https://token-verse.github.io/results/multi_concepts/06.png Both of these show a man's face in a source image being used in a newly generated image. I agree that it isn't complicated, but you seem to be drawing different conclusions to everyone else here. If your point is that it can't perform face transfer, you seem to be wrong - that's what's happening her…

Well. If they had working face / human character transfer, listen, my dude, every single image would show a face transfer. It's one of the biggest challenges.

Re: TokenVerse: Multi-Concept Personalization in Token Modulation Space by Google

#14

Post by mettamage »

jasonjmcghee wrote: post #2

Feels like a moodboarding multiplier for some design disciplines, if these aren't cherry-picked / transfer to other domains. Pretty interesting. Seems like you could apply similar ideas to text too.

Not just a moodboard if you can highlight the words you want in your output.

Re: TokenVerse: Multi-Concept Personalization in Token Modulation Space by Google

#15

Post by jiggawatts »

“Code coming soon” from Google means basically never.

I don’t understand why they keep making these announcements and then just sitting on the results.

This is an immediately commercially useful product even as an API. You could make a mobile app for kids to “create their own cartoon story”.

Someone else will have to reproduce this for it to see the light of day.

Re: TokenVerse: Multi-Concept Personalization in Token Modulation Space by Google

#16

Post by Kiro »

jiggawatts wrote: post #15

“Code coming soon” from Google means basically never. I don’t understand why they keep making these announcements and then just sitting on the results. This is an immediately commercially useful product even as an API. You could make a mobile app for kids to “create their own cartoon story”. Someone else will have to reproduce this for it to see the light of day.

I have the same feeling but I wonder if it's actually true. Do we have any examples of announcements where the code was never released?

Re: TokenVerse: Multi-Concept Personalization in Token Modulation Space by Google

#19

Post by rhet0rica »

doctorpangloss wrote: post #13
danpalmer wrote: post #12

Earlier quoted context omitted.

https://token-verse.github.io/results/multi_concepts/25.png https://token-verse.github.io/results/multi_concepts/06.png Both of these show a man's face in a source image being used in a newly generated image. I agree that it isn't complicated, but you seem to be drawing different conclusions to everyone else here. If your point is that it can't perform face transfer, you seem to be wrong - that's what's happening her…

Well. If they had working face / human character transfer, listen, my dude, every single image would show a face transfer. It's one of the biggest challenges.

Hot take: there are no legitimate use cases for human face transfer.
Post reply on HN