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

Tuning-Free Personalized Image Generation

ai.meta.com

Post reply on HN
Print view View original

11–20 of 49 posts

Re: Tuning-Free Personalized Image Generation

#11

Post by kkielhofner »

phkahler wrote: post #3
LarsDu88 wrote: post #2

Up until recently, to insert yourself into an image generation algorithm, you had to use a technique like Dreambooth, which involves finetuning the model itself with a new mapping of the subject to a rare token. Meta just released and productionized a new technique that doesn't require finetuning at all. This enables a whole host of new possibilities... People can now be inserted into scenes or outfits at will withou…

This will be great for people on Instagram.

Given how absurd Instagram/social media already is (entire cottage industries of "private jet" stages in warehouses, etc) it will arguably be a benefit for society when it completely jumps the shark and anyone can generate over the top ridiculousness in seconds.

Re: Tuning-Free Personalized Image Generation

#13

Post by smokel »

Photographic images generated by these systems tend to look like the graffiti portraits you see on fairground attractions.

I've done a lot of photorealistic drawings, and the trick to make something look real, is to get the tones exactly right. Misjudge a tone a bit, and the result looks like a mediocre drawing or a painting. In other words, the gradient of skin tones is off, which is ironic, I guess.

I assume that there is a systemic error in (linearly?) interpolating colors (in the wrong color space?) somewhere, which potentially could be easy to fix and lead to improved photorealism. On the other hand, it might be a horrible problem to fix, because it would require accurate radiosity and raytracing to get right.

Re: Tuning-Free Personalized Image Generation

#14

Post by jsheard »

smokel wrote: post #13

Photographic images generated by these systems tend to look like the graffiti portraits you see on fairground attractions. I've done a lot of photorealistic drawings, and the trick to make something look real, is to get the tones exactly right. Misjudge a tone a bit, and the result looks like a mediocre drawing or a painting. In other words, the gradient of skin tones is off, which is ironic, I guess. I assume that t…

I know what you mean, my theory is that it's an emergent property from RLHF tuning penalizing examples of bad/incoherent lighting, which pushes the model towards that kind of vague "lit from everywhere" style which is relatively easy to sell as correct without a proper understanding of light transport. It looks amateurish because that's the same trick an amateur human might use to try to sell photorealism without good lighting fundamentals.

Re: Tuning-Free Personalized Image Generation

#15

Post by GaggiX »

smokel wrote: post #13

Photographic images generated by these systems tend to look like the graffiti portraits you see on fairground attractions. I've done a lot of photorealistic drawings, and the trick to make something look real, is to get the tones exactly right. Misjudge a tone a bit, and the result looks like a mediocre drawing or a painting. In other words, the gradient of skin tones is off, which is ironic, I guess. I assume that t…

The fact that these models rely heavily on classifier-free guidance has a strong impact on the tones of the image.

Re: Tuning-Free Personalized Image Generation

#16

Post by GaggiX »

LarsDu88 wrote: post #2

Up until recently, to insert yourself into an image generation algorithm, you had to use a technique like Dreambooth, which involves finetuning the model itself with a new mapping of the subject to a rare token. Meta just released and productionized a new technique that doesn't require finetuning at all. This enables a whole host of new possibilities... People can now be inserted into scenes or outfits at will withou…

>Up until recently, to insert yourself into an image generation algorithm, you had to use a technique like Dreambooth

I mean, not really, you could just train a LoRA for example (it doesn't require training with Dreambooth).

Re: Tuning-Free Personalized Image Generation

#17

Post by add-sub-mul-div »

robterrell wrote: post #7
educasean wrote: post #6

The future of Netflix isn't going to feature DiCaprio or Zendaya. It will be you, your wife, and your friends on the screen as hobbits adventuring to Mordor.

Is this a common desire? I have absolutely no interest in watching myself inserted into a film or TV show.

It sounds like it would be a common desire, like when you see the futuristic computer interface in Minority Report. It seems cool on the surface but falls apart the minute you imagine the reality of using it in practice. Your arms would get tired very quickly trying to control an interface in 3D space.

The idea that we'd someday have no more shared experience around media is harrowing and thankfully the public isn't actually calling for it.

Re: Tuning-Free Personalized Image Generation

#18

Post by TylerE »

smokel wrote: post #13

Photographic images generated by these systems tend to look like the graffiti portraits you see on fairground attractions. I've done a lot of photorealistic drawings, and the trick to make something look real, is to get the tones exactly right. Misjudge a tone a bit, and the result looks like a mediocre drawing or a painting. In other words, the gradient of skin tones is off, which is ironic, I guess. I assume that t…

It doesn’t help that RGB is very badly tuned for many skin tones.

Re: Tuning-Free Personalized Image Generation

#19

Post by baq »

LarsDu88 wrote: post #5
fxtentacle wrote: post #4

I know exactly why Facebook / Meta are researching this. Just imagine the possibilities for advertisers: Instead of telling someone how happy they would be if only they bought your expensive car, let's just spam them with AI pictures of themselves sitting in said expensive car, ideally next to some very attractive other people that match their dating preferences. Facebook has all the data they need to create very ple…

This is a much bigger thing than the llama3.1 release. Llama 3.1 doesn't really help Meta's bottom line. But content creation and ads are Meta's killer app. By having a model that doesn't require finetuning, they just changed the whole game.

Where do I sign up for my personalized AI content filter bot which can reliably detect ads and remove them from my browser?
Post reply on HN