Hacker News Reader

Comment by amazingamazing | Hacker News Reader

Don’t understand the remove from face example. Without other pictures showing the persons face, it’s just using some stereotypical image, no?

View on HN

There's no "truth" it's uncovering, no real face, these are all just generated images, yes.

I get that but usually you would have two inputs, the reference “true”, and the target that it to be manipulated.

Not necessarily. "As you may see, this is a Chinese lady. You have seen a number of Chinese ladies in your training set. Imagine the face of this lady so that it won't contradict the fragment visible on the image with the snowflake". (Damn, it's a pseudocode prompt.)

yes, so a stereotypical image. my point is best illustrated if you look at all of the photos of the woman.

Even if you provide another image (which you totally can btw) the model is still generalizing predictions enough that you can say it's just making a strong guess about what is concealed.

I guess my main point is "this is where you draw the line? at a mostly accurate reconstruction of a partial of someone's face?" this was science fiction a few years ago. Training the model to accept two images (which it can, just not for explicit purposes of reconstructing (although it learns that too )) seems like a very task-specific, downstream way to handle this issue. This field is now about robust, general ways to emerge intelligent behavior not task specific models.

is it mostly accurate though? how would you know? suppose you had an asian woman whose face is entirely covered with snow.

sure you could tell AI to remove the snow and some face will be revealed, but who is to say it's accurate? that's why traditionally you have a reference input.

What's the traditional workflow? I haven't seen that done before, but it's something I'd like to try. Could supply the "wrong" reference too, to get something specific.

> sure you could tell AI to remove the snow and some face will be revealed, but who is to say it's accurate? that's why traditionally you have a reference input.

As I stated a few times, the model HAS SUPPORT FOR MULTIPLE IMAGES. The article here doesn't try your very specific reference-image-benchmark but that doesn't mean you can't do it yourself - and it also doesn't imply there's anything wrong with the article or BFL - they're merely presenting a common usecase - not defining how the model should be used.

Look more closely at the example. Clearly there is an opportunity for inference with objects that only partially obscure.

I think they are doing that because using real images the model changes the face. So that problem is removed if the initial image doesn't show the face

Mm, depends on the underlying model and where it is in the pipeline; identity models are pretty sophisticated at interpolating faces from partial geometry.

The slideshow appears to be glitched on that first example. The input image has a snowflake covering most of her face.

That's the point, it can remove it.

They chosen Asian traits that Western beauty standards fetishize that in Asia wouldn't be taken serious at all.

I notice American text2image models tend to generate less attractive and more darker skinned humans where as Chinese text2image generate attractive and more light skinned humans.

I think this is another area where Chinese AI models shine.

> notice American text2image models tend to generate less attractive and more darker skinned humans where as Chinese text2image generate attractive and more light skinned humans

This seems entirely subjective to me.

> They chosen Asian traits that Western beauty standards fetishize that in Asia wouldn't be taken serious at all.

> where as Chinese text2image generate attractive and more light skinned humans.

Are you saying they have chosen Asian traits that Asian beauty standards fetishize that in the West wouldn't be taken seriously at all? ;) There is no ground truth here that would be more correct one way or the other.

Wow, that is some straight-up overt racism. You should be ashamed.

It reads as racist if you parse it as (skin tone and attractiveness) but if you instead parse it as (skin tone) and (attractiveness), ie as two entirely unrelated characteristics of the output, then it reads as nothing more than a claim about relative differences in behavior between models.

Of course, given the sensitivity of the topic it is arguably somewhat inappropriate to make such observations without sufficient effort to clarify the precise meaning.

I find that people who are hypersensitive to racism are usually themselves pretty racist. It's like people who are aroused by something taboo are usually the biggest critic. I forget what this phenomena is called.

Calling out overt racism is not “hypersensitivity” and in what fucking world could it be racism? This mentality is why the tech industry is so screwed up.

You have your head in your ass. Read the text:

> Chinese text2image generate attractive and more light skinned humans. > I think this is another area where Chinese AI models shine.

That is racism. There simply is no other way to classify it.

Asians can be pretty colorist within themselves and they're not going to listen to you when you tell them it's bad. Asian women love skin-lightening creams.

This particular woman looks Vietnamese to me, but I agree nothing about her appearance looks like anyone's fashion I know. But I only know California ABGs so that doesn't mean much.

Reply on news.ycombinator.com