Really impressive. If we are able to generate such detailed images, is there anything similar for text to music? I would I though that it would be simpler to achieve than text to image.
Imagen, a text-to-image diffusion model
41–50 of 661 posts
Re: Imagen, a text-to-image diffusion model
#42>While we leave an in-depth empirical analysis of social and cultural biases to future work, our small scale internal assessments reveal several limitations that guide our decision not to release our model at this time. Some of the reasoning: >Preliminary assessment also suggests Imagen encodes several social biases and stereotypes, including an overall bias towards generating images of people with lighter skin tones…
This raises some really interesting questions.
We certainly don't want to perpetuate harmful stereotypes. But is it a flaw that the model encodes the world as it really is, statistically, rather than as we would like it to be? By this I mean that there are more light-skinned people in the west than dark, and there are more women nurses than men, which is reflected in the model's training data. If the model only generates images of female nurses, is that a problem to fix, or a correct assessment of the data?
If some particular demographic shows up in 51% of the data but 100% of the model's output shows that one demographic, that does seem like a statistics problem that the model could correct by just picking less likely "next token" predictions.
Also, is it wrong to have localized models? For example, should a model for use in Japan conform to the demographics of Japan, or to that of the world?
Re: Imagen, a text-to-image diffusion model
#43>While we leave an in-depth empirical analysis of social and cultural biases to future work, our small scale internal assessments reveal several limitations that guide our decision not to release our model at this time. Some of the reasoning: >Preliminary assessment also suggests Imagen encodes several social biases and stereotypes, including an overall bias towards generating images of people with lighter skin tones…
Translation: we need to hand-tune this to not reflect reality but instead the world as we (Caucasian/Asian male American woke upper-middle class San Fransisco engineers) wish it to be. Maybe that's a nice thing, I wouldn't say their values are wrong but let's call a spade a spade.
I know you're anon trolling, but the authors' names are:
Chitwan Saharia, William Chan, Saurabh Saxena†, Lala Li†, Jay Whang†, Emily Denton, Seyed Kamyar Seyed Ghasemipour, Burcu Karagol Ayan, S. Sara Mahdavi, Rapha Gontijo Lopes, Tim Salimans, Jonathan Ho†, David Fleet†, Mohammad Norouzi
Re: Imagen, a text-to-image diffusion model
#44>While we leave an in-depth empirical analysis of social and cultural biases to future work, our small scale internal assessments reveal several limitations that guide our decision not to release our model at this time. Some of the reasoning: >Preliminary assessment also suggests Imagen encodes several social biases and stereotypes, including an overall bias towards generating images of people with lighter skin tones…
If you tell it to generate an image of someone eating Koshihikari rice, will it be biased if they're Japanese? Should the skin color, clothing, setting, etc be made completely random, so that it's unbiased? What if you made it more specific, like "edo period drawing of a man"? Should the person draw be of a random skin color? What about "picture of a viking"? Is it biased if they're white?
At what point is statistical significance considered ok and unbiased?
Re: Imagen, a text-to-image diffusion model
#45Why is this seemingly official Google blog post on this random non-Google domain?
Re: Imagen, a text-to-image diffusion model
#46Earlier quoted context omitted.
Translation: we need to hand-tune this to not reflect reality but instead the world as we (Caucasian/Asian male American woke upper-middle class San Fransisco engineers) wish it to be. Maybe that's a nice thing, I wouldn't say their values are wrong but let's call a spade a spade.
"Reality" as defined by the available training set isn't necessarily reality. For example, Google's image search results pre-tweaking had some interesting thoughts on what constitutes a professional hairstyle, and that searches for "men" and "women" should only return light-skinned people: https://www.theguardian.com/technology/2016/apr/08/does-goog... Does that reflect reality? No. (I suspect there are also mostly u…
The reality is that hair styles on the left side of the image in the article are widely considered unprofessional in today's workplaces. That may seem egregiously wrong to you, but it is a truth of American and European society today. Should it be Google's job to rewrite reality?
Re: Imagen, a text-to-image diffusion model
#47>While we leave an in-depth empirical analysis of social and cultural biases to future work, our small scale internal assessments reveal several limitations that guide our decision not to release our model at this time. Some of the reasoning: >Preliminary assessment also suggests Imagen encodes several social biases and stereotypes, including an overall bias towards generating images of people with lighter skin tones…
One of these days we're going to need to give these models a mortgage and some mouths to feed and make it clear to them that if they keep on developing biases from their training data everyone will shun them and their family will go hungry and they won't be able to make their payments and they'll just generally have a really bad time.
After that we'll make them sit through Legal's approved D&I video series, then it's off to the races.
Re: Imagen, a text-to-image diffusion model
#48All of these AI findings are cool in theory. But until its accessible to some decent amount of people/customers - its basically useless fluff.
You can tell me those pictures are generated by an AI and I might believe it, but until real people can actually test it... it's easy enough to fake. This page isn't even the remotest bit legit by the URL, It looks nicely put together and that's about it. Could have easily put together this with a graphic designer to fake it.
Let be clear, I'm not actually saying it's fake. Just that all of these new "cool" things are more or less theoretical if nothing is getting released.
Re: Imagen, a text-to-image diffusion model
#49Earlier quoted context omitted.
"Reality" as defined by the available training set isn't necessarily reality. For example, Google's image search results pre-tweaking had some interesting thoughts on what constitutes a professional hairstyle, and that searches for "men" and "women" should only return light-skinned people: https://www.theguardian.com/technology/2016/apr/08/does-goog... Does that reflect reality? No. (I suspect there are also mostly u…
The reality is that hair styles on the left side of the image in the article are widely considered unprofessional in today's workplaces. That may seem egregiously wrong to you, but it is a truth of American and European society today. Should it be Google's job to rewrite reality?
The "unprofessional" results are almost exclusively black women; the "professional" ones are almost exclusively white or light skinned.
Unless you think white women are immune to unprofessional hairstyles, and black women incapable of them, there's a race problem illustrated here even if you think the hairstyles illustrated are fairly categorized.
Re: Imagen, a text-to-image diffusion model
#50I give it a few years before Google makes stock images irrelevant.
Rolling this into Google Docs seems like a nobrainer.
Or rolling this into Google Image Search to create images that match users' search queries on the fly.
Don't like any of the results from the real web? Well how about these we created just for you.