Ok. Now, how about the legality of it generating socially unacceptable images like child porn?
Imagen, a text-to-image diffusion model
91–100 of 661 posts
Re: Imagen, a text-to-image diffusion model
#92What's the best open source or pre-trained text to image model?
Re: Imagen, a text-to-image diffusion model
#93>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…
Reinforcement learning?
Re: Imagen, a text-to-image diffusion model
#94>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 gener…
> But is it a flaw that the model encodes the world as it really is
Does a bias towards lighter skin represent reality? I was under the impression that Caucasians are a minority globally.
I read the disclaimer as "the model does NOT represent reality".
Re: Imagen, a text-to-image diffusion model
#95Earlier quoted context omitted.
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 gener…
It depends on whether you'd like the model to learn casual or correlative relationships. If you want the model to understand what a "nurse" actually is, then it shouldn't be associated with female. If you want the model to understand how the word "nurse" is usually used, without regard for what a "nurse" actually is, then associating it with female is fine. The issue with a correlative model is that it can easily be…
Additionally, if you optimize for most-likely-as-best, you will end up with the stereotypical result 100% of the time, instead of in proportional frequency to the statistics.
Put another way, when we ask for an output optimized for "nursiness", is that not a request for some ur stereotypical nurse?
Re: Imagen, a text-to-image diffusion model
#96Jesus, this is so awesome. I think it’s the first AI that really makes me have that “wow” sensation.
Re: Imagen, a text-to-image diffusion model
#97Why is this seemingly official Google blog post on this random non-Google domain?
I'n not certain but I think it's prelease. The paper says the site should be at
https://imagen.research.google/ but that host doesn't respond
Re: Imagen, a text-to-image diffusion model
#98Earlier quoted context omitted.
The ironic part is that these "social and cultural biases" are purely from a Western, American lens. The people writing that paragraph are completely oblivious to the idea that there could be other cultures other than the Western American one. In attempting to prevent "encoding of social and cultural biases" they have encoded such biases themselves into their own research.
What makes you think the authors are all American?
The authors are listed on the page and a quick look at LinkedIn seem to be mostly Canadian.
Re: Imagen, a text-to-image diffusion model
#99Earlier quoted context omitted.
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.
Ah yes, deepfakes porn as a service would have been a blessing for teenage me.
Re: Imagen, a text-to-image diffusion model
#100Earlier quoted context omitted.
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.
If you type as a prompt "most beautiful woman in the world", you get a brown-skinned brown-haired woman with hazel eyes. What should be the right answer then ? You put a blonde, you offend the brown haired. You put blue eyes, you offend the brown eyes. etc.
That's an unanswerable question. Perhaps the answer is "don't".
Siri takes this approach for a wide range of queries.