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

Imagen, a text-to-image diffusion model

gweb-research-imagen.appspot.com

Post reply on HN
Print view View original

171–180 of 661 posts

Re: Imagen, a text-to-image diffusion model

#171

Post by astrange »

jvalencia wrote: post #122
jdashg wrote: post #95

Earlier quoted context omitted.

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?

You could simply encode a score for how well the output matches the input. If 25% of trees in summer are brown, perhaps the output should also have 25% brown. The model scores itself on frequencies as well as correctness.

The only reason these models work is that we don’t interfere with them like that.

Your description is closer to how the open source CLIP+GAN models did it - if you ask for “tree” it starts growing the picture towards treeness until it’s all averagely tree-y rather than being “a picture of a single tree”.

It would be nice if asking for N samples got a diversity of traits you didn’t explicitly ask for. OpenAI seems to solve this by not letting you see it generate humans at all…

Re: Imagen, a text-to-image diffusion model

#173

Post by joeycodes »

benwikler wrote: post #27

Would be fascinated to see the DALL-E output for the same prompts as the ones used in this paper. If you've got DALL-E access and can try a few, please put links as replies!

Posting a few comparisons here.

https://twitter.com/joeyliaw/status/1528856081476116480?s=21...

Re: Imagen, a text-to-image diffusion model

#174

Post by addandsubtract »

jonahbenton wrote: post #155

I know that some monstrous majority of cognitive processing is visual, hence the attention these visually creative models are rightfully getting, but personally I am much more interested in auditory information and would love to see a promptable model for music. Was just listening to "Land Down Under" from Men At Work. Would love to be able to prompt for another artist I have liked: "Tricky playing Land Down Under."…

I agree. How cool would it be to get an 8 min version of your favorite song? Or an instant DnB remix? Or 10 more songs in the style of your favorite album?

Re: Imagen, a text-to-image diffusion model

#175

Post by tines »

Imnimo wrote: post #163
tines wrote: post #42

Earlier 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…

>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. Yeah, but you get that same effect on every axis, not just the one you're trying to correct. You might get male nurses, but they have green hair and six fingers, because you're…

Yeah, good point, it's not as simple as I thought.

Re: Imagen, a text-to-image diffusion model

#177

Post by mdp2021 »

LudwigNagasena wrote: post #137
karpierz wrote: post #61

Earlier quoted context omitted.

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…

> 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. That’s a distinction without a difference. Meaning is use.

Very certainly not, since use is individual and thus a function of competence. So, adherence to meaning depends on the user. Conflict resolution?

And anyway - contextually -, the representational natures of "use" (instances) and that of "meaning" (definition) are completely different.

Re: Imagen, a text-to-image diffusion model

#178

Post by bogwog »

daenz wrote: post #7

>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…

I wouldn't describe this situation as "sad". Basically, this decision is based on a belief that tech companies should decide what our society should look like. I don't know what emotion that conjures up for you, but "sadness" isn't it for me.

Re: Imagen, a text-to-image diffusion model

#179

Post by varenc »

nomel wrote: post #59
wmfrov wrote: post #51

Earlier quoted context omitted.

Looks like no, "The potential risks of misuse raise concerns regarding responsible open-sourcing of code and demos. At this time we have decided not to release code or a public demo. In future work we will explore a framework for responsible externalization that balances the value of external auditing with the risks of unrestricted open-access."

> the risks of unrestricted open-access What exactly is the risk?

See section 6 titled “Conclusions, Limitations and Societal Impact” in the research paper: https://gweb-research-imagen.appspot.com/paper.pdf

One quote:

> “On the other hand, generative methods can be leveraged for malicious purposes, including harassment and misinformation spread [20], and raise many concerns regarding social and cultural exclusion and bias [67, 62, 68]”

Re: Imagen, a text-to-image diffusion model

#180

Post by adriand »

daenz wrote: post #80
tines wrote: post #42

Earlier 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…

I think the statistics/representation problem is a big problem on its own, but IMO the bigger problem here is democratizing access to human-like creativity. Currently, the ability to create compelling art is only held by those with some artistic talent. With a tool like this, that restriction is gone. Everyone, no matter how uncreative, untalented, or uncommitted, can create compelling visuals, provided they can use…

> So even if we managed to create a perfect model of representation and inclusion, people could still use it to generate extremely offensive images with little effort. I think people see that as profoundly dangerous.

Do they see it as dangerous? Or just offensive?

I can understand why people wouldn’t want a tool they have created to be used to generate disturbing, offensive or disgusting imagery. But I don’t really see how doing that would be dangerous.

In fact, I wonder if this sort of technology could reduce the harm caused by people with an interest in disgusting images, because no one needs to be harmed for a realistic image to be created. I am creeping myself out with this line of thinking, but it seems like one potential beneficial - albeit disturbing - outcome.

> Restricting the ability to be creative seems to be a new frontier of censorship.

I agree this is a new frontier, but it’s not censorship to withhold your own work. I also don’t really think this involves much creativity. I suppose coming up with prompts involves a modicum of creativity, but the real creator here is the model, it seems to me.

Post reply on HN