OpenAi really thought they had done something with DALL-E, then Google's all "hold my beer".
Imagen, a text-to-image diffusion model
21–30 of 661 posts
Re: Imagen, a text-to-image diffusion model
#22>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…
Transformers are parallelize-able, right? What’s stopping a large group of people from pooling their compute power together and working towards something like this? IIRC there were some crypto projects a while back that we’re trying to create something similar (golem?)
Re: Imagen, a text-to-image diffusion model
#23>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.
Re: Imagen, a text-to-image diffusion model
#24>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…
The big labs have become very sensitive with large model releases. It's too easy to make them generate bad PR, to the point of not releasing almost any of them. Flamingo was also a pretty great vison-language model that wasn't released, not even in a demo. PaLM is supposedly better than GPT-3 but closed off. It will probably take a year for open source models to appear.
Re: Imagen, a text-to-image diffusion model
#25I give it a few years before Google makes stock images irrelevant.
Rolling this into Google Docs seems like a nobrainer.
Re: Imagen, a text-to-image diffusion model
#26This looks incredible but I do notice that all the images are of a similar theme. Specifically there are no human figures.
Re: Imagen, a text-to-image diffusion model
#27Would 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!
Re: Imagen, a text-to-image diffusion model
#28Is there a way to try this out? DALL-E2 also had amazing demos but the limitations became apparent once real people had a chance to run their own queries.
Re: Imagen, a text-to-image diffusion model
#29>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…
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.
It seems you've got it backwards: "tendency for images portraying different professions to align with Western gender stereotypes" means that they are calling out their own work precisely because it is skewed in the direction of Western American biases.
Re: Imagen, a text-to-image diffusion model
#30>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 was hoping your conclusion wasn't going to be this as I was reading that quote. But, sadly, this is HN.