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

Imagen: An AI system that creates photorealistic images from input text

imagen.research.google

Post reply on HN
Print view View original

191–200 of 233 posts

Re: Imagen: An AI system that creates photorealistic images from input text

#191

Post by mmastrac »

acoard wrote: post #183
prophesi wrote: post #136

Earlier quoted context omitted.

There's also a fork that requires a lot less VRAM. I was able to get this working with an Nvidia GTX 1070. https://github.com/basujindal/stable-diffusion You'd clone the fork, then download Stability AI's checkpoint, sd-v1-4.ckpt, from https://huggingface.co/CompVis/stable-diffusion-v-1-4-origin... Follow the instructions in the forked repo, and you should be good to go in a manner of minutes.

The only issue I had was WSL 2 was not using my GPU, so obviously it failed. Couldn't get it working on Windows either, failed at installing dependencies. I'm thinking of dual-booting Linux just to try out stable-diffusion. I normally dev on Linux but don't do GPU work, only my Windows gaming PC has the horsepower to run stable-diffusion and unfortunately I couldn't get it working on Windows. Shame cause I'd love to…

Try out a Ubuntu live image. You can probably get set up with everything without even having to touch your HDD! I just don't know how the native NVidia drivers work in that case, but I think you can get them installed and restart the window manager, even w/a a liveCD.

Re: Imagen: An AI system that creates photorealistic images from input text

#192

Post by TaupeRanger »

canoebuilder wrote: post #184
napolux wrote: post #156

Is anyone aware of people doing the same for NSFW images? They can easily wipe out an entire industry. No models to pay and to check for legal ages, infinite possibilities: just write the pic you want, the massive body part you want, how many genitals are involved and boom. You have your image.

Quoted post unavailable.

Andrew Huberman - How to Cherry Pick Neuroscience "Studies" to Pretend Something is True So You Can Make Lots of Money as a Health Guru Personality

Re: Imagen: An AI system that creates photorealistic images from input text

#194

Post by canoebuilder »

TaupeRanger wrote: post #192
canoebuilder wrote: post #184

Earlier quoted context omitted.

Quoted post unavailable.

Andrew Huberman - How to Cherry Pick Neuroscience "Studies" to Pretend Something is True So You Can Make Lots of Money as a Health Guru Personality

I’ve listened to a number of his podcasts, I’ve never gotten that impression at all. He comes across as a well versed, legit scientist. And there is lots of other evidence to back that up, not just my impression from a few podcasts, publications, tenured professorship at Stanford, etc.

But in this case, does it really need extensive scientific study? Just think about it and look around.

The thing our entire biological systems are largely oriented around, reproduction, and human connection/contact.

And then we have this super stimuli version of that always on tap at a moments notice, but it is a trap, a mirage.

It might be best to minimize exposure to that since in the end it doesn’t/cannot produce the same results.

I’ve not even listened to that link yet, I just caught glimpse of it the other day. I think it’s just starting to seem obvious to more and more people. The evidence seems to accrue daily as to the social detriment it causes.

Are there any specific examples of cherry picking you have?

Re: Imagen: An AI system that creates photorealistic images from input text

#195

Post by izacus »

gallabytes wrote: post #142
motoboi wrote: post #140

Earlier quoted context omitted.

in the case of imagen, I suppose the cost is at least two orders of magnitude over 500k.

... no it definitely wasn't. that's $50m. read the paper, they tell you how long it took on a v4-256, which you know the public rental price for.

And where did you think the tagged dataset and software came from?

Re: Imagen: An AI system that creates photorealistic images from input text

#196

Post by Imnimo »

Roark66 wrote: post #74

Every single time I see an article about a new AI model that has a section called "societal impact" I know immediately they are not releasing the model, the training set, nothing... It seems to be the kind of bullshit statement that those companies put in place of "we paid $500k training this model and we're not giving it for free to anyone".

>Every single time I see an article about a new AI model that has a section called "societal impact" I know immediately they are not releasing the model, the training set, nothing...

This section is just a requirement for some of the big ML conferences, like NeurIPS.

Re: Imagen: An AI system that creates photorealistic images from input text

#197

Post by 29athrowaway »

Roark66 wrote: post #74

Every single time I see an article about a new AI model that has a section called "societal impact" I know immediately they are not releasing the model, the training set, nothing... It seems to be the kind of bullshit statement that those companies put in place of "we paid $500k training this model and we're not giving it for free to anyone".

They will still use it and make a lot of money from it, I guarantee it.

Google is in the business of ads, this might have useful applications in the ad space.

Re: Imagen: An AI system that creates photorealistic images from input text

#198

Post by Terretta »

glenneroo wrote: post #81
andresgottlieb wrote: post #38

Earlier quoted context omitted.

Saul Goodman if he was a character in Twin Peaks: https://media.discordapp.net/attachments/999426920376717513/... Generated with Midjourney Beta

Which is now Stable Diffusion under the hood, sprinkled with a little prompt parsing "magic".

This may be misleading.

As far as I could tell (using it before, during, and after this Beta option was available) it was the upscalar using that, not the original 4 image generation.

Re: Imagen: An AI system that creates photorealistic images from input text

#199

Post by ceeplusplus »

izacus wrote: post #195
gallabytes wrote: post #142

Earlier quoted context omitted.

... no it definitely wasn't. that's $50m. read the paper, they tell you how long it took on a v4-256, which you know the public rental price for.

And where did you think the tagged dataset and software came from?

Marginal cost of using that is basically $0. The internal dataset is a sunk cost that's already been paid for (presumably for their other, revenue generating products like Google Images). Half of their dataset is a publicly available one.

Re: Imagen: An AI system that creates photorealistic images from input text

#200

Post by ceeplusplus »

jquery wrote: post #189
ImprobableTruth wrote: post #150

Earlier quoted context omitted.

>the major strides they’re making at removing racial/gender biases They're literally just appending a race/gender string at the end [1]. In what world is that not just hot air? [1] https://twitter.com/jd_pressman/status/1549523790060605440

That’s a pretty uncharitable interpretation of my post. You shared an example of a single mitigation that you personally find ludicrous (without explaining why). And then I’m supposed to throw up my hands and go “I guess it’s pointless to try and be less racist”? Bias amplification is a real issue. https://www.theverge.com/2016/3/24/11297050/tay-microsoft-ch... Tay might still be around if Microsoft gave a thought to…

> a single mitigation

That is the only mitigation used in DALL-E 2, which up until recently was the only publicly available text to image model.

> I’d prefer not to have this awesome technology tainted out of the gate as a tool for racists and pornographers

Why is it your business what people do with the model? If people want to be racist they can already do so, they don't need a shitty model that doesn't work half as well as paying some guy in the third world $2/h to shitpost online. And I don't see the problem with pornography.

Post reply on HN