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

A Web UI for Stable Diffusion

github.com

Post reply on HN
Print view View original

131–140 of 148 posts

Re: A Web UI for Stable Diffusion

#131

Post by jrm4 »

visarga wrote: post #76
MattRix wrote: post #71

Earlier quoted context omitted.

This is exactly it. It’s pretty remarkable that it was trained on over 100 terabytes of images and yet the model has been distilled down to only 4gb.

Then maybe we should remind about this 25,000:1 ratio when an artist complains about his copyrights being abused. The model doesn't have space to actually copy his works inside, it can only memorise the equivalent of a thumbnail from each input. A very small thumbnail, scaled down 150:1 per width and height (square root of 25000). That's like a grain of rice on the screen.

Ah, I can step in here.

Fair use might work but maybe not? If I were to argue against it, I'd probably compare something like a recording of music vs. a MIDI file. Same raw data scaling.

Re: A Web UI for Stable Diffusion

#132

Post by cloudking »

DougBTX wrote: post #127
cthalupa wrote: post #115

Earlier quoted context omitted.

Thaler specifically asks for himself to be given the copyright assignment in the filing, claiming that the AI is essentially creating it in a work-for-hire. He does not ask for the Creativity Machine to be assigned the copyright. >In that case, a human is providing a prompt to the model (providing creative input), and asking if they themselves count as the author (a human rather than a neural net), so it seems like a…

Thanks for the link, interesting reading. I can totally appreciate the angle that some generations may be too trivial to be worthy of protection. I happen to be in the UK, and this happens to match my expectations, but it does strongly imply more regional variation than I’d have guessed: > The situation may be different in the UK, where copyright law allows copyright on a computer-generated work, the author of which…

Interesting, so if I run SD on a server in the UK, would the images technically be generated in the UK?

Re: A Web UI for Stable Diffusion

#133

Post by fibonacc »

fragmede wrote: post #82
fibonacc wrote: post #43

a sigh of relief as I thought that this would generate instead of pictures, React UI code based on plain text description. First they came for illustrators, then they came for UI designers.

You've seen https://twitter.com/sharifshameem/status/1282676454690451457 yeah?

yes what I mean was mixing stable diffusion into the UI styling without the fine atomic details. Like say I want a dashboard with color themes from cyberpunk complete with graphics/art/logo. It would be a "good enough" category if something can literally be told to produce a complete frontend.

Re: A Web UI for Stable Diffusion

#134

Post by namarie »

DrSiemer wrote: post #126
holoduke wrote: post #118

Earlier quoted context omitted.

It's the same as someone trying to mimic a style. Nothing wrong with that. Certainly not something you could get copyrights from.

It is not the same as trying to mimic a style. It is cloning the essence of a style and making it readily available to anyone who asks for it. Sure, it's not copyright infringement, but you could argue that this takes away from the hardship the original artist had to go through to perfect their style.

> Sure, it's not copyright infringement

Which was precisely what the discussion was about.

> But you could argue that this takes away from the hardship the original artist had to go through to perfect their style

You could argue the same things about photoshop, a lot of other digital tools, drum machines, the photograph and the phonograph.

Re: A Web UI for Stable Diffusion

#135

Post by kcartlidge »

geuis wrote: post #60
offsky wrote: post #54

I’m waiting for someone to wrap this up into a desktop app that I can install and run on my Mac.

I've been looking into this for the last 2 days. Unless you're running an M1 Mac or newer, you're SOL. Stable Diffusion is built on PyTorch. PyTorch mainly has been designed to work with Nvidia cards. However PyTorch added support for something called RocM like a year ago that adds compatibility with newer AMD cards. Unfortunately RocM doesn't support slightly older AMD cards in conjunction with intel processors. So…

> I've been looking into this for the last 2 days. Unless you're running an M1 Mac or newer, you're SOL.

And not just any old M1 Mac. Last week I got it running on my 2021 8GB M1 MacBook Air and it's slow. Images at 512x512 with 10 steps take between 7 and 10 minutes to generate.

It's the only thing I do that hits performance limitations on the 8GB machine so there's no regrets on that score, but with the way this stuff is progressing 16GB+ is a realistic minimum for comfortable use.

Re: A Web UI for Stable Diffusion

#136

Post by rkeene2 »

peoplefromibiza wrote: post #117
skipnup wrote: post #91

Earlier quoted context omitted.

Is it any different than Photoshop content aware fill? Or using a camera? Nobody would ever think about Adobe or Nikon having copyright claims over your pictures. For me it's just a tool, the artistic part is providing a good description/base image, refining and choosing the best output. Anyway, I'm not a lawyer and we probably live in different countries, so it'll be interesting to wait for the first lawsuit.

> Nobody would ever think about Adobe or Nikon having copyright claims over your pictures But it is illegal to share pictures of Eiffel Tower, for example. People do it, but they shouldn't. If I put a picture of Eiffel Tower at night in a book or any other kind of commercial product, I have to pay to use it. Doesn't matter that it's there for my eyes to see it. The question is: are the images generated by an hyper ac…

What if Stable Diffusion generates those images ? :-)

Re: A Web UI for Stable Diffusion

#137

Post by moozilla »

kcartlidge wrote: post #135
geuis wrote: post #60

Earlier quoted context omitted.

I've been looking into this for the last 2 days. Unless you're running an M1 Mac or newer, you're SOL. Stable Diffusion is built on PyTorch. PyTorch mainly has been designed to work with Nvidia cards. However PyTorch added support for something called RocM like a year ago that adds compatibility with newer AMD cards. Unfortunately RocM doesn't support slightly older AMD cards in conjunction with intel processors. So…

> I've been looking into this for the last 2 days. Unless you're running an M1 Mac or newer, you're SOL. And not just any old M1 Mac. Last week I got it running on my 2021 8GB M1 MacBook Air and it's slow. Images at 512x512 with 10 steps take between 7 and 10 minutes to generate. It's the only thing I do that hits performance limitations on the 8GB machine so there's no regrets on that score, but with the way this st…

FWIW I'm on a 2021 16GB M1 MacBook Pro and it takes about 7min for me as well.

I've just been following the steps here with default settings: https://replicate.com/blog/run-stable-diffusion-on-m1-mac, but maybe there's a better way to run it at this point?

Re: A Web UI for Stable Diffusion

#138

Post by kcartlidge »

moozilla wrote: post #137
kcartlidge wrote: post #135

Earlier quoted context omitted.

> I've been looking into this for the last 2 days. Unless you're running an M1 Mac or newer, you're SOL. And not just any old M1 Mac. Last week I got it running on my 2021 8GB M1 MacBook Air and it's slow. Images at 512x512 with 10 steps take between 7 and 10 minutes to generate. It's the only thing I do that hits performance limitations on the 8GB machine so there's no regrets on that score, but with the way this st…

FWIW I'm on a 2021 16GB M1 MacBook Pro and it takes about 7min for me as well. I've just been following the steps here with default settings: https://replicate.com/blog/run-stable-diffusion-on-m1-mac , but maybe there's a better way to run it at this point?

That's what I initially followed, too. But there does seem to be a better way - I've just installed CHARL-E [0] (mentioned elsewhere in this thread) and it was trivial to set up. Literally download the dmg, drag into Applications, and run.

It's an electron app and you can either download it with the weights, or without and add them separately.

Using that it just took slightly over 5 minutes on my 8GB so it's a little bit quicker for me. Maybe the code has improved since I cloned stuff over a week ago, or maybe it's just different system resources when it is run. Either way, it looks like the easy way I've been waiting for.

[0] https://www.charl-e.com

Edit: It is however missing the CFG setting.

Re: A Web UI for Stable Diffusion

#139

Post by fragmede »

TekMol wrote: post #78
fragmede wrote: post #73

Earlier quoted context omitted.

Colab: https://colab.research.google.com/github/WASasquatch/StableD... To run it elsewhere in the cloud, grab a GPU (spot) instance and SSH in.

You mean a VM on a machine with a GPU? Or does it have to be a bare metal machine? What is a good provider of suitable VMs/machines? And what do you do after you SSHed in? The installation instructions seem to be for windows users (click here, then click there ...) is there a linux script that does the installation automatically?

Here's an install script if you need handholding :) https://github.com/JoshuaKimsey/Linux-StableDiffusion-Script...

Re: A Web UI for Stable Diffusion

#140

Post by kcartlidge »

fragmede wrote: post #81
offsky wrote: post #54

I’m waiting for someone to wrap this up into a desktop app that I can install and run on my Mac.

https://www.charl-e.com/ There are a few bugs to iron out before it's ready for prime time. For now, create the folder `~/Desktop/charl-e/samples/` manually before you run it.

Great stuff, and works on an 8GB M1 Air taking between 5 and 10 minutes for between 5 and 15 steps. As a suggestion, perhaps add the option for setting the CFG too (I know, it's open source etc, but it's just a suggestion).
Post reply on HN