Is there any way to download this on my PC and run it offline? Something like a command-line tool like $ ./something "cow flying in space" > cow-in-space.png that runs with local-only data (i.e. no internet access, no DRM, no weird API keys, etc like pretty much every AI-related application i've seen recently) would be neat.
Yes, that's actually the biggest reason this is such a cool announcement! You just need to download the model checkpoints from HuggingFace[0] and follow the instructions on their Github repo[1] and and you should be good to go. You basically just need to clone the repo, set up a conda environment, and make the weights available to the scripts they provide. [0] https://huggingface.co/CompVis/stable-diffusion [1] https…
Stable Diffusion Public Release
311–320 of 437 posts
Re: Stable Diffusion Public Release
#312Is there any way to download this on my PC and run it offline? Something like a command-line tool like $ ./something "cow flying in space" > cow-in-space.png that runs with local-only data (i.e. no internet access, no DRM, no weird API keys, etc like pretty much every AI-related application i've seen recently) would be neat.
Yes, clone the repo ( https://github.com/CompVis/stable-diffusion ), download the weights and follow the readme for setting up a conda environment. I am presently doing so on my RTX 3080.
Re: Stable Diffusion Public Release
#313Earlier quoted context omitted.
This feels so wrong this AI thing, strangely enough Im not that stressed. Look at the recursive side of it its hilarious. Im an artist. AI is around. Do I want to put my work online? No. So no artists put stuff online anymore? So how does future of art work exactly? Will send booklets by mail again? There is the democratic side of it. We the people ultimately decides. Those pictures are generated by using artists wor…
Yeah going offline begins to look tempting except for the part that huge amounts of how you get people to want to pay for your work is by sharing it publicly. Except then someone can come along and scrape it all and dump it into their AI training black box without giving two shits about copyright.
Im not stressed. We can and will manage this.
Re: Stable Diffusion Public Release
#314Earlier quoted context omitted.
Yes, clone the repo ( https://github.com/CompVis/stable-diffusion ), download the weights and follow the readme for setting up a conda environment. I am presently doing so on my RTX 3080.
Can you please tell me where is the model.ckpt? I am not able to find any weight with ".ckpt" format there in the both links that you have given. There are the ".bin" file on the hugging face.
Here's the direct link.
Re: Stable Diffusion Public Release
#315DALL-E 2 just got smoked. Anyone with a graphics card isn't going to pay to generate images, or have their prompts blocked because of the overly aggressive anti-abuse filter, or have to put up with the DALL-E 2 "signature" in the corner. It makes me wonder how OpenAI is going to work around this because this makes DALL-E 2 a very uncompetitive proposition. Except, of course, for people without graphics cards, but it'…
DALL-E's filters are so harsh that I find myself often in the situation where I don't even understand how what I prompted could possibly be in violation. It's a novel feeling, but utterly stifling when it comes to actual creativity, and I'm not even trying to push any NSFW boundaries, just explore the artspace. Once I can run unfiltered on my own GPU, DALL-E will never get used by me again.
Problem was that her cat is a Maine Coon cat and DALL-E doesn't like the word "coon".
When I finally got an image of a Maine long haired cat on a horse when I tried to expand the image it was giving me another error.
I think the cat was sitting on the backside of the horses back, and I guess it thought it was too close to a doggy style position...
Re: Stable Diffusion Public Release
#316So how do I set up a server to generate images for me? An API I can post anything to and get an image back.
Re: Stable Diffusion Public Release
#317Is there any way to download this on my PC and run it offline? Something like a command-line tool like $ ./something "cow flying in space" > cow-in-space.png that runs with local-only data (i.e. no internet access, no DRM, no weird API keys, etc like pretty much every AI-related application i've seen recently) would be neat.
cog predict r8.im/stability-ai/stable-diffusion -i prompt="cow flying in space"
Or you can run the Docker image directly. More details under "run on your own computer" here: https://replicate.com/stability-ai/stable-diffusionRe: Stable Diffusion Public Release
#318Re: Stable Diffusion Public Release
#319Re: Stable Diffusion Public Release
#320Earlier quoted context omitted.
> The most interesting part, to me, of a release like this is the amount of "please don't abuse this technology" pleading. > Why bother asking people not to? I guess if it helps you sleep at night that you tried, I guess? I've perceived this as them doing the necessary amount of virtue-signaling and ass-covering to avoid the ire of groups that are loud/powerful enough to cause issues for them in the short-term. I've…
I never saw it create anything more NSFW than female boobs. It won't generate penises or genitals besides mounds of hair. Right now the "NSFW" flag/filter is 99%+ false positives. This is stuff that used to be allowed in G-rated movies in the US. True to both Stable Diffusion and Dalle2, the more encompassing the content of your image is, the more incorrect the detail is. Both generally will make fantastic faces but…