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

11–20 of 148 posts

Re: A Web UI for Stable Diffusion

#11

Post by drexlspivey »

smrtinsert wrote: post #7

I have a 6gb 1660ti, barely holding on. Is a new 12gb card good enough for now, or should I go even higher to be safe for a few years of sd innovation?

How is M1/M2 support for SD? Is there a significant performance drop? Presumably you would be able to buy a 32GB M2 and be future proof because of the shared memory between CPU/GPU.

Re: A Web UI for Stable Diffusion

#12

Post by filiphorvat »

wyldfire wrote: post #9
smrtinsert wrote: post #7

I have a 6gb 1660ti, barely holding on. Is a new 12gb card good enough for now, or should I go even higher to be safe for a few years of sd innovation?

It sounds like there's forks that are able to work with But yeah the next generation of models would probably capitalize on more memory somehow.

People have reported that this repo even works with 2gb cards if you run it with --lowvram and --opt-split-attention.

Re: A Web UI for Stable Diffusion

#13

Post by hwers »

People recently figured out how to export stable diffusion to onnx so it’ll be exciting to see some actual web UIs for it soon (via quantized models and tfjs/onnxruntime for web)

Re: A Web UI for Stable Diffusion

#14

Post by CitrusFruits »

smrtinsert wrote: post #7

I have a 6gb 1660ti, barely holding on. Is a new 12gb card good enough for now, or should I go even higher to be safe for a few years of sd innovation?

I'm using it with a 2070 (4 year old card with 8gb vram) and it takes about 5 seconds for a 512x512 image. It's been plenty fast to have some fun, but I think I'd want faster if it was part of a professional work flow.

Re: A Web UI for Stable Diffusion

#16

Post by jjcon »

drexlspivey wrote: post #11
smrtinsert wrote: post #7

I have a 6gb 1660ti, barely holding on. Is a new 12gb card good enough for now, or should I go even higher to be safe for a few years of sd innovation?

How is M1/M2 support for SD? Is there a significant performance drop? Presumably you would be able to buy a 32GB M2 and be future proof because of the shared memory between CPU/GPU.

In my setup at least it runs essentially in CPU mode since there is no CUDA acceleration available and metal support is really messy right now. So while quite slow I don't run into memory issues at least. It runs much faster on my desktop GPU but that has more constraints (until I upgrade my personal 1080 to a 3090 one of these days).

Re: A Web UI for Stable Diffusion

#17

Post by jrm4 »

So, and this is an ELI5 kind of question I suppose. There must be something going on like "processing a kazillion images" and I'm trying to wrap my head around how (or what part of) that work is "offloaded" to your home computer/graphics card? I just can't seem to make sense of how you can do it at home if you're not somehow in direct contact with "all the data?" e.g. must you be connected to the internet, or "stable-diffusions servers" for this to work?

Re: A Web UI for Stable Diffusion

#18

Post by codefined »

jrm4 wrote: post #17

So, and this is an ELI5 kind of question I suppose. There must be something going on like "processing a kazillion images" and I'm trying to wrap my head around how (or what part of) that work is "offloaded" to your home computer/graphics card? I just can't seem to make sense of how you can do it at home if you're not somehow in direct contact with "all the data?" e.g. must you be connected to the internet, or "stable…

All those 'kazillion' images are processed into a single 'model'. Similar to how our brain cannot remember 100% of all our experiences, this model will not store precise copies of all images it is trained off of. However, it will understand concepts, such as what a unicorn looks like.

For StableDiffusion, the current model is ~4GB, which is downloaded the first time you run the model. These 4GB encode all the information that the model requires to derive your images.

Re: A Web UI for Stable Diffusion

#19

Post by ducktective »

jrm4 wrote: post #17

So, and this is an ELI5 kind of question I suppose. There must be something going on like "processing a kazillion images" and I'm trying to wrap my head around how (or what part of) that work is "offloaded" to your home computer/graphics card? I just can't seem to make sense of how you can do it at home if you're not somehow in direct contact with "all the data?" e.g. must you be connected to the internet, or "stable…

As someone with ~0 knowledge in this field, I think this has to do with a concept called "transfer learning" in which you once train with that kazillion of images, then use that same "coefficients" for further run of the NN.
Post reply on HN