A Web UI for Stable Diffusion

Post by cypress66 » Sat, Sep 10, 2022, 9:34 PM UTC

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…

Post by adammarples » Sun, Sep 11, 2022, 12:18 PM UTC

cthalupa wrote: post #129

adammarples wrote: post #125

Earlier quoted context omitted.

Can I run (train?) this textual inversion using the same consumer GPUs that work with stable-diffusion? Or does it require a much beefier machine

You can, though you might run into memory limitations running it on a GPU. There can be tuning done to lower the VRAM utilization, but I have been lucky enough to not need this - I do some CG work and ran into VRAM limitations there, so I'm on a 3090 with 24GB. You can always run it on a CPU and utilize your RAM instead if needed, though the training might extend to 24+ hours that way. Edit: Here's an example of some…

Post by needle0 » Mon, Sep 12, 2022, 1:09 AM UTC

fragmede wrote: post #142

mach1ne wrote: post #122

Earlier quoted context omitted.

Indeed, Stable Diffusion does not currently run on AMD graphics cards.

It does, on Linux, Windows, and MacOS.

Post by underlines » Mon, Sep 12, 2022, 5:32 PM UTC