Glenn 'devalias' Grant
Glenn 'devalias' Grant
> The formatting here is getting completely hosed, I'm not sure what is going on, sorry about that. @GeorgiaM-honestly Have you wrapped it in triple backticks to make it a...
Looking at the 'references timeline' on https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/3449 also pointed me to this PR by @jn-jairo that was merged ~9 days ago: - https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/4098 - https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/4142 @GeorgiaM-honestly I wonder if that's...
@jn-jairo With your PRs getting merged, is this issue resolved now? Or are there still more issues here still? - https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/4098 - https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/4142
A friend mentioned that using [xformers](https://github.com/facebookresearch/xformers) could make things non-deterministic, and that there were a lot of references to it on the repo issues here. Wanting to understand a bit...
There is an issue talking about integrating StableHorde into this UI: - https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/1449 - https://github.com/db0/AI-Horde/issues/60 As well as another that I just opened with regards to exploring integrations with Project...
I also noticed that one of the core things deepspeed supports is being able to distribute a workload across multiple GPUs (including remote GPUs). Here's a tutorial I found on...
Potentially Related: - https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/914 - https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/1734 - https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/3586 - https://github.com/AUTOMATIC1111/stable-diffusion-webui/discussions/1741 - https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/2002 - https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/2002#issuecomment-1296308600 - > Closing, opening new PR to squash commits and make it clean. - https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/3995 -...
> Some options: > > Add v2 to the hash like: 87d1ac53-v2 > Use more characters instead of 8: 87d1ac53ab > Use another param in info text: Model hash: 87d1ac53,...
Also, just as a 'prior art' reference, this (hashing the entire `*.ckpt` file + outputting the full hash as a `*.sha256`) appears to be what InvokeAI is currently doing: -...
> @dfaker: @raefu had a nice and consistently fast solution to this: hashing the zip directory section at the end of the file so it's a hash of the attributes...