touch foxglove NOW 
https://github.com/rinongal/textual_inversion
So if I understand this right, textual_inversion creates prompts for a series of images such that you can use them as inputs for Stable Diffusion. We have a massive dataset of marseys, so maybe if you fed them in as an input, you could get a prompt that describes marsey as well as possible, allowing for unlimited marsey generation, rendering chiobu obsolete once and for all!
I would try myself but not only am I a Windows-cel, I'm also a GPU-let, using AMD in an NVIDIA user's world. Probably going to try either dual booting into ubuntu or something like that later, but that will take a while of finangling, so I thought I'd suggest it to one of the many nerds who probably already have done this
Jump in the discussion.
No email address required.
yeah I was looking into it but I don't have a GPU cause I'm not a gaymer lmao
you could try this too: Run Stable Diffusion on Intel CPUs
really pretty cool
https://textual-inversion.github.io/
Edit: oh ya
@HeyMoon I ran some interrogator thingy on 
@brzl's marsey commission and got this
Jump in the discussion.
No email address required.
i wonder how many years until TPUs are outdated or available for consumer machines
Jump in the discussion.
No email address required.
The only TPU I used were Google Colab ones and they honestly sucked butt everytime, somehow almost worse than cpu lmao
Are they good in general or kinda meh compared to current GPUs?
Jump in the discussion.
No email address required.
idk im not a machinelearningcel but the really expensive ones are probably faster than equivalent non focused stuff for those tasks?
Jump in the discussion.
No email address required.
More options
Context
More options
Context
I think some SBCs have TPUs already: https://brainjar.ai/blogs/coral-tpu-jetson-nano-performance
Jump in the discussion.
No email address required.
More options
Context
More options
Context
hmm that is interesting, I have never heard of an interrogator before, but it makes sense
Jump in the discussion.
No email address required.
More options
Context
More options
Context
Plagarized post 🥱😴
Jump in the discussion.
No email address required.
Okay frickhole what post did I plagiarize
Jump in the discussion.
No email address required.
https://rdrama.net/h/marsey/post/99051/-
Jump in the discussion.
No email address required.
YOU LITERAL R-SLUR THATS MY POST. FRICK YOU. GO TO HECK YOU LITTLE C*NT. FRICK
Jump in the discussion.
No email address required.
source? Deboonked
Jump in the discussion.
No email address required.
More options
Context
More options
Context
More options
Context
More options
Context
More options
Context
You can use Google Colab.
On a sidenote, is there a way to just DL all marseys? I have an ok gpu and was working on AI shit anyways so might as well give it a go.
Jump in the discussion.
No email address required.
Maybe grab the whole directory here lol: https://github.com/Aevann1/rDrama/tree/frost/files/i/emojis
https://rdrama.net/marsey_list.json
Or from the marsey archive: https://github.com/geese-suck/MarseyArchive
or marsey booru: https://booru.marsey.cat/index.php?q=post/list
Some random assets can be found in this repo too: https://github.com/MarseyLivesMatter/MarseyPride
Jump in the discussion.
No email address required.
Thanks
Jump in the discussion.
No email address required.
Anytime
It's quite impressive how much AI media synthesis blew up after dall-e and stable diffusion, the style transfers from almost a year ago probably pales in comparison with what you can get today lol
Jump in the discussion.
No email address required.
More options
Context
More options
Context
More options
Context
Well that costs money if you want to do SD, and I want to do bulk shit
Also, the rdrama github repo has all of them i think, in assets or something. So if you do a git clone it should get all of them for you
Jump in the discussion.
No email address required.
i'm using this notebook and it's working on my poorcel free plan and currently generating a vidya: https://colab.research.google.com/github/deforum/stable-diffusion/blob/main/Deforum_Stable_Diffusion.ipynb
i think you need to download the checkpoints file from huggingface first
Jump in the discussion.
No email address required.
oh shit, didn't realize that
Jump in the discussion.
No email address required.
apparently it's some group effort for the "ultimate SD notebook" but there's only a groomercord link and i ain't touching that lol
exhaustive list here: https://pharmapsychotic.com/tools.html
Jump in the discussion.
No email address required.
More options
Context
More options
Context
More options
Context
The free version of Colab is okay, but I reckon it's because I'm not in burgerland where it's hard to not get a trash gpu in the rare event you're let out of the GPU jail.
Jump in the discussion.
No email address required.
More options
Context
More options
Context
More options
Context
Can you run stable diffusion on a Jetson Nano? I did a lazy search and didn't find anything, but A) it was lazy, and b) brave search sucks
Jump in the discussion.
No email address required.
well i think you'll get better results if you have more VRAM
Jump in the discussion.
No email address required.
A Jetson Micro then?
Jump in the discussion.
No email address required.
Jump in the discussion.
No email address required.
More options
Context
More options
Context
More options
Context
More options
Context
Snapshots:
archive.org
archive.ph (click to archive)
ghostarchive.org (click to archive)
Jump in the discussion.
No email address required.
More options
Context
look into dreambooth, will probably be better.
Jump in the discussion.
No email address required.
More options
Context