AI Art: It is criminal to not post your prompt

The Something Awful Forums > Main > General Bullshit > AI Art: It is criminal to not post your prompt

dumb.: Apr 11, 2014; -=💀=-

XYZAB posted:

I posed this question in the D&D AI thread thinking it would be more appropriate there, but it doesn't seem to be getting any traction so I'll ask here instead:

Can anyone here recommend to me an �audio file to text� AI transcription github project that I can install locally to chew over a bunch of .wav files I�ve got kicking around, that doesn�t require me to upload those files to a third party service for processing? Think hundreds of hours of noisy lecture audio in raw 24 bit 48khz *.wav format that I can let an RTX card chug away at, that also isn�t the newest version of Microsoft Word. That�s what I�m looking for. Does such a thing exist?

I've had decent luck with this windows build of Whisper:

https://github.com/Purfview/whisper-standalone-win/

It whipped through a bunch of hour+ long audio files on my 4080, and the results were pretty accurate. Be sure to get the cuBLAS/cuDNN libraries.

# ¿ Feb 3, 2024 15:21

Adbot: ADBOT LOVES YOU

# ¿ May 14, 2024 06:10

dumb.: Apr 11, 2014; -=💀=-

# ¿ Feb 11, 2024 16:59

dumb.: Apr 11, 2014; -=💀=-

snorch posted:

I'd watch any one of those.

Also PaleFigure and swagman what are y'all using to get those images? They seem unusually crisp and coherent, or is it just the Art of the Prompt at work? I get decent results with SDXL but I'd say it only ever reaches about 80% of that fidelity.

I've found lowering the CFG scale helps.

# ¿ Mar 19, 2024 19:03

dumb.: Apr 11, 2014; -=💀=-

namlosh posted:

Sorry if this is the wrong thread, but what are some of the best models that can be run locally?
I�ve got it stable diffusion running locally from this git repo:
https://github.com/CompVis/stable-diffusion.git
And it�s generating images but they aren�t that great. I�m not trying to generate stuff as good as whats in this thread, but I am trying to generate the best I can locally for free. I want to see what the limit is for offline generation. I have a beefy machine with a 4090 if that matters.
I�m using the �default� stable-diffusion-v1/model.ckpt file that�s around 7.5gb. Should I be grabbing a different one from somewhere.

Sorry if this is all obvious or the wrong place to ask. Just point me in a direction and I�ll head that way.

I'm not familiar with that SD ui, but it looks pretty old... can it only do SDv1? If so, you might want to check out a more modern interface that can run SDXL models like Fooocus, AUTOMATIC1111 or ComfyUI.

As for XL models, I'm a fan of RealVisXL, Juggernaut XL, Colossus Project and ZavyChromaXL.

I don't use 1.5 very often anymore, but some 1.5 models I dig are Analog Madness, Photon, Realistic Stock Photo and Epic Photogasm.

# ¿ Mar 25, 2024 17:25

The Something Awful Forums > Main > General Bullshit > AI Art: It is criminal to not post your prompt