Check out Stable Diffusion and the llama model family. You can run those offline on your local hardware and wont have to worry about sharing private details with some cloud service that openly says they will look at your discussions and data and use it for training.

[–] Rai@lemmy.dbzer0.com 1 points 2 years ago (1 children)

That sounds awesome! What kinda hardware would we need for that? Our machines are a 9900k/3070ti and a 12600k/3070; I would assume they should suffice?

[–] voluntaryexilecat@lemmy.dbzer0.com 3 points 2 years ago (1 children)

Yes, that should work. Check out stable-diffusion-webui (automatic1111) and text-generation-webui (oobabooga). And grab the models from civitai (stable diffusion) and huggingface (llms like llama, vicuna, gpt-j, wizard, etc.).

[–] Rai@lemmy.dbzer0.com 2 points 2 years ago

I don’t know any of those words and I will look them up shortly! Hahaha thank you!

[–] NekoRogue 2 points 2 years ago (1 children)

I'm curious, how can you tell that it's AI? The hands do look a bit off in some of the panels but nothing else is standing out to me.

[–] ag_roberston_author 2 points 2 years ago

The fact that each panel is a different style and features and different character is a giveaway. Why would someone do that if they were drawing it themselves?