Playing with Llama 7B and 13B, I found that the 13B model was capable of doing a simple task, rewriting titles in sentence case for Tildes submissions. The 7B model doesn't appear capable of the same task, out of the box.

I heard about Android's new AICore available on a couple of new devices. But it sounds like Gemini Nano, which runs on-device, can only handle 2B or 3B parameters.

Is this size of model useful for real tasks? Does it only become useful after training on a specific domain? I'm a novice and wanting to learn a little bit about it. On-device AI is an appealing concept to me.

Howdy Tildes wizards.

I decided to have a looksy at Stable Diffusion on my local computer (Manjaro, AMD 7500x CPU, 32GB) using Easy Diffusion. I've gotten my head around the basics and grabbed MidJourney V4 LLM, and now I'm learning how to prompt.

So far I've generated some cool cyberpunk cyborg things, landscapes, etc. One of the things I wanted to use Stable Diffusion for is generating silhouettes. Sounds weird, I know, but they're great to use with decal and vinyl printing for my wife's business.

Any ideas on ways to do silhouette generation?

Next is, what's good to read to learn about model types and what all of the settings really do?

I'm ordering a GPU (3060) to improve the horrendous render times, so don't worry about the under powered rig, I'm still in toy mode.