There are already ways to get around this. For example, renting compute from people who aren't in datacenters. Which is already a thing: https://vast.ai. - Source: Hacker News / 5 months ago

By "SETI" I assume you mean the SETI@Home distributed computing project. There's a two-way market where you can rent out your GPU here: https://vast.ai/. - Source: Hacker News / 6 months ago

- https://vast.ai/ (linked by gchadwick above). - Source: Hacker News / 7 months ago

Have you considered running on a cloud machine instead? You can rent machines on https://vast.ai/ for under $1 an hour that should work for small/medium models (I've mostly been playing with stable diffusion so I don't know what you'd need for an LLM off hand). Good GPUs and Apple hardware is pricey. Get a bit of automation setup with some cloud storage (e.g backblaze B2) and you can have a machine ready to run... - Source: Hacker News / 7 months ago

I have heard vast.ai is cheap but I haven't tried it out. https://websiteinvesting.com/reviews/vast-ai-review/. Source: 7 months ago

The core of EchoAI involves two Google Sheets (or CSV files) that feed data into a Stable Diffusion API (Auto1111) or any online Stable Diffusion service with API support, like leonardo.ai. Here’s a glimpse of what the Sheet looks like: [ Google Sheet ]. The Python script combines elements from each column of the sheet (environment, ambiance, etc.) to generate unique scenes using the model of your choice, or even... Source: 7 months ago

I'm wondering if there is something similar to leonardo.ai live canvas for locally run setups. Assuming it would have to use sdturbo or the like. Hoping a 4090 could run something like that! Lol. Source: 7 months ago

I'm wondering the best way to make videos frame-by-frame that flow into each other using leonardo.ai. Source: 9 months ago