It seems to be able to run on consumer GPUs. So maybe I can invest into a GPU and integrate LN invoices there without breaking any ToS?

Stable Diffusion runs on under 10 GB of VRAM on consumer GPUs, generating images at 512x512 pixels in a few seconds. This will allow both researchers and soon the public to run this under a range of conditions, democratizing image generation. We look forward to the open ecosystem that will emerge around this and further models to truly explore the boundaries of latent space.

https://stability.ai/blog/stable-diffusion-announcement

Daily discussion thread

saloon

I'll look into StableDiffusion.
It seems to be able to run on consumer GPUs. So maybe I can invest into a GPU and integrate LN invoices there without breaking any ToS?

> Stable Diffusion runs on under 10 GB of VRAM on consumer GPUs, generating images at 512x512 pixels in a few seconds. This will allow both researchers and soon the public to run this under a range of conditions, democratizing image generation. We look forward to the open ecosystem that will emerge around this and further models to truly explore the boundaries of latent space.

-- https://stability.ai/blog/stable-diffusion-announcement