Hacker News new | past | comments | ask | show | jobs | submit login

Folk are already using lower end cards with Stable Diffusion, even the 4GB models.

My 3080 is well capable of generating 512&768 images with a high step count in under a minute, and 500 odd steps (just for fun) in around 2 minutes (or even less with different samplers)

The interesting bit is when we get more VRAM (24-32GB) and can actually train the models with off the shelf hardware without breaking the bank.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: