I love AI

170
Jump in the discussion.

No email address required.

Wtf you just straight up stole :marseymimic: my post

Jump in the discussion.

No email address required.

I stole this from elsewhere didn't see your post sorry nibba :marseyrain:

Jump in the discussion.

No email address required.

@A I am interested :marseyschizoexcited: any idea why the algorithm treated the same image :marseymissing2: so much differently?

Jump in the discussion.

No email address required.

You mean when you use the same prompts?

1. Different seed #, it's usually set to be random

2. The popular sampling methods like Euler A and PLMS are non-deterministic. They add random noise to the image.

If you run the exact same prompt on the same model, with the same number of sampling steps, at the same resolution, with the same seed, and a deterministic sampling method then I think you should get the same image.


https://i.rdrama.net/images/17092367509484937.webp https://i.rdrama.net/images/17093267613293715.webp https://i.rdrama.net/images/17151063782028813.webp

Jump in the discussion.

No email address required.

Na

Jump in the discussion.

No email address required.

Link copied to clipboard
Action successful!
Error, please refresh the page and try again.