f-rank

> I'm sure it was already addressed. Xformers change the output, it's how it works apparently xformers turns euler_a non-deterministic ?

> Create a grid against Steps (18, 19, 20, 21, 22) and CFG (6.4, 6.7, 7, 7.3, 7.7) – to better understand, are the cars supposed to behave like that...

> Euler_a will produce different images regularly. Most of the ancestral samplers are like this but Euler_a is very prone to it. It produces the same image when not using...

> Some hours ago it was working fine. Now I get: > > RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu...

Would also be valuable to have hires fix available in img2img too, for much finer control with the Deforum plugin for Aautomatic1111 at higher resolution renders.

> you can fix this locally by `git config --add remote.origin.fetch '^refs/heads/Prevent-people-from-saying-*'` this will blacklist `git fetch` and thus `git pull` from touching that one branch in particular with the...

> If you get this error your git install is quite out of date and should be updated. Negative refspec support was added in git 2.29 over 2 years ago....

> > I'm on 2.32.0.windows.1 > > Hmm... that should be fine then. Though rereading your error message it appears you have made a typo and left out the ^...

I notice that with Euler and DDIM (512x512) it is able to reproduce the same image over and over. Diff from the one created with same info while not using...

Same thing happening here. I select pre-processor ClipVision and Model t2iadapter_style_sd14v1 and it spews " Recognizing Control Model failed:" in console.