Kevin Turner

See Katherine's note on https://github.com/huggingface/diffusers/issues/277#issuecomment-1279452625 > k-diffusion's Euler and Euler Ancestral samplers are just the VE versions of DDIM and the original DDPM sampling method though, they should actually produce...

Not completely. My primary familiarity with asynchronous APIs in Python is through [Twisted](https://twisted.org/), and I get the feeling that is not a common API among your target audience in this...

You are correct that we've muddied the discussion here with several different concepts with their own concerns. The original request was for cancellation support: the ability to interrupt work on...

I'm afraid that the full explanation of the current behavior is even worse than this: > Image 1: Seed 42 > Image 2: Seed <unknowable chaos seed> > Image 3:...

What do you do about it? You could, as exo-pla-net suggested, have a generator for each entry in the batch. But currently, schedulers are blissfully unaware of the batch width,...

My favorite idea for this so far is to use a coordinate-based noise system. A [`torch.Generator`](https://pytorch.org/docs/stable/generated/torch.Generator.html#torch.Generator) is a one-dimensional function, and it has internal state that advances its position every...

There's been a lot of discussion on this lately. See #551 if you haven't yet.

Superseded by #1905?

I've found that it's [very difficult to use a `torch.Generator`](https://github.com/huggingface/diffusers/issues/612#issuecomment-1261330855) for such an application, and suggest using coordinate-based procedural noise.

Working on this at #PyCascades sprints!