Katherine Crowson

Oh it mostly seems to happen at higher guidance scales than I typically use... that's why I hadn't been seeing it.

> Interesting! What does "still stopping after S steps." means? I think it means skipping the last step, you can do it better by `sigmas = torch.cat([sigmas[:-2], sigmas[-1:]])` so you...

> for what it's worth: I settled on these params for 5-step DPM-Solver++ sampling via Karras… If you want to do one more function evaluation have you tried doing a...

You have to paste the 2S step code into the 2M sampler because you need to save its `denoised` to init `old_denoised` in the 2M sampler... 2M does an Euler...

It's this branch of the conditional: https://github.com/crowsonkb/k-diffusion/blob/60e5042ca0da89c14d1dd59d73883280f8fce991/k_diffusion/sampling.py#L487. It's a first-order DPM-Solver++ step, which as per the DPM-Solver++ paper is equivalent to an Euler (DDIM) step. It's done for the first...

> hmm like this? That's what I meant to do, yes :)

@mcmonkey4eva I think I could include a modified get_sigmas_karras() that it avoided the second to last sigma... maybe generating a ramp that was one step longer then manually chopping off...

I would need to heavily filter the dataset to exclude images that are smaller than 512px on the short edge, so probably not. However I am thinking about trying for...

Ohh. I have been experimenting with scaling up then re-noising the image and doing forward sampling starting from there (i.e. using it as an init image) and that has been...

No I just wanted to clean it up first before releasing it and then never got around to it... ^^;;