Anton Obukhov

Thanks for this analysis, a couple of things to double check: - Can you please match the inputs sizes against the charts from https://github.com/toshas/torch-householder readme plots? This will give you...

Can you please run https://github.com/toshas/torch-householder/blob/master/tests/benchmark_one.py with the values of width (r), height (d), and batchsize (b) of interest?

I applied the patch and not sure what the modified benchmark is supposed to verify. The way it was implemented, it timed pure calls to the functions. After patching there...

Thanks for the pointer @w-e-w , however, are the following code bits not used within this repo? https://github.com/AUTOMATIC1111/stable-diffusion-webui/blob/master/modules/sd_models.py#L372 https://github.com/AUTOMATIC1111/stable-diffusion-webui/blob/master/modules/sd_models.py#L413-L453

Hi, thanks for your interest in the toolkit. I'm confused why PPL is inaccessible in 0.3.0; I can see it inside the wheel: https://files.pythonhosted.org/packages/dd/72/687a54bab9a11e351cff3859ece48fb58e13786a493eb13a5da32b42de32/torch_fidelity-0.3.0.tar.gz under `torch_fidelity/metric_ppl.py`. I just had a...

We are brewing a pull request to integrate our new Marigold-LCM model and possibly a pipeline. Additional modalities (normals) are also in the making.

A few questions regarding planning the pipelines growth and lifecycle. ### 1 The new Marigold-LCM pipeline will use the same code as the original but with a different set of...

Hi @sayakpaul, @yiyixuxu , I made a round of changes to address your comments. Thanks to your input, the pipelines look more like the other official pipelines. Please have a...

@coccofresco Thank you! If the data and time permit, could you please showcase some of the results on Twitter and refer our original announcement post? https://twitter.com/AntonObukhov1/status/1732946419663667464?t=8iIVVDbbrhwGHQgHNOoj2A&s=19

Stay tuned ;)