Suhail

This still occurs for me.

If someone is interested in working on this, I will pay you a $10,000 prize for doing it. DM me on Twitter if so: https://twitter.com/suhail Performance (throughput, memory) should not...

+1 to a ws client

It would useful to compare this sampler to other samplers with the same prompt/seed/etc with images to see the difference it might have on images.

Do you guys support these?  Is k_dpm_2 DPMSolverMultistepScheduler?

Very helpful - thank you

> @Suhail To generate features from the pretrained backbones, just use a transform similar to the standard one used for evaluating on image classification with the typical ImageNet normalization mean...

> > > @Suhail To generate features from the pretrained backbones, just use a transform similar to the standard one used for evaluating on image classification with the typical ImageNet...

Sounds like this is all I need to do to get a features embedding: `dino_emb = dinov2_vitg14(t_img.unsqueeze(0))`

After `sudo make install`, I got things working via: 'libraries': ['-lsoundio'], (same as `-l libsoundio` I believe) `#include ` in my cpp file If it's not working, I'd try sudo...