[Birch-san]

stable-diffusion supports k-diffusion just fine on M1. You just have to detach a tensor in to_d() to stop the values exploding to infinity. https://twitter.com/Birchlabs/status/1563622002581184517?s=2...

[code51]

I've been following your MPS branch and have run it but couldn't address the issue without this explanation. Thank you!