fixes issue where "--use-cpu" all properly makes SD run on CPU but leaves ControlNet (and other extensions, I presume) pointed at GPU, causing a crash in ControlNet caused by a mismatch between devices between SD and CN
https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/14097
Since norm layer need fp32, I only convert the linear operation layer(conv2d/linear)
And TE have some pytorch function not support bf16 amp in CPU. I add a condition to indicate if the autocast is for unet.
Adds "Upcast cross attention layer to float32" option in Stable Diffusion settings. This allows for generating images using SD 2.1 models without --no-half or xFormers.
In order to make upcasting cross attention layer optimizations possible it is necessary to indent several sections of code in sd_hijack_optimizations.py so that a context manager can be used to disable autocast. Also, even though Stable Diffusion (and Diffusers) only upcast q and k, unfortunately my findings were that most of the cross attention layer optimizations could not function unless v is upcast also.
This also handles type casting so that ROCm and MPS torch devices work correctly without --no-half. One cast is required for deepbooru in deepbooru_model.py, some explicit casting is required for img2img and inpainting. depth_model can't be converted to float16 or it won't work correctly on some systems (it's known to have issues on MPS) so in sd_models.py model.depth_model is removed for model.half().
When saving training results with torch.save(), an exception is thrown:
"RuntimeError: Can't call numpy() on Tensor that requires grad. Use tensor.detach().numpy() instead."
So for MPS, check if Tensor.requires_grad and detach() if necessary.
torch.manual_seed() already sets a CPU generator, so there is no reason to create a CPU generator manually. torch.randn_like also needs a MPS fix for k-diffusion, but a torch hijack with randn_like already exists so it can also be used for that.
Fix typo "MasOS" -> "macOS"
If MPS is available and PyTorch is an earlier version than 1.13:
* Monkey patch torch.Tensor.to to ensure all tensors sent to MPS are contiguous
* Monkey patch torch.nn.functional.layer_norm to ensure input tensor is contiguous (required for this program to work with MPS on unmodified PyTorch 1.12.1)
Kohaku-Blueleaf