Apparently the version of PyTorch macOS users are currently at doesn't always handle half precision VAEs correctly. We will probably want to update the default PyTorch version to 2.0 when it comes out which should fix that, and at this point nightly builds of PyTorch 2.0 are going to be recommended for most Mac users. Unfortunately someone has already reported that their M2 Mac doesn't work with the nightly PyTorch 2.0 build currently, so we can add --no-half-vae for now and give users that can install nightly PyTorch 2.0 builds a webui-user.sh configuration that overrides the default.
Allows loading instruct-pix2pix models via same method as inpainting models in sd_models.py and sd_hijack_ip2p.py
Adds ddpm_edit.py necessary for instruct-pix2pix
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().
add PIP_INSTALLER_LOCATION env var to install pip if it's not installed
remove accidental call to accelerate when venv is disabled
add another env var to skip venv - SKIP_VENV
The loading of the model for approx nn live previews can change the internal state of PyTorch, resulting in a different image. This can be avoided by preloading the approx nn model in advance.
