InvokeAI/invokeai/backend/stable_diffusion/diffusion
gogurtenjoyer 233869b56a Mac MPS FP16 fixes
This PR is to allow FP16 precision to work on Macs with MPS. In addition, it centralizes the torch fixes/workarounds
required for MPS into a new backend utility file `mps_fixes.py`. This is conditionally imported in `api_app.py`/`cli_app.py`.

Many MANY thanks to StAlKeR7779 for patiently working to debug and fix these issues.
2023-07-04 18:10:53 -04:00
..
__init__.py all vestiges of ldm.invoke removed 2023-03-03 01:02:00 -05:00
cross_attention_control.py make InvokeAIDiffuserComponent.custom_attention_control a classmethod 2023-05-11 21:13:18 -04:00
cross_attention_map_saving.py all vestiges of ldm.invoke removed 2023-03-03 01:02:00 -05:00
shared_invokeai_diffusion.py Mac MPS FP16 fixes 2023-07-04 18:10:53 -04:00