mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
233869b56a
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. |
||
---|---|---|
.. | ||
diffusion | ||
image_degradation | ||
schedulers | ||
__init__.py | ||
diffusers_pipeline.py | ||
offloading.py |