diff options
| author | brkirch <brkirch@users.noreply.github.com> | 2023-01-24 23:51:45 -0500 |
|---|---|---|
| committer | brkirch <brkirch@users.noreply.github.com> | 2023-01-25 01:13:02 -0500 |
| commit | 84d9ce30cb427759547bc7876ed80ab91787d175 (patch) | |
| tree | a87ca1a7094ca9b7af4e573a211b1dcf8146af67 /modules/sd_hijack_optimizations.py | |
| parent | 48a15821de768fea76e66f26df83df3fddf18f4b (diff) | |
Add option for float32 sampling with float16 UNet
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().
Diffstat (limited to 'modules/sd_hijack_optimizations.py')
0 files changed, 0 insertions, 0 deletions