diff options
| author | brkirch <brkirch@users.noreply.github.com> | 2023-01-25 04:51:45 +0000 |
|---|---|---|
| committer | brkirch <brkirch@users.noreply.github.com> | 2023-01-25 06:13:02 +0000 |
| commit | 84d9ce30cb427759547bc7876ed80ab91787d175 (patch) | |
| tree | a87ca1a7094ca9b7af4e573a211b1dcf8146af67 /README.md | |
| parent | 48a15821de768fea76e66f26df83df3fddf18f4b (diff) | |
| download | stable-diffusion-webui-gfx803-84d9ce30cb427759547bc7876ed80ab91787d175.tar.gz stable-diffusion-webui-gfx803-84d9ce30cb427759547bc7876ed80ab91787d175.tar.bz2 stable-diffusion-webui-gfx803-84d9ce30cb427759547bc7876ed80ab91787d175.zip | |
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 'README.md')
| -rw-r--r-- | README.md | 1 |
1 files changed, 1 insertions, 0 deletions
@@ -157,4 +157,5 @@ Licenses for borrowed code can be found in `Settings -> Licenses` screen, and al - DeepDanbooru - interrogator for anime diffusers https://github.com/KichangKim/DeepDanbooru
- Security advice - RyotaK
- Initial Gradio script - posted on 4chan by an Anonymous user. Thank you Anonymous user.
+- Sampling in float32 precision from a float16 UNet - marunine for the idea, Birch-san for the example Diffusers implementation (https://github.com/Birch-san/diffusers-play/tree/92feee6)
- (You)
|