AUTOMATIC1111/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2026-04-29 02:31:40 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add option for float32 sampling with float16 UNet

Browse Source 
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().
This commit is contained in:
brkirch
2023-01-24 23:51:45 -05:00
parent 48a15821de
commit 84d9ce30cb
8 changed files with 82 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@@ -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)