diff options
| author | AUTOMATIC1111 <16777216c@gmail.com> | 2023-01-25 16:12:29 +0000 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-01-25 16:12:29 +0000 |
| commit | 1574e967297586d013e4cfbb6628eae595c9fba2 (patch) | |
| tree | 99374009f63cf73cadc713b02db5fbba0701e516 /README.md | |
| parent | 1982ef68900fe3c5eee704dfbda5416c1bb5470b (diff) | |
| parent | e3b53fd295aca784253dfc8668ec87b537a72f43 (diff) | |
| download | stable-diffusion-webui-gfx803-1574e967297586d013e4cfbb6628eae595c9fba2.tar.gz stable-diffusion-webui-gfx803-1574e967297586d013e4cfbb6628eae595c9fba2.tar.bz2 stable-diffusion-webui-gfx803-1574e967297586d013e4cfbb6628eae595c9fba2.zip | |
Merge pull request #6510 from brkirch/unet16-upcast-precision
Add upcast options, full precision sampling from float16 UNet and upcasting attention for inference using SD 2.1 models without --no-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)
|