From 84d9ce30cb427759547bc7876ed80ab91787d175 Mon Sep 17 00:00:00 2001 From: brkirch Date: Tue, 24 Jan 2023 23:51:45 -0500 Subject: 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(). --- README.md | 1 + 1 file changed, 1 insertion(+) (limited to 'README.md') diff --git a/README.md b/README.md index 9c0cd1ef..a5611671 100644 --- a/README.md +++ b/README.md @@ -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) -- cgit v1.2.3