OPENGIT/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2025-02-07 06:02:53 +08:00
Code Issues Packages Projects Releases Wiki Activity

Add version note

catboxanon 2023-08-17 09:33:23 -04:00
parent eaad63b1ff
commit 18c4f01620
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
Features.md

@ -771,7 +771,7 @@ CLIP is a very advanced neural network that transforms your prompt text into a n
Some models were trained with this kind of tweak, so setting this value helps produce better results on those models.
## Extra noise
Adds additional noise from the random seed, determined by the setting, defaulting to `0`. Implemented in [#12564](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12564), available in settings under `img2img` -> `Extra noise multiplier for img2img and hires fix`. As noted in the UI, it should always be lower than the denoising strength used to yield the best results.
Adds additional noise from the random seed, determined by the setting, defaulting to `0`. Implemented in version 1.6.0 via [#12564](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/12564), available in settings under `img2img` -> `Extra noise multiplier for img2img and hires fix`. As noted in the UI, it should always be lower than the denoising strength used to yield the best results.
One purpose for this tweak is to add back additional detail into hires fix. For a very simplified understanding, you may think of it as a cross between GAN upscaling and latent upscaling.