From b7deec399a19dcc0dad67d1a91cdba405f4076f4 Mon Sep 17 00:00:00 2001 From: ClashSAN <98228077+ClashSAN@users.noreply.github.com> Date: Fri, 14 Apr 2023 03:43:30 +0000 Subject: [PATCH] upcast-sampling, note for hampered nvidia cards --- Optimizations.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/Optimizations.md b/Optimizations.md index b2d682c..e0fda59 100644 --- a/Optimizations.md +++ b/Optimizations.md @@ -1,4 +1,4 @@ -A number of optimization can be enabled by [commandline arguments](Run-with-Custom-Parameters): +A number of optimization can be enabled by [commandline arguments](Command-Line-Arguments-And-Settings): | commandline argument | explanation | |--------------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| @@ -15,6 +15,7 @@ A number of optimization can be enabled by [commandline arguments](Run-with-Cust | `*do-not-batch-cond-uncond` | Prevents batching of positive and negative prompts during sampling, which essentially lets you run at 0.5 batch size, saving a lot of memory. Decreases performance. Not a command line option, but an optimization implicitly enabled by using `--medvram` or `--lowvram`. | | `--always-batch-cond-uncond` | Disables the optimization above. Only makes sense together with `--medvram` or `--lowvram` | | `--opt-channelslast` | Changes torch memory type for stable diffusion to channels last. Effects not closely studied. | +| `--upcast-sampling` | For Nvidia and AMD cards normally forced to run with `--no-half`, [should improve generation speed](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/8782). | Extra tips (Windows):