From 15a4f5f6fc36d7ba235bb1511e2c2c96bb741da2 Mon Sep 17 00:00:00 2001 From: AUTOMATIC1111 <16777216c@gmail.com> Date: Thu, 4 May 2023 11:27:51 +0300 Subject: [PATCH] Updated Seed breaking changes (markdown) --- Seed-breaking-changes.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/Seed-breaking-changes.md b/Seed-breaking-changes.md index 03e99d0..14d9601 100644 --- a/Seed-breaking-changes.md +++ b/Seed-breaking-changes.md @@ -1,4 +1,4 @@ -# v1.1.0 #9669 - Fix prompt schedule for second order samplers +# v1.1.0 [#9669](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/9669) - Fix prompt schedule for second order samplers Second order samplers (Heun, DPM2/a, DPM++ 2S/a, DPM++ SDE / Karras) cause the prompt schedule to run twice as fast when prompting something like [dog:cat:0.5] (i.e. for 100 steps, prompt is dog until step 25, cat until 50, and remains dog until 100). This fixes that by checking if the sampler is any of these second order samplers and multiplies the step count by 2 for calculating the prompt schedule. # [2023-03-26](https://github.com/AUTOMATIC1111/stable-diffusion-webui/commit/80b26d2a69617b75d2d01c1e6b7d11445815ed4d) - Apply LoRA by altering layer's weights