nodes/wootwootwootwoot-ComfyUI-RK-Sampler
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Jay
2024-07-22 04:43:54 +07:00
committed by GitHub
parent abc4c2d913
commit 4f6211566a
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+2 -2
View File
@@ -19,7 +19,7 @@ ComfyUI Manager Menu > Install via Git URL > https://github.com/wootwootwootwoot
### Manual installation
> From `ComfyUI/custom_nodes` and ComfyUI virtual environment
```
git pull https://github.com/wootwootwootwoot/ComfyUI-RK-Sampler.git
git clone https://github.com/wootwootwootwoot/ComfyUI-RK-Sampler.git
pip install torchode
```
@@ -147,4 +147,4 @@ Tested on `RTX3090`, `SDXL`, `896x1152`, `CFG=30`, `ae_bosh3 (ComfyUI-RK-Sampler
The Runge-Kutta methods are a family of methods used for solving approximate solutions of ODEs by iterative discretization (or, if in diffusion terms, by sampling).
Runge-Kutta methods generally have less discretization error than standard diffusion sampling methods, allowing for the use of high CFG scales (within practical limits) to create high-quality results without artifacts.
Runge-Kutta methods generally have less discretization error than standard diffusion sampling methods, allowing for the use of high CFG scales (within practical limits) to create high-quality results without artifacts.