~scriptsaistable-diffusion-webui-forge
1 itemDownload ./*

..
startcmdonly.bat


stable-diffusion-webui-forgestartcmdonly.bat
1 KB• 9•  8 months ago•  DownloadRawClose
8 months ago•  9

{}
@echo off

echo 1 >F:\xampp\www\stable.log

rem python -m venv venv

rem call venv\Scripts\deactivate.bat
rem call venv\Scripts\activate.bat

set PYTHON=
set GIT=
set VENV_DIR=
set COMMANDLINE_ARGS=--listen --api --xformers --enable-console-prompts --precision full --disable-gpu-warning
rem  --no-half
rem --no-half By running that argument you are denying the card the ability to run at fp16 (half precision), which is a massive speed boost without much quality loss. 
rem --op-sdp-attention can slightly improve performance over --xformers but it uses so much more Vram even my 24GB 3090 cannot do a 2x upscale to 2048x2048 without running out of ram, so it is useless for higher resolutions. 

@REM Uncomment following code to reference an existing A1111 checkout.
@REM set A1111_HOME=Your A1111 checkout dir
@REM
@REM set VENV_DIR=%A1111_HOME%/venv
@REM set COMMANDLINE_ARGS=%COMMANDLINE_ARGS% ^
@REM  --ckpt-dir %A1111_HOME%/models/Stable-diffusion ^
@REM  --hypernetwork-dir %A1111_HOME%/models/hypernetworks ^
@REM  --embeddings-dir %A1111_HOME%/embeddings ^
@REM  --lora-dir %A1111_HOME%/models/Lora

call webui.bat

rem accelerate launch --num_cpu_threads_per_process=6 launch.py


echo 0 >F:\xampp\www\stable.log


Top
©twily.info 2013 - 2025
twily at twily dot info



2 335 039 visits
... ^ v