<h1 id="heading-54">Credit:</h1>This script package from bdsqlszuse <a target="_blank" rel="ugc" href="https://github.com/kohya-ss/sd-scripts">kohya-ss/sd-scripts (</a><a target="_blank" rel="ugc" href="http://github.com">github.com</a><a target="_blank" rel="ugc" href="https://github.com/kohya-ss/sd-scripts">)</a> for coreoriginal script from <a target="_blank" rel="ugc" href="https://github.com/Akegarasu/lora-scripts">Akegarasu/lora-scripts: LoRA training scripts use kohya-ss's trainer, for diffusion model. (</a><a target="_blank" rel="ugc" href="http://github.com">github.com</a><a target="_blank" rel="ugc" href="https://github.com/Akegarasu/lora-scripts">)</a><h1 id="heading-55">How to use:</h1>0、(windows)Give unrestricted script access to powershell so venv can work:<ul><li>Open an administrator powershell window</li><li>Type <code>Set-ExecutionPolicy Unrestricted</code> and answer A</li><li>Close admin powershell window</li></ul>1、Unzip this to anyway you want(Recommend with other train program which has venv)if you Update it,just Rerun <a target="_blank" rel="ugc" href="http://install-cn-qinglong.ps">install-cn-qinglong.ps</a>1.then enter N2、Run install-cn-qinglong.ps1 in windows(linux just use commnd line)it will automatically install environment(if you has venv,just put to over it)3、Put your datesets in /input dir.a formattting: ./input/2_lora/(datasets images)4、Run tagger.ps1 for tagger them,automatically.(linux use tagger.sh)5、Edit your datesets if your want6、Edit train script(train_8Glora or train_16G_DB)(linux use train_tacanime)<h2 id="heading-56">just for</h2><ol><li>train_mode(lora、db、sdxl_lora、sdxl_db、cn3l)</li><li>pretrained_model</li><li>train_data_dira formatting ./input/</li><li>resolution(SDXL for 1024*1024,sd1.5 for 576*576)</li><li>max and min bucket repo(SDXL 640~1536,sd1.5:256~1024)</li><li>optimizer(SDXL:adaFactor for batch size1,Pagedadamw8bit for batch size 4)</li></ol>other dont need more change if you dont know itif i can help you ,i will very happy that~<a target="_blank" rel="ugc" href="https://ko-fi.com/bdsqlsz">Support 青龍聖者@bdsqlsz on Ko-fi! ❤️. </a><a target="_blank" rel="ugc" href="http://ko-fi.com/bdsqlsz">ko-fi.com/bdsqlsz</a><a target="_blank" rel="ugc" href="https://ko-fi.com/bdsqlsz"> - Ko-fi ❤️ Where creators get support from fans through donations, memberships, shop sales and more! The original 'Buy Me a Coffee' Page.</a>

SDXL LoRA train(8GB) and Checkpoint finetune(16GB)

fixed bugs about bitsandbytes over 0.35

sdxlLoraTrain8GBAnd_v30.zip

v3.0

v12.1

v6.5

v4.5

v4.0

v3.5

v2.0

v1.1

v1.0

Files with SHA256: afde27c6fcd1e5414891b6c4b21fe18079efb8a5ed7945f6fa61b26829a2802c