<h3 id="v2.7-ilnoob-versionskipped-2.0-2.6-as-these-where-failed-versions"><span style="color:rgb(253, 126, 20)"><u>V2.7 IL/NOOB Version</u></span><br />skipped 2.0-2.6 as these where failed versions</h3><h3 id="suggested-weight-anywhere-from-0.8-to-1">Suggested weight anywhere from 0.8 to 1</h3><p>Scheduling type depends on base model you use but in most cases Euler a works fine.</p><p>this LoRA was 100% made with my own self-made art, I rendered everything in Blender cycles/eevee</p><p>This version was trained locally on my pc using the same dataset as last version but it has way better results and the file size is much more agreeable</p>

BCkiwi's 3D style

<ul><li><p>Better dataset tagging</p></li><li><p>Expanded training dataset by over 2 times as much from V1</p></li><li><p>Better style consistency </p></li></ul>

Files with SHA256: 84adb35e13bb5e860316a00fc4b2329ac8a85e048f6f8a805ed8dfc1ee5cbe9f