<h1>LoRA of Kursk from Azur Lane</h1>Recommended parameters:<ul><li>LoRA weight: 0.6-0.8</li><li>Sampling method: Euler a or DPM++ 2M Karras or SDE</li><li>Sampling steps: 20-40</li><li>CFG Scale: 4-11</li><li>Upscaler: depend on model that you use UPDATE I did V2 (2 versions with deferent training parameters) based on new dataset but i have no option to test it, so i will be grateful if someone can test it and send a results: <a target="_blank" rel="ugc" href="https://drive.google.com/drive/folders/1cek7rWy9QvPY0C9RXlNP3tjWxGUQJoCe?usp=share_link">LINK</a></li></ul>

[SN] Kursk | Azur Lane | LoRA

Data set is 18 imagines. It's enough to make simple LoRA, but not enough for perfect result. It will be improved in future!

Files with SHA256: e4ed7a8af8c028bbe9c6eec2bd36b590caf4d1242bb52d8c3c5349bd72aaa088