v3 - Updated methods, accuracy, captions and a bunch of other work over a few days. Though similar results, I feel this version prompts better now; Examples are with the preview images but it tends to work well even just written as: &lt;loraname:1&gt; or: in the style of &lt;loraname:1&gt;, It can be tricky to get night scenes ( especially indoors ) this is something I might improve in the future but for now try adding night, dark, to prompts. FOR v2 USERS: you no longer need howlsbgs as a trigger word on v3.<a target="_blank" rel="ugc" href="https://www.patreon.com/nucleardiffusion">https://www.patreon.com/nucleardiffusion</a>or please consider an easy one off donation here: <a target="_blank" rel="ugc" href="https://ko-fi.com/nucleardiffusion">https://ko-fi.com/nucleardiffusion</a> Trained from the brilliant Ghibli movie Howls Moving Castle only, this LoRA is capable of creating different interiors and landscapes in the style from the film.Notice: This free work is intended for art and illustration purposes of emergent technology and not intended nor' trained for making illicit images, as the author I've taken care to not use any private data in the training process or designed it for such purposes. By downloading this model you are agreeing with the aforementioned intent and that you will not use my work to create / share images of a potentially immoral and / or illegal nature.

Files with SHA256: 07645d116ad3a4652c299ba20e163289336dd20874c8605a79da6ec14a166f92