<ol><li>Lora is trained in the works of a Golden Age artist. It's realism, of course. Anime hadn't been invented yet.</li><li>It will try to make your image look realistic. Use the scientific method and adjust the weight of LoRa for a particular character. Different checkpoints will have different results, different datasets will have different results.</li><li>It looks like the hatching is perceived by SD as part of the frame. Try non-standard resolutions, for example 1920x1080 with upscaling x2 as in one of the previews, you may get very interesting results.</li></ol>

Files with SHA256: ecc00821c36aed9dd3ba2283fffe1d5db2f4f26a28d665323b4b4285d230de2d