Blacksouls style, trained on the in game character shots. Pony XL version of a previously released NAI-based <a target="_blank" rel="ugc" href="https://civarchive.com/models/66944/blacksouls">LoRA</a>.Prompt: "1girl" and then whatever else you want. A lot of monster girls in the dataset so those types of tags work fairly well. I recommend using DPM++ 2M Karras since other samples tend to clean up the output too much. For more specific prompts tips please see the sample images. Note that v1.1 version requires the Pony XL trigger "anime source". If this conflicts with other LoRAs please use v1.0.Misc Trained on Pony SDXL at 1024 resolution with a dataset of 213 images. All images are untouched txt2img, no inpainting or helper embeddings used for quality transparence, e.g. - things should look even better if you do. The training was done on a small subset of the artists images, as such the output of this LoRA is not an accurate representation neither in quality or style of the source material. Go support the <a target="_blank" rel="ugc" href="https://www.dlsite.com/maniax/circle/profile/=/maker_id/RG33488.html">circle</a> if you want the good stuff.

BLACKSOULS [Pony XL]

Retrained using 'source_anime' Pony XL tag. Should perform more reliably especially with non-canon content. Increased feelings of despair by 40%

Files with SHA256: eae0b9ba6e48ab8fccc0f0fd5956c56710f9faf20cd6b501fc55de819b2203bd