Makes images similar in style to the artist Epeulu.
How to use
Prompt as normal, this version was trained on solely humanoids. Things this LoRA likes outputting is hatching textures, depth of field, heavy shading, Chainsaw Man characters and various human and monster girl features. Some of the images had a white border which may blend in, use “border” and/or “white border” in negatives if so. All where in greyscale/monochrome but you can prompt color too.
For more prompt suggestions please see the sample images or the uploaded zip of training tags.
MISC
Trained on Pony SDXL at 1024 resolution with a dataset of 88 images.
All sample images are raw txt2img upscales, no inpainting or helper embeddings used, e.g – your outputs should look better with more than minimum effort.
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 artist if you want the good stuff