A colorful artistic style specialized mainly in portraitsHow to use While no trigger word is required I highly recommend using "simple background" or, preferably, any color background tag.On AOM2 and any other model with realism mixed in I also recommend adding "3d" and/or "realistic" to the negative tags for best performance. Content this model is good at are portraits as mentioned, upper body shots, close-ups, androgynous boys and themes from the Berserk manga. The LoRA is a bit unstable, you may occasionally get nightmarish fleshpile monstrosities but I still felt like sharing it since when it works it works very well IMHO.For prompt tips please see the sample images or the uploaded zip of training tags.As usual all images are raw, slightly cherrypicked, txt2img gens, no inpainting or helper embeddings used.MISC Trained on NAI at 512 resolution with a dataset of 80 images. 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 <a target="_blank" rel="ugc" href="https://twitter.com/nisino2222">Nisino22222</a> if you want the good stuff.

Files with SHA256: 51bb364260fca415475f86e269e75731dd31d6a9c74d91e11d7b39108213cf17