<a target="_blank" rel="ugc" href="https://patreon.com/psoft"><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/8dcbc56a-15e9-429e-9b36-c2bc22594678/width=525/8dcbc56a-15e9-429e-9b36-c2bc22594678.jpeg" /></a> Support my work on <a target="_blank" rel="ugc" href="https://www.patreon.com/psoft">Patreon</a> and <a target="_blank" rel="ugc" href="https://ko-fi.com/psoft">Ko-Fi</a> and get access to tutorials and exclusive models. Rate and leave a like if you enjoyed it, and follow for new models!<hr />Well, it's finally here again: the BLACKED LoRA! After many requests from users, after many many failed attempts, I bring you a new version of what has been my most controversial LoRA (need a hint why?).It still has its flaws, but I already spent way too much time to try to improve it (even starting a new dataset from scratch), with very little success. This version (v4.23!) was the best one so far. Hope you enjoy it!How to use. Trigger: black manYou should include tags that describe an interaction between characters, e.g.: couple, hug, kiss, sex, grabbing, or sex-related tags, e.g. sex, fellatio, gangbang, etc.

BLACKED

No trigger words, standard CFG, regular weight. Trained on NAI, should work with most models.You don't need LoRA specific trigger words, just as long as you have include male tags in your prompt (e.g. 1boy, 2boys, multiple boys) and/or sex-related tags (e.g. sex, fellatio, gangbang). In some models you can increase the effect by using tags such as black man, interracial, etc. See the examples (non-cherry-picked generations).The idea was to achieve good results with the least impact on style and composition as possible. You can use this LoRA in combination with other LoRAs (as long as those are not overtrained). Depending on the model, I suggest between 0.8-1.1 weight and your standard CFG.

Files with SHA256: 14bed5e872fbfac6572e8a973f78ed981288bf4621cf575e2a9075f2ba139665