Pleased to present a Solo Levelling style LoRA (or more accurately Jang Sung-rak's style R.I.P). Wasnt trained with any NSFW in the dataset, but by all means it can be NSFW if you prompt for it because it was trained on Anything v4.0. You can weight it from 0.7-1 and you should get pretty consistent results. For further away shots, the eyes can get a little fucky, but what can you do. Just inpaint them if they are that bad. You can prompt whatever you want, but to achieve the firey look, add fire or blue fire. Armor or Black armor also works well to get the manhwa feel. As seen in the larger panel style images I made, it receives prompts like Dragon and Monster really well. Long story short, if just prompt for what you want based on what you know/want from the Manhwa and you should be able to get it (Besides the dymanic fights because dur.... although controlnet/inpainting could probably do it) Enjoy If you have any LoRA requests and wouldnt mind buying me a Hot Chocolate, please consider going to my page. <a target="_blank" rel="ugc" href="https://www.buymeacoffee.com/JohnStinko">https://www.buymeacoffee.com/JohnStinko</a>

Solo Levelling style LoRA [76mb]

4th Epoch, 7,600 optimized steps (Total 30,400 without Batch = 4), 512x512. THIS LORA IS OUTDATED. If you wish to use it with the original merge it was trained on, use the following merge recipe: Anything 4.0 (Offset True Darkness - SD 1.5) Aultiplier = x1 Add difference

Files with SHA256: a4d5b693c6282280e9eb8da68ba10f8dd7801f7e9dd94f177195f8d1ad11b0a0