Style LoRA trained on the artist <s>@18dart3</s> <a target="_blank" rel="ugc" href="https://twitter.com/18dart5">@18dart5</a>. Please let me know your thoughts!PonyXL version can also be downloaded <a rel="ugc" href="https://huggingface.co/AiAF/D-ART_18DART5_Style-LoRA">here from Huggingface! </a>Huggingface: <a target="_blank" rel="ugc" href="https://huggingface.co/AiAF">https://huggingface.co/AiAF</a>Twitter: AiArt Factory (@AiArtFactory) / X (twitter.com)TikTok: https://www.tiktok.com/@ai_art_factory?_t=8cykD6v1PRu&amp;_r=1Instagram: https://instagram.com/aiart.factory?igshid=NGExMmI2YTkyZg==Deviantart: https://www.deviantart.com/aiartfactory

D-ART | @18dart5 - Style LoRA [Anima | Flux.2 Klein | Z-image Turbo | Chroma | Illustratious | Flux | Pony Diffusion | NAI]

D-ART Style LoRA trained off of D-ART's style. I did something a little different with the data set this time. The images used are identical to the ones used to train the [De-watermarked] PonyXL LoRA, I decided to tag them with more natural sounding "naive" tags as opposed to booru style tagging.<s> I also did not include any trigger words for this one</s>. According to this quick-start guide, this leads to the LoRA performing better and has better responsiveness to prompts. It works well most of the time but will occasionally spit out realism pictures. Prompts like "anime style picture" or "cartoon" help steer it back to D-ART's style.

Files with SHA256: 84d3c509a8e58132aff7fe3ddcb3b9f9e10147f32c1af38de14bab62d09ad2fe