Welcome to my first style LoRA! SD3 Version is already at Shakker AI! <a target="_blank" rel="ugc" href="https://www.shakker.ai/modelinfo/20d01bf7f9be44778b723939574346aa">https://www.shakker.ai/modelinfo/20d01bf7f9be44778b723939574346aa</a> Optimal settings and model to use it on: Deliberate - <a target="_blank" rel="ugc" href="https://civarchive.com/models/4823/deliberate">https://civarchive.com/models/4823/deliberate</a> Anime - <a target="_blank" rel="ugc" href="https://civarchive.com/models/108656/anime">https://civarchive.com/models/108656/anime</a> Try to mix it with my "Eflorescense" LoRA! (See results in <a target="_blank" rel="ugc" href="https://civarchive.com/images/1616935?period=AllTime&amp;periodMode=published&amp;sort=Newest&amp;view=categories&amp;modelVersionId=117611&amp;modelId=109158&amp;postId=407852">posts</a>) Prompt tweaks: Optimal weights for LoRA: 0.7 - 0.9 "Trigger word" - Style by NTY. You can play with weights, I prefer to use it on 1.3 - 1.4. Use "dark" for darker images, and "colourful" for more coloured arts. Negative prompt: (worst quality, low quality, mutated hands and fingers, bad anatomy, wrong anatomy, ugly, mutation:1.2) Technical settings: Steps: 22 - 27 Sampler: DPM++ 2M Karras CFG scale: 2.5 - 5 Clip skip: 1 - 2 (preferably 2) Feel free to play with weights to get the best results!SDXLI've made an SDXL version of my lora from the same dataset!<a target="_blank" rel="ugc" href="https://civarchive.com/models/137963/oilpaint-sdxl">https://civarchive.com/models/137963/oilpaint-sdxl</a>

Olivian Opulence / Oil Paint LoRA

OilPaint.safetensors

v1.0

Welcome to my first style LoRA!Optimal settings and model to use it on:Deliberate - <a target="_blank" rel="noopener noreferrer nofollow" href="https://civitai.com/models/4823/deliberate">https://civitai.com/models/4823/deliberate</a>Anime - <a target="_blank" rel="noopener noreferrer nofollow" href="https://civitai.com/models/108656/anime">https://civitai.com/models/108656/anime</a>Try to mix it with my "Eflorescense" LoRA! (See results in <a target="_blank" rel="ugc" href="https://civitai.com/images/1616935?period=AllTime&amp;periodMode=published&amp;sort=Newest&amp;view=categories&amp;modelVersionId=117611&amp;modelId=109158&amp;postId=407852">posts</a>)Prompt tweaks: Optimal weights for LoRA: 0.7 - 0.9 "Trigger word" - Style by NTY. You can play with weights, I prefer to use it on 1.3 - 1.4. Use "dark" for darker images, and "colourful" for more coloured arts.Negative prompt: (worst quality, low quality, mutated hands and fingers, bad anatomy, wrong anatomy, ugly, mutation:1.2)Technical settings:Steps: 22 - 27Sampler: DPM++ 2M KarrasCFG scale: 2.5 - 5Clip skip: 1 - 2 (preferably 2)Feel free to play with weights to get the best results!SDXLI've made an SDXL version of my lora from the same dataset!<a target="_blank" rel="noopener noreferrer nofollow" href="https://civitai.com/models/137963/oilpaint-sdxl">https://civitai.com/models/137963/oilpaint-sdxl</a>

Files with SHA256: dad9061b2e3dd721cbf9b9c1ffc89440b0950b59134a259e8d0467ca45e47463