If you like what I do please consider supporting me on <a target="_blank" rel="ugc" href="https://patreon.com/getphat">Patreon</a> and contributing your ideas to my future projects!Leonardo da Vinci art style LoRA for SDXL 1.0. Leonardo da Vinci is one the most famous artists of all time and now you can generate art similar to his style within your own Stable Diffusion workflow. This model was trained on 1024 x 1024 resolution and is able to produce higher details and greater accuracy than if you were to simply type his name into your prompt. This LoRA was particularly challenging because all of his paintings are hundreds of years old and have degraded significantly over time. I am pleasantly surprised with the outcome of the model however. I decided to not do any kind of restoration on the training images so you will see cracked and chipped paint as well as other types of flaws in the outputs at higher LoRA weights. <a target="_blank" rel="ugc" href="https://imgur.com/a/GRE4bX3%EF%BF%BC%EF%BF%BCI"> </a>I use this at a weight of around 0.8 - 1 but you may have to adjust the weight up or down to 0.6 incrementally by 0.1 depending on the complexity of your prompt. I used clip skip 1 for all of the images you see uploaded to this page. CFG 7 I think works good for this art style. The main trigger is dvnc and there are no additional tags for this art style. Be creative with your txt2img or use img2img to guide the basic composition and colors. Have fun playing around with this remarkable tech and if you like it be sure to review and upload all of your amazing works of art!

Files with SHA256: 7c567101e0ba7112ced9276f16375e817a75a74c752e8385bfe78ad2bed25a30