ParchartXL - art on parchmentThe unifying theme of this LoRA is the substrate - parchment. Just add 'on parchment' to any prompt!CODA: And that's a wrap! This version harmonizes basically all the previous versions of this LoRA and presents what is a near-perfect version of what I was chasing. The parchment texture (the whole raison d'être for the LoRA) is persistent and gorgeous, the illustration style consistent and reasonably flexible, and random words and annotations show up with regularity. Compared to the last version of the LoRA this final iteration brings back those annotations a lot. It also shows a lot lower frequency of the compass rose shapes (they still pop up, but not so persistently) and some of the parchment surface quality is a little better, more akin to v1.2 than subsequent versions.All in all, it's fully baked. Done and done!<a target="_blank" rel="ugc" href="https://civarchive.com/models/382972/parchart-sm">🔗 new 1.5 version of ParchArt on a separate model page</a>Have some need to generate just a blank sheet of parchment? <a target="_blank" rel="ugc" href="https://civarchive.com/models/141471?modelVersionId=286123">Check out the version 0.5 I uploaded here as well</a>. Pretty niche kind of thing, but it's yours if you want it!

ParchartXL

ParchartXL-2.0.safetensors

v2.0

CODA

v0.5

v1.5

v1.2

v1.1

v1.0

ParchartXL - art on parchment (if you want prompts from my sample images, head over to CivitAI <a target="_blank" rel="noopener noreferrer nofollow" href="https://civitai.com/models/141471/parchartxl">https://civitai.com/models/141471/parchartxl</a> - I'll try to replace these with images generated on Tensor-dot-art soon)The unifying theme of this LoRA is the substrate - parchment. Just add 'on parchment' to any prompt!2.0 update: After quite a few iterations, this model is finally approaching what always was my vision for it - a warm-toned, textured substrate with an art style of ink or pencil and watercolor or colored pencil that responds to a wide range of prompts.The parchment texture in early iterations of the LoRA were spot on, but the illustration style much more chaotic and messy than I wanted. As I refined the illustration style, I lost consistency of the parchment appearance too often. But with 1.5 I got much closer, though the illustration style moved a bit further from my target. And in 2.0 it finally all comes together. This is the style I have been aiming to present since I started training this odd thing.I can see it taking potentially one more version, as I revisit the idea of training on old maps, to bring some authentic-looking cartography. It's a very niche interest - but that would be my ideal form for ParchArt.If you want a bolder illustration style, I recommend using this LoRA at 1.0 strength in conjunction with Eldritch Comics at a lower strength, around 0.5Want more from me than images? You can also buy my short story "<a target="_blank" rel="noopener noreferrer nofollow" href="https://www.amazon.com/dp/B0BT8W58LT">Willem &amp; Ellene.</a>" But I warn you - it's darn near unreadable for most people.

Files with SHA256: 3149502826bb1cc7787baee766f603fa78d570801d5d7c5df70ccba887efc1e5