"I woke up this morning wondering: 'What would happen if I put the Monster Manual of D&D 3.5 in a blender to make a LoRa.'
PonyXL version - use 1.2 strenght, use <lora:ADD_3.5_Monster_Manual_PonyXL:1.2> text, character name, character_profile trigger words.
I first generate txt to img DPM++ 2m, 20 sampling steps.
Then i send the image in img to img and go to 40 sampling steps with ADetailer if need.
Here's what it gives. This LoRa is strange, experimental, but I find it interesting. It's not perfect (that's not the goal), but I think there's a lot to do and test with to achieve great results. Or simply be surprised by the creations of AI?
Test, have fun, and, most importantly, share the strange or not-so-strange results you get!
Description
For this version you must use strenght at least a 1.2 and trigger worlds: text, character name, character_profile
FAQ
Comments (2)
How did you do it? It is very cool! My attempts to do something similar have failed
Hi ! I have transform the three monster manuels and fiend folio in a lot of jpg, then delete all page without illustration. After that caption with Konya and the CivitAi lora maker :)
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.