This is a lora based on my favourite artist donaught. He/she is well known for their very thick/curvy proportions and I wanted to try and replicate it.
Image info
Model used anything v4.5
Training settings?
The most important part of training is getting a good dataset!
Training settings can be found by installing the additional networks extension in auto1111
Extensions -> available -> load from -> additional networks
Restart webui
place lora into stable-diffusion-webui\extensions\sd-webui-additional-networks\models\lora
To view the training settings
Go to additional network tab -> choose model -> training parameters
Description
FAQ
Comments (6)
Is there any difference between this one published just now and the V2 published in Apr?
this is much better than the older v2, less over trained + more high quality images
Nice! Thx, can't wait then to try it out. Great work as always btw :)
very nice!
If you don't mind, please make a LoRA of artist amazon(nacchuushou)
man what an outstanding lora rework, now it works impecable, pls pls pls can you update the same way kunaboto lora? it has practically the same problems older juju lora had, if would be this good as juju 2.0 it would mean world to me ma man pls, when youll have time ofc
Magnificent