Esthetic Jang Wonyoung (v1.7)
Added 2023-03-16 13:12:58 +0000 UTCPatreon version. Double the number of art - more variety, more accuracy, MUCH less distortion at high Hires fix, better hands, better legs, better eyes, better teeth. Better adapted to other models, even anime models. Of the shortcomings, I note a little less details of the backs, fewer curls))) (fixed by adding curly hair prompt), the influence of art with a "chubby face" has been reduced (for some, a disadvantage, for someone, a plus).
LORA weight - I use 0.7-0.8
CFG Scale - 4 (don't use 6 or higher)
Use model ddosmix
This model does not need loras and embeddings "improvers", like ulzzang-6500 or koreanDollLikeness, just use ddosmix
Just use hires fix as much as your video card is capable of, so as not to give an error, with 8gb of video memory it is 512x768 with hires fix 1.7-2.0, upscaler Latent (nearest-exact) or just Latent (if there are problems with the image), the picture will be much more detailed.
Trigger Words: Jang Wonyoung
Combined with my other LORA
How to use LoRA's in auto1111:
- Update webui (use git pull like here or redownload it)
- Copy the file to stable-diffusion-webui/models/lora
- Select your LoRA like in this video
- Make sure to change the weight (by default it's :1 which is usually too high)
*Information taken from Lykon
