Jang Wonyoung (Ive) save the world ( ͡❛ ᴗ ͡❛)✌

P.P.S. new model ogipote (2.5D) and ogipote (2.5D)_v2.0 on Boosty

I made a video on how to achieve the same quality or just repeat my art

my first attempt at a realistic character, I didn't want to post a badly done job so it took a long time, the lack of realism is in the details of the face, more training is needed, I took down some bad lora and came to the conclusion that booru tags fit realism as well, that gave a significant increase in quality + correctly selected tags, improved art, manual prompts and correct settings, in general I am dissatisfied (as always) and will continue to train realism to find the best approach.

LORA weight - I use 0.6-1

CFG Scale - 4-9 (According to my personal observations, 6-7 is the best choice)

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
  
  Please post your work with or without comments, it will help me improve. Thanks!
  
  If you like my work, click on the heart above, I will be pleased :3