Type | |
Stats | 2,381 33 |
Reviews | (363) |
Published | Mar 7, 2023 |
Base Model | |
Training | Steps: 4,700 Epochs: 1 |
Trigger Words | kamado nezuko bamboo |
Hash | AutoV2 A3DEE64FBE |
Esthetic Nezuko Kamado (Demon Slayer: Kimetsu no Yaiba)
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
Due to the high quality of the art, I advise you to use the clip skip 2, but it is possible and clip skip 1 if it is completely possible to realize the plan
CFG Scale - 3.5-6
LORA weight from 0.2 to 1 depending on your goals, 1 - closer to the original style, there are no restrictions here, 0.6 - 0.5-0.7 is a good choice
Use Abyssorangemix3aom3_aom3a3.safetensors With these negative prompts:
(worst quality, low quality:1.4) OR (EasyNegative:1) (don't use together)
EasyNegative - embedding
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 2, upscaler Latent (nearest-exact) or just Latent (if there are problems with the image), the picture will be much more detailed.
Trigger Words: kamado nezuko, bamboo
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 <3 above, I will be pleased :3