Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
There is already a pretty good embedding, but this was still requested as a LoRA net, so I made it.
I've tested it on some of my anime models and seems to work as per usual. You find prompts and models in the PNG data reported in the info (bottom right corner of the pics). Pic 2 and 5 have been made using NeverEnding Dream (NED).
The main trigger word is makima \(chainsaw man\)
but, as usual, you need to describe how you want her, as the model is not overfitted. Weight should be between 1 and 1.4 for the offset version (0.5-0.7 for the original one). The pic with the bunny costume is also using my ratatatat74 LoRA. Pic 1, 3, and 10 have been made by Joobilee.
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 according to the instructions (by default it's :1
)