Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
Model commissioned/sponsored by Dreamscape, which is building an open source platform (non-exclusive) for model creators. Join their discord here: https://discord.gg/tDsAykmcff.
This was trained on my hand selected and tagged dataset of "western illustrations" of the specific type requested by the client. Trigger word is western illustration
and should work fine on AnyLoRA at weight 1.
It works most accurately on AnyLoRA and I've offset it so that it works at 1 weight. Should actually work on most anime models and on NeverEnding Dream.
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
)