Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
Consider leaving a ❤️ to receive future updates.
Second successful experiment I made for testing out my theory on how to make an anime character from a photorealistic dataset. The answer was simply to use NeverEnding Dream (NED). The first one, with an explanation of the process, was my Jack Sparrow one: https://civitai.com/models/12206/jack-sparrow-realistic-anime-lora-guide
You can use at weight 1 generally, but tune it based on the model (see the examples). Trigger is liv moore
. Control the style using photorealistic
or anime screencap
(with an appropriate model)
As most of my LoRA's, this can be customized a lot. However, this time I tuned down the likeness of the actress. I'm also locking down the comment section to avoid porn.
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
)