Anime Screencap Style LoRA

Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕

This took a lot of time, as the dataset had to be fairly large. Plus I made some mistakes along the way and had to start over a couple of times.

For the preview pics I used weight between 0.2 and 0.4 as this net is pretty strong. As for the model I used Anything V4.5, but it probably works with most nai based things. Trigger keyword is anime screencap.

30 epoch version is usually better and stronger. Still decided to add the 35 epoch because it gave me a better result once.

Be aware that this model is NSFW and can generate explicit hentai stuff.

Also note that I have used no embedding for the examples.

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)