Making models is costing me my children's tuition. Do you like what I do? Feel free to buy me a coffee 🤗💖

This LoRA was made due to the request of an Anon Discord user and my appreciation for the art style of Silence Girl. I used NED (Never Ending Dream) as a base model for training. This LoRA was trained on about 90 Images of her art. I've been testing out some new things for style LoRA's so please let me know what you thinking by dropping a review. 💖

It's flexible enough merge with Character LoRA's and other Style LoRA's aswell. Please check the examples.

The LoRA itself is quite flexible with various weights. I personally recommend using Anything V4.5 to generate images with this model as it captures the 2D art style better but in the end it's up to you to decide and test out what works best for you.

There isn't any trigger words that specially trigger the LoRA ( I still don't know how to do that ) but the LoRA works just fine at a weight of "0.9" or more/less but might require tuning based on the model you're using it on. Works great on Any V4.5 and with other Character/Style loras, or on any anime model out there.

(SMALL DISCLAIMER)

Using WD Vae might make it end up looking too oversaturated so I'd recommend using AnythingV3 or AnyV4 vae.

Please enjoy and consider supporting me.

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)