What' is this:
These LORA's are for adjusting style of AnimagineXLV3.
It is not meant to make major changes to the style, but can be used for fine adjustments.
How to use:
No trigger word is needed.
The recommended weights vary for each LORA, so please refer to the content of the image for guidance.
It is assumed to be used with positive weights, but it can also be used with negative weights.
Train base model is AnimagineXLV3, so it may not work well with other models.
How was it made::
These LORA's were created by copy machine learning method, and utilize sd-webui-traintrain.
I would be happy if there is anything here that can be of even a little use.
Description
Anime face.
Recommended weight is 1.
FAQ
Comments (5)
Pony version?
"It seems like I can achieve the same thing with this, so I haven't made a pony version.
https://civitai.com/models/264290?modelVersionId=297988
@markwatkin I will attempt it. Thanks.
Given the way these enhancements are generated, they may need updating against Animagine XL 3.1. Anime Face at least makes everything flat, unlike in 3.0.
I'll try remaking it with Animagine 3.1. I forgot how I made it...
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.