Type | |
Stats | 3,215 15,930 159 |
Reviews | (489) |
Published | Mar 9, 2023 |
Base Model | |
Hash | AutoV2 EFDE6B673C |
This is a micro-LoRa to recreate the style of Andava.
I suggest using this LoRA at 0.9-1.0 weight for best results.
This LoRA was trained on 400 sfw and nsfw pictures with NAI. All examples images were generated on AOM2 and OrangeMix VAE.
I suggest using this LoRA at 0.7-1.0 weight when using with other LoRAs or Characters. (Just play around with it.)
This LoRA is amazing at close-ups, upper body and cowboy shots. It will get a little finnicky once trying to do full body.
Known Issues
It struggles with eyes occasionally but if you upscale, you fix that problem.
Sometimes it won't generate the correct color clothes (ex. Black Shirt will generate a white shirt) sometimes.
All pictures were upscaled using these settings:
Upscaler: Fatal-Anime 4x
Hires. Steps: 25
Denoising Strength: 0.5
Upscale by 1.5 (768x768)
Embeds and LoRAs Used
Marnie, Giovanna, Ryuuko, Toga Himiko, Ragyo, Yohana (OC)
Follow me on Twitter for updates- https://twitter.com/TrueHeroBang
Support - https://ko-fi.com/ekune