metadata
license: other
tags:
- anime
- style
Anima Highres/Aesthetic Boost - v1.0 - 2855073
Model Type: LORA
Base Model: Anima
Trigger Words: None
Tags: anime, style
Gallery
 |
 |
 |
 |
Description
Showcase images are base model (left) vs LoRA (right).
This LoRA does two things:
- Allows generating at higher resolutions. 1536 works without any major issues, and even 2048 (4 MP) now works without completely falling apart.
- Slight aesthetic increase toward higher-quality images.
It is trained on 10,000 high rated Danbooru images, with mixed-res training at [512, 1024, 1536] resolutions. The images are sampled to have a more even balance of SFW/NSFW and male/female (because otherwise, selecting on ratings only, you would get almost 100% NSFW female). The aesthetic boost is fairly weak, and is prompt dependent. It is not targeting any particular aesthetic, but simply "high rated Danbooru images", so there is still a lot of stylistic diversity, and hence the LoRA's effect is subtle.
Author: circlestone_labs
Model: CivitAI Model Page
Archive: CivArchive Page