yiwuyi/anima-highres-aesthetic-boost

anima-highres-aesthetic-boost

<Gallery />

Model 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&#x2F;NSFW and male&#x2F;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 &quot;high rated Danbooru images&quot;, so there is still a lot of stylistic diversity, and hence the LoRA&#39;s effect is subtle.

Trigger words

You should use None to trigger the image generation.

Source

https://civitai.red/models/2540444/anima-highresaesthetic-boost?modelVersionId=2855073

Credit

https://civitai.red/user/circlestone_labs

Download model

Download them in the Files & versions tab.