This model generates the Woot art style, specifically older works such as those found here https://woot.iiichan.net/ I limited the data to just those with a "hard shading" style without dithering, so it should be more specific. This is different from Woot's more recent work.

Trigger word is @wootart

This is a full checkpoint trained with the same data as the LoRA. The results were pretty great so I'm posting it.

The model has a strong bias towards very round ladies. The model was trained on the Danbooru breast size tags, with a bias towards bigger, but it's recommended to specify this.

Works best at the 1024x1024 resolution (or smaller) due to the dataset. Note that Anima can make 512x512 images.

Another recommended tag is oekaki since Anima independently knows the Oekaki style and so it will accentuate those aspects of the style.