RDBT | Krea 2

RDBT [Krea 2]

Improve anime/art aesthetic a little bit. Better details, lightings, outlines, etc...

Note that: the dataset is big enough, the model was not overfitted and does not have bias. It won't drastically change the image, style and faces. This is a feature, not a bug. It can generalize to almost any art style.

Update log:

v0.1: 1k images, 12 epochs, all default settings, testing.

Sharing merges using this model is not allowed. This "restriction" won't affect anyone. It's only aimed at those who steal others' models to sell.

About the RDBT dataset:

Currently contains 11k handpicked images. High aesthetic illustrations. Zero shiny plastic glossy AI images. All captions are NL from LLM.