Welcome to Anime Changeful XL model
This is a Anime style model, which can also be said to be an base model on SDXL1.0 training, it is currently in the testing phase.
Model is trained using training method similar to Naive AI.
The dataset contains 30,000 images and five major categories, and the model is capable of achieving diverse anime effects.
Currently, the model is still in the process of fine-tuning, so today we are releasing a beta version.
We would like to thank Yidhar and Keruchis for their assistance in the training process.
We hope that this model will have the potential to serve as a base for anime-style images, and we will continue to improve it in the future.
Description
FAQ
Comments (6)
Does this model support booru tags or was it designed for normal prompting?
at least the example images are using booru tags
@chekaaa Did you train the text encoder with booru tags?
I would assume booru prompting as the bio of the model says it was trained on booru images
a portion of the training set is annotated using danbooru, so it is supported
@L_A_X - If you had to guess, what percent of the 30,000 images were danbooru tags?
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.