Baguette-Anime XL is a model that I created based on images which suited my tastes before anything else.

Trained on more that 45K images, this is the first version of a model that I want to maintain and improve in the long run.

As it is my first ever model, I still have a lot to learn and improve, but this is a first iteration that I am proud of since I find the results quite satisfactory.

Important keywords :

This model was trained to be able to recognize danbooru tags.
Since the dataset was still relatively "small", there are some tags that the AI didn't understand well, or didn't see at all.

In addition to common danbooru tags, there are a total of four "special" keywords that the model was trained on :

• bad quality & worst quality : Works that the AI was trained on to not reproduce, because of distorted limbs, or because the image didn't suit my tastes

• best quality & masterpiece : Works from which I wanted the AI to learn the most

As you can see in the exemple images, I use these 4 keywords everytime.

Warning : The masterpiece keywords affects the image's composition, while best quality seem to only impact the details and colors of the image.

Roadmap :

• Polish the training dataset, add more different tags

• Make the model able to recognize characters by their name

• Reduce the "oil painting" style in favor of a more anime style

• Improve the NSFW capabilities of the model, that are quite lacking at the moment

I will gladly accept any feedback about this model, to improve it even more in the future !