Just a nice girl.

Video blogger, YouTube and Twitch streamer, fashion model

The model is made exclusively for a variety of faces, during generation.

The training was conducted on the CIVITAI website.

125 photos were used.

Sometimes, when using LoRa models, there are still problems with limbs, whereas on a pure DEV model, there are much fewer of them, keep this in mind when generating.

we have to temporarily make early access to the model in order, if possible, to slightly compensate for the BUZZ spent on training.

the model itself has become smaller, and there are more photos in the dataset for training. The model itself is more flexible in generation, but there are several more different problems with generation.