VERSION 2.0 CHANGES:

• the sensitivity of the model to promt has improved many times, the first version of the model was overtrained

• The size of the model itself has become smaller, with improved picture quality.

• Stylization by Anton Semenov.

• The training was conducted on the CIVITAI website.

• 130 pictures 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.