Integrating training based on the v2 version, built-in VAE, adding role materials from my previous training of LORA, the characters have a slight sense of realism

The model is trained with fusion

Sampling steps: 30+

Sampling method: DPM ++2M Karras or Euler or others

This model is about the anime two-dimensional flat style

Attention

Do not force download this model.

Do not write comments unless you support and love my work.

Wish you a pleasant day.

1. You may not host this model and its derivative versions (such as fusion model versions) on websites/applications intended for earning income or donations. If you need to use this model and its derivative versions for commercial purposes (such as generative services, selling images, publishing images in articles or publications on short video platforms, etc.), please contact me through internal channels;

2. You may not directly sell images generated by this model, unless you have made sufficient manual modifications to the image to be fully recognized as your personal work in a legal sense. If you violate this clause, you will bear all legal consequences personally, and I will not be responsible;

3. You are not allowed to use the model intentionally to create or share illegal or harmful content for dissemination and output. Please abide by ethics and morality, and use this model for positive and constructive purposes.