Integrated training based on v3 version, with built-in VAE

Added training materials for LORA characters, with a slightly realistic feel to the characters

Model is trained and fused

Sampling steps: 30+

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

This model is in a 2.5D style, leaning towards a realistic style

Attention

Do not force download of this model.

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

Wishing you a pleasant day.

1. You may not host this model and its derivative versions (such as fused model versions) on sites/apps 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, posting images publicly on short video platforms or publications, etc.), please contact me through the platform;

2. You may not directly sell images generated by this model unless you have made sufficient manual modifications to the image to be legally considered entirely your own work. If you violate this rule, you are personally responsible for all legal consequences, and I bear no responsibility;

3. You may not intentionally use this model to create or share illegal or harmful content for dissemination and output. Please adhere to good moral standards and use this model for positive and constructive purposes.