Update README.md

README.md

@@ -55,7 +55,8 @@ Using the model to generate content that is cruel to individuals is a misuse of
 ## Training
 
 **Training Data**
-- This version is based on stable-diffusion-xl-base-1.0 and has undergone minor fine-tuning on 80 specially selected images.
+- This version is based on stable-diffusion-xl-base-1.0 and has undergone 12 training steps on 80 specially selected images.
+After which the data set is changed.
 - The current name of the version is "a10".
 (OpenCLIP-ViT/G and CLIP-ViT/L) have not been changed.
 - © All images used in the training model belong to my studio, or have permission from the author to use in the training.