Update README.md

README.md

@@ -23,7 +23,7 @@ _I've found interesting the output in the img2img generation. You can see the re
   _prompt and settings used: **[person] in dbluth style** | **Steps: 30 - denoising stregth around 50/70 but you can play around with settings**_
   
 --
-This model was trained with Dreambooth training by TheLastBen, using 64 images at 6400 steps with 25% of text encoder.
+This model was trained with Dreambooth training by TheLastBen, using 40 images at 8000 steps with 20% of text encoder for each model and then merged in a single one with Automatic1111 webui checkpoint merger.
 --
 ## License
 This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.