Update README.md

README.md

@@ -1,2 +1,9 @@
-Trained for 2 epochs at 5400 steps on AnythingV3 using images of Evan Stanleys art totaling 140 from her twitter. 
-Most training images were full colored single subject shots but some contained multiple subjects or black and white sketches.
+3 Dreambooth models based on AnythingV3 for the base model and training images from Evan Stanley's twitter.
+
+evan5400 was trained on ~30 images for 5400 steps, use keyword 'sonic person' when prompting
+mobianstrimmed6000 was trained on 100 images for 6000 steps, use keyword 'mobian person' when prompting
+mobianstrimmed12000 was trained on 100 images for 12000 steps, use keyword 'mobian person' when prompting
+
+Current testing shows that mobianstrimmed6000 and evan5400 produce the best quality images, I would recommend starting with one of those two and compare results.
+Apologies for using different keywords between models, I wanted to fully switch over to 'mobian person' but unfortunetaly im not fully conviced even though I used more than
+double the training images, that it is better so I included both models. 6000 seemed like the sweet spot as I have noticed mobianstrimmed12000 doesnt give as consistantly good images as the other two.