Update README.md

README.md

@@ -1,7 +1,8 @@
 ---
 datasets:
 - opendiffusionai/laion2b-45ish-1120px
-- opendiffusionai/laion2b-en-aesthetic-square-cleaned
+- opendiffusionai/laion2b-squareish-1024px
+- opendiffusionai/laion2b-squareish-1536px
 ---
 
 # What is this?
@@ -22,6 +23,10 @@ Use it like any other SD1.5 model
 
 This is an fp32 model, trained with full fp32 precision, finetuned on a single 4090.
 
-The dataset list isnt QUITE accurate. It was actually trained on a larger squareish laion subset.
-Things of note:
-I used both "WD" and "moondream ai generated captions (yes, I used the same image twice like this.)
+The current version was trained on:
+- opendiffusionai/laion2b-45ish-1120px,moondream captions
+- opendiffusionai/laion2b-45ish-1120px, wd14 captions
+- opendiffusionai/laion2b-squareish-1024px, moondream captions
+- opendiffusionai/laion2b-squareish-1536px, wd14 captions.
+
+The 1024px was a mistake: i meant to use the 1536px. but by the time I noticed it, it was 2 days in, and I thought "what the heck, let it run"