Update README.md

README.md

@@ -6,22 +6,22 @@ datasets:
 ---
 
 # What is this?
-This is not a permenantly released model. More like an open alpha release.
+This is not a permenantly released model yet. More like an open alpha work-in-progress.
 
-## Latest: 2025/03/01
+## Latest News: 2025/03/05
 
-XLsd32-dlionb16a8-phase1-LAION-e2.sft
+(Currently up to epoch 7)
 
 SD1.5 base, with the SDXL VAE tacked on, and then retrained to actually WORK.
 
-I think that this has reached parity with existing SD base. I'm going to keep training, but wanted to share what I had so far.
+I think that this has reached parity with existing SD base, for human output. I'm going to keep training, but wanted to share what I had so far.
 
 # How to use
 Use it like any other SD1.5 model
 
 # How it was trained
 
-This is an fp32 model, trained with full fp32 precision, finetuned on a single 4090.
+This is an fp32 model, trained with full fp32 precision, finetuned on a single 4090 (starting from the SD1.5 base + SDXL VAE).
 
 The current version was trained on:
 - opendiffusionai/laion2b-45ish-1120px,moondream captions
@@ -29,7 +29,8 @@ The current version was trained on:
 - 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"
+The 1024px was a mistake: i meant to use the 1536px. the 1024px dataset is 3x as large!!
+But by the time I noticed it, it was 2 days in, and I thought "what the heck, let it run"
 
 
 # Recreating the model