Update README.md

README.md

@@ -18,8 +18,9 @@ Example chosen frame of GIF from CLIP
 
 ## Training Details
 
-Stage 1 (0-12k steps) The text encoder was trained along with the UNet at half precision for 15% of the total 8,000 steps (1,200 steps), and then the UNet was trained alone for the rest. I used a polynomial learning rate decay starting at 2e-6 (the default in fast-DreamBooth). "low quality" concatenated onto 1/3 of the prompts.
+Stage 1 (0-8k steps) The text encoder was trained along with the UNet at half precision for 15% of the total 8,000 steps (1,200 steps), and then the UNet was trained alone for the rest. I used a polynomial learning rate decay starting at 2e-6 (the default in fast-DreamBooth). "low quality" concatenated onto 1/3 of the prompts.
 
+Stage 2 (8k-) Text encoder trained 50% of steps, random choice "low quality" "lowres" "jpeg" concatenated onto 10% of prompts, starting at 1e-6 
 
 ## How to use with `diffusers` library (section from [openjourney](https://huggingface.co/openjourney/openjourney))