awoo

Signed-off-by: Balazs Horvath <[email protected]>

README.md

@@ -675,7 +675,9 @@ Always set this to match the model's resolution, which in Pony's case it is 1024
 
 ##### `--scale_weight_norms`
 
-⚠️
+[![An AI generated image.](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/tutorial/dropout1.png)](https://huggingface.co/k4d3/yiff_toolkit/resolve/main/static/tutorial/dropout1.png)
+
+Encourages the LoRA to diversify it's training by randomly removing some weights, the network you are training needs to support it though! See [PR#545](https://github.com/kohya-ss/sd-scripts/pull/545) for more details.
 
 ```py
     --scale_weight_norms=1 \
@@ -685,7 +687,7 @@ Always set this to match the model's resolution, which in Pony's case it is 1024
 
 ##### `--no_half_vae`
 
-⚠️
+Disables mixed precision for the SDXL VAE and sets it to `float32`. Very useful if you don't like NaNs.
 
 ```py
     --no_half_vae \