another example

README.md

@@ -54,7 +54,7 @@ During inference, use `wrong` as the negative prompt.
 
 ## Examples
 
-Left is the base model output (no LoRA) + refiner, right is base + LoRA and refiner. The generations use the same seed.
+**Left image** is the base model output (no LoRA) + refiner, **right image** is base (w/ LoRA) + refiner. Both generations use the same seed.
 
 `realistic human Shrek blogging at a computer workstation, hyperrealistic award-winning photo for vanity fair` (cfg = 13, seed = 56583700)
 
@@ -72,6 +72,10 @@ Left is the base model output (no LoRA) + refiner, right is base + LoRA and refi
 
 ![](img/example4.webp)
 
+`hyperrealistic death metal album cover featuring edgy moody realistic (human Super Mario)++, edgy and moody` (cfg = 13, seed = 30416580)
+
+![](img/example5.webp)
+
 ## Methodology
 
 The methodology and motivation for creating this LoRA is similar to my [wrong SD 2.0 textual inversion embedding](https://huggingface.co/minimaxir/wrong_embedding_sd_2_0) by training on a balanced variety of undesirable outputs, except trained as a LoRA since textual inversion with SDXL is complicated. The base images were generated from SDXL itself, with some prompt weighting to emphasize undesirable attributes for test images.