images/examples

README.md

@@ -12,6 +12,8 @@ inference: true
 
 # sdxl-wrong-lora
 
+![](img/header.webp)
+
 A LoRA for SDXL 1.0 Base which improves output image quality after loading it and using `wrong` as a negative prompt during inference.
 
 Benefits of using this LoRA:
@@ -21,7 +23,7 @@ Benefits of using this LoRA:
 - Higher sharpness for blurry/background objects
 - Better at anatomically-correct hands
 - Less likely to have random artifacts
-- Appears to allow the model to follow the input prompt with a more expected behavior
+- Appears to allow the model to follow the input prompt with a more expected behavior, particularly with prompt weighting such as the [Compel](https://github.com/damian0815/compel) syntax.
 
 ## Usage
 
@@ -58,6 +60,18 @@ Left is the base model output (no LoRA) + refiner, right is base + LoRA and refi
 
 ![](img/example1.webp)
 
+`pepperoni pizza in the shape of a heart, hyperrealistic award-winning professional food photography` (cfg = 13, seed = 75789081)
+
+![](img/example2.webp)
+
+`presidential painting of realistic human Spongebob Squarepants wearing a suit, (oil on canvas)+++++` (cfg = 13, seed = 85588026)
+
+![](img/example3.webp)
+
+`San Francisco panorama attacked by (one massive kitten)++++, hyperrealistic award-winning photo by the Associated Press` (cfg = 13, seed = 45454868)
+
+![](img/example4.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.