minor edits

README.md

@@ -19,6 +19,7 @@ Benefits of using this LoRA:
 - Higher color saturation and vibrance
 - Higher detail in textures/fabrics
 - 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
 
@@ -30,7 +31,10 @@ The LoRA can be loaded using `load_lora_weights` like any other LoRA in `diffuse
 import torch
 from diffusers import DiffusionPipeline, AutoencoderKL
 
-vae = AutoencoderKL.from_pretrained("madebyollin/sdxl-vae-fp16-fix", torch_dtype=torch.float16)
+vae = AutoencoderKL.from_pretrained(
+    "madebyollin/sdxl-vae-fp16-fix",
+    torch_dtype=torch.float16
+)
 base = DiffusionPipeline.from_pretrained(
     "stabilityai/stable-diffusion-xl-base-1.0",
     vae=vae,
@@ -44,7 +48,7 @@ base.load_lora_weights("minimaxir/sdxl-wrong-lora")
 _ = base.to("cuda")
 ```
 
-During inference, use `wrong` as the sole negative prompt.
+During inference, use `wrong` as the negative prompt.
 
 ## Examples
 
@@ -52,9 +56,10 @@ Left is the base model output (no LoRA) + refiner, right is base + LoRA and refi
 
 ## Methodology
 
-The methodology for creating this LoRA is similar to my [wrong SD 2.0 textual inversion embedding](https://huggingface.co/minimaxir/wrong_embedding_sd_2_0), except trained as a LoRA since textual inversion on SDXL is complicated. The base images were generated from SDXL itself.
+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 on SDXL is complicated. The base images were generated from SDXL itself, with some prompt weighting to emphasize undesirable attributes for test images.
 
 ## Notes
 
+- The intuitive way to think about how this LoRA works
 - It's possible to use `not wrong` in the prompt itself but in testing it has no effect.
-- You can use other negative prompts in conjunction with the `wrong` prompt but you may want to weight them.
+- You can use other negative prompts in conjunction with the `wrong` prompt but you may want to weight them appropriately.