FoodDesert
/

Boring_Embeddings

textual inversion embeddings

image-generation

stable diffusion

Model card Files Files and versions Community

FoodDesert commited on Feb 1

Commit

8fde562

•

1 Parent(s): eed959c

Update README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -111,5 +111,6 @@ To qualitatively illustrate how well the Boring embeddings have learned to impro
 ![Performance on Simple Prompts](comparison.jpg)
 As we can see, putting these embeddings in the negative prompt yields a more delicious burger, a more vibrant and detailed landscape, a prettier pharoah, and a more 3-d-looking aquarium.
 <br>

 ![Performance on Simple Prompts](comparison.jpg)
 As we can see, putting these embeddings in the negative prompt yields a more delicious burger, a more vibrant and detailed landscape, a prettier pharoah, and a more 3-d-looking aquarium.
+Hyperparameters were tuned based on manual evaluations of grids like these.
 <br>