Update README.md

README.md

@@ -63,13 +63,13 @@ The distribution of timestep t sampled during grads accumulation is very importa
 For this merge, I gathered 10K random danbooru images from the danbooru2023 dataset (https://huggingface.co/datasets/KBlueLeaf/danbooru2023-metadata-database/tree/main), each with at least 1024^2 pixels (not necessarily square). For NoobAI, following the guidance from the readme on their huggingface, the prompt followed the format:
 
 ```
-masterpiece, best quality, newest, absurdres, highres, safe, <caption>
+masterpiece, best quality, newest, absurdres, highres, safe, <ordered danbooru tags>
 ```
 
 and following the guidance from the readme of the huggingface release for animagine, animagine prompts follow this format:
 
 ```
-<caption>, masterpiece, high score, great score, absurdres
+<ordered danbooru tags>, masterpiece, high score, great score, absurdres
 ```
 
 The prompts are then prepended for half of the dataset by a random artist following the distribution of artists in the Danbooru image board (only including users that were trained on, those that have a larger catalogue get more weight). In particular, at each gradient accumulation step, we either prepend an artist tag to the prompt of NoobAI (for even iterations) or that of Animagine (for odd iterations) but never both at the same time.