Update README.md

README.md

@@ -21,7 +21,7 @@ datasets:
 
 ## Fast Anime PromptGen
 
-The main model `pytorch_model.bin` is trained on **80K** anime tags, all with **up_score ≥ 8** and without "greyscale","girls","boys", and "others", fetched from the [Safebooru API endpoint](https://safebooru.donmai.us/posts/random.json). 
+The main model `pytorch_model.bin` is trained on **80K** anime tags, all with **up_score ≥ 8** and without the [blacklisted tags](./blacklist.txt), fetched from the [Safebooru API endpoint](https://safebooru.donmai.us/posts/random.json). 
 I didn't release the V1 model because it only generated gibberish prompts. After trying all means to correct that behavior, I eventually figured that the cause of the gibberish prompts is not from the model or training duration, but rather from the random usernames present in the training data. 
 Here's the complete [prompt preprocessing](./preprocess.py).