Update README.md

README.md

@@ -15,7 +15,7 @@ pipeline_tag: text-to-video
 
 For more information on how to use it, please check [GitHub](https://github.com/mihirp1998/VADER).
 
-This is a checkpoint trained using a reward function combining HPSv2.1 and Aesthetic function with a LoRA rank of 8 for our paper [Video Diffusion Alignment via Reward Gradient](https://vader-vid.github.io/) by 
+This is a checkpoint trained using a reward function combining HPSv2.1 and Aesthetic function with a LoRA rank of 8 on prompts in `assets/chatgpt_custom_instruments.txt` for our paper [Video Diffusion Alignment via Reward Gradient](https://vader-vid.github.io/) by 
 
 Mihir Prabhudesai*, Russell Mendonca*, Zheyang Qin*, Katerina Fragkiadaki, Deepak Pathak.