Update readme to include citation and correct code snippet

README.md

@@ -26,7 +26,7 @@ This model is meant for research purposes. Please look at the [model limitations
 
 ## Use cases
 
-This model has a wide range of applications, and can reason and generate videos based on arbitrary English text descriptions. 
+This model has a wide range of applications and can reason and generate videos based on arbitrary English text descriptions.
 
 ## Usage 
 
@@ -96,7 +96,7 @@ pipe.enable_model_cpu_offload()
 pipe.enable_vae_slicing()
 
 # generate
-prompt = Spiderman is surfing. Darth Vader is also surfing and following Spiderman"
+prompt = "Spiderman is surfing. Darth Vader is also surfing and following Spiderman"
 video_frames = pipe(prompt, num_inference_steps=25, num_frames=200).frames
 
 # convent to video
@@ -130,3 +130,15 @@ The training data includes [LAION5B](https://huggingface.co/datasets/laion/laion
 
 _(Part of this model card has been taken from [here](https://huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis))_
 
+## Citation
+
+```
+@misc{luo2023videofusion,
+      title={VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation}, 
+      author={Zhengxiong Luo and Dayou Chen and Yingya Zhang and Yan Huang and Liang Wang and Yujun Shen and Deli Zhao and Jingren Zhou and Tieniu Tan},
+      year={2023},
+      eprint={2303.08320},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```