Improve model card and metadata

This PR updates the model card and metadata. The pipeline tag is changed to `text-to-video`, and the `library_name` and `license` are added. Additionally, the model card is improved by adding a link to the paper and restructuring the content.

README.md

@@ -1,40 +1,32 @@
 ---
-pipeline_tag: image-to-video
+pipeline_tag: text-to-video
+library_name: diffusers
+license: mit
 ---
 
-
 # StreamingSVD
 
-
-**[StreamingSVD: Consistent, Dynamic, and Extendable Image-Guided Long Video Generation]()**
+**[StreamingSVD: Consistent, Dynamic, and Extendable Image-Guided Long Video Generation](https://huggingface.co/papers/2403.14773)**
 </br>
-Roberto Henschel,
-Levon Khachatryan,
-Daniil Hayrapetyan,
-Hayk Poghosyan,
-Vahram Tadevosyan,
-Zhangyang Wang, Shant Navasardyan, Humphrey Shi
+Roberto Henschel, Levon Khachatryan, Daniil Hayrapetyan, Hayk Poghosyan, Vahram Tadevosyan, Zhangyang Wang, Shant Navasardyan, Humphrey Shi
 </br>
 
 [Video](https://www.youtube.com/watch?v=md4lp42vOGU) | [Project page](https://streamingt2v.github.io) | [Code](https://github.com/Picsart-AI-Research/StreamingT2V)
 
 
-<p align="center">
-<img src="__assets__/teaser/Streaming_SVD_teaser.jpg" width="800px"/>  
-<br>
-<h2>🔥 Meet StreamingSVD - A StreamingT2V Method</h2>
-<em>  
-StreamingSVD is an advanced autoregressive technique for image-to-video generation, generating long hiqh-quality videos with rich motion dynamics, turning SVD into a long video generator. Our method ensures temporal consistency throughout the video, aligns closely to the input image, and maintains high frame-level image quality. Our demonstrations include successful examples of videos up to 200 frames, spanning 8 seconds, and can be extended for even longer durations.  
+## 🔥 Meet StreamingSVD - A StreamingT2V Method
+
+StreamingSVD is an advanced autoregressive technique for image-to-video generation, generating long high-quality videos with rich motion dynamics, turning SVD into a long video generator. Our method ensures temporal consistency throughout the video, aligns closely to the input image, and maintains high frame-level image quality. Our demonstrations include successful examples of videos up to 200 frames, spanning 8 seconds, and can be extended for even longer durations.  
 The effectiveness of the underlying autoregressive approach is not limited to the specific base model used, indicating that improvements in base models can yield even higher-quality videos. StreamingSVD is part of the StreamingT2V family.
-</em>
-</p>
 
 
 
 ## BibTeX
+
 If you use our work in your research, please cite our publications:
+
 ```
-StreamingSVD paper comming soon.
+StreamingSVD paper coming soon.
 
 @article{henschel2024streamingt2v,
   title={StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text},