Update README.md

README.md

@@ -1,5 +1,7 @@
 ---
 license: cc-by-nc-4.0
+tags: 
+  - text-to-video
 ---
 
 # show-1-base
@@ -10,7 +12,6 @@ To marry the strength and alleviate the weakness of pixel-based and latent-based
 
 ![](https://showlab.github.io/Show-1/assets/images/method.png)
 
-
 ## Model Details
 
 This is the base model of Show-1 that generates videos with 8 keyframes at a resolution of 64x40. The model is trained from [DeepFloyd/IF-I-L-v1.0](https://huggingface.co/DeepFloyd/IF-I-L-v1.0) on the [WebVid-10M](https://maxbain.com/webvid-dataset/) dataset.
@@ -31,13 +32,13 @@ git clone https://github.com/showlab/Show-1.git
 pip install -r requirements.txt
 ```
 
-Run the following command to generate a video from a text prompt. This will automatically download all the model weights from huggingface. 
+Run the following command to generate a video from a text prompt. By default, this will automatically download all the model weights from huggingface. 
 
 ```bash
 python run_inference.py
 ```
 
-You can also download the weights manually:
+You can also download the weights manually and change the `pretrained_model_path` in `run_inference.py` to run the inference. 
 
 ```bash
 git lfs install
@@ -67,7 +68,6 @@ If you make use of our work, please cite our paper.
 }
 ```
 
-
 ## Model Card Contact
 
 This model card is maintained by [David Junhao Zhang](https://junhaozhang98.github.io/) and [Jay Zhangjie Wu](https://jayzjwu.github.io/). For any questions, please feel free to contact us or open an issue in the repository.