Update README.md

README.md

@@ -62,14 +62,14 @@ Video-GPT is a video self-supervised generative pre-trained model that you can u
 
 Here is the illustrations of Video-GPT's capabilities: 
 - Powerful world modeling capabilities
-![demo](https://github.com/zhuangshaobin/Video-GPT/tree/main/imgs/phys_visual.png)
+![demo](./imgs/phys_visual.png)
 - Based on the pre-trained Video-GPT, we continue training on class to video and text to video tasks, and can achieve better results than training from scratch.
-![demo](https://github.com/zhuangshaobin/Video-GPT/tree/main/imgs/c2v_gen.png)
-![demo](https://github.com/zhuangshaobin/Video-GPT/tree/main/imgs/t2v_gen.png)
+![demo](./imgs/c2v_gen.png)
+![demo](./imgs/t2v_gen.png)
 
 - By fine-tuning with a small amount of data, Video-GPT can also achieve good generalization performance on downstream tasks.
-![demo](https://github.com/zhuangshaobin/Video-GPT/tree/mainimgs/anim.png)
-![demo](https://github.com/zhuangshaobin/Video-GPT/tree/mainimgs/seg.png)
+![demo](./imgs/anim.png)
+![demo](./imgs/seg.png)