update_checkpoint

README.md

@@ -5,11 +5,11 @@ pipeline_tag: text-to-video
 
 The original repo is [here](https://modelscope.cn/models/damo/text-to-video-synthesis/summary). 
 
-**We Are Hiring!** (Based in Beijing / Hangzhou, China.)
+We Are Hiring! (Based on Beijing / Hangzhou, China.)
 
 If you're looking for an exciting challenge and the opportunity to work with cutting-edge technologies in AIGC and large-scale pretraining, then we are the place for you. We are looking for talented, motivated and creative individuals to join our team. If you are interested, please send your CV to us.
 
-EMAIL: yingya.zyy@alibaba-inc.com
+EMAIL: wangjiuniu.wjn@alibaba-inc.com
 
 This model is based on a multi-stage text-to-video generation diffusion model, which inputs a description text and returns a video that matches the text description. Only English input is supported.
 
@@ -25,17 +25,14 @@ This model has a wide range of applications and can reason and generate videos b
 
 ## How to use
 
- 
-The model has been launched on [ModelScope Studio](https://modelscope.cn/studios/damo/text-to-video-synthesis/summary) and [huggingface](https://huggingface.co/spaces/damo-vilab/modelscope-text-to-video-synthesis), you can experience it directly; you can also refer to [Colab page](https://colab.research.google.com/drive/1uW1ZqswkQ9Z9bp5Nbo5z59cAn7I0hE6R?usp=sharing#scrollTo=bSluBq99ObSk) to build it yourself.
-In order to facilitate the experience of the model, users can refer to the [Aliyun Notebook Tutorial](https://modelscope.cn/headlines/detail/26) to quickly develop this Text-to-Video model.
-
-This demo requires about 16GB CPU RAM and 16GB GPU RAM. Under the ModelScope framework, the current model can be used by calling a simple Pipeline, where the input must be in dictionary format, the legal key value is 'text', and the content is a short text. This model currently only supports inference on the GPU. Enter specific code examples as follows:
+Under the ModelScope framework, the current model can be used by calling a simple Pipeline, where the input must be in dictionary format, the legal key value is 'text', and the content is a short text. This model currently only supports inference on the GPU. Enter specific code examples as follows:
 
+For Colab usage, you can view [this webpage](https://colab.research.google.com/drive/1uW1ZqswkQ9Z9bp5Nbo5z59cAn7I0hE6R?usp=sharing).
 
 ### Operating environment (Python Package)
 
 ```
-pip install modelscope==1.4.2
+pip install git+https://github.com/modelscope/modelscope.git 
 pip install open_clip_torch
 pip install pytorch-lightning
 ```
@@ -85,15 +82,3 @@ The output mp4 file can be viewed by [VLC media player](https://www.videolan.org
 ## Training data
 
 The training data includes [LAION5B](https://huggingface.co/datasets/laion/laion2B-en), [ImageNet](https://www.image-net.org/), [Webvid](https://m-bain.github.io/webvid-dataset/) and other public datasets. Image and video filtering is performed after pre-training such as aesthetic score, watermark score, and deduplication.
-
-## Citation
-
-```bibtex
-    @InProceedings{VideoFusion,
-        author    = {Luo, Zhengxiong and Chen, Dayou and Zhang, Yingya and Huang, Yan and Wang, Liang and Shen, Yujun and Zhao, Deli and Zhou, Jingren and Tan, Tieniu},
-        title     = {VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation},
-        booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
-        month     = {June},
-        year      = {2023}
-    }
-```

text2video_pytorch_model.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e139fb08e50a6c072127d9ecef4fe8e91dbdf24edad23a4e1a7c569f0ca3488
+oid sha256:d9609d02717b799137a97244844ab6df0d1a071568a1d24dcb62d9050f3a24a3
 size 5645549049