Uploaded March 2023 | Updated September 2026, 5 hours ago

---

This video is covering ModelScope's new text-to-video model. More information can be found here: https://modelscope.cn/models/damo/text-to-video-synthesis/summary

Github: huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis

Google Collab (to run online):
colab.research.google.com/drive/1uW1ZqswkQ9Z9bp5Nbo5z59cAn7I0hE6R?usp=sharing#scrollTo=udMLgdRcPuhX

Hugging Face's (to run online):
huggingface.co/spaces/NeuralInternet/modelscope-text-to-video-synthesis
huggingface.co/spaces/damo-vilab/modelscope-text-to-video-synthesis
huggingface.co/spaces/j00bert/modelscope-text-to-video-synthesis

G-Risk (to run locally): grisk.itch.io/text2video-gui-001

or

Automatic1111's Stable Diffusion Web-ui extension: install using "Install from URL" with the github link above! Then make sure all the model files from this branch are in your models folder, in "Models/ModelScope/tz2" : huggingface.co/damo-vilab/modelscope-damo-text-to-video-synthesis/blob/main

If you dont have A1111's Stable Diffusion Web-UI, you can follow this tutorial: youtube.com/watch?v=oTrmgXuc3e8&t=0s

hope this helped!


chapter:
00:00 - Intro
00:40 - Online Method 1: Hugging Face
1:30 - Online 2: Google Collab
1:50 - Online 3:
2:20 - Local Method 1: Grisk G.U.I
3:00 - Local 2: Automatic1111's Web-UI
4:50 - Outro