Text-to-Video within less than 1 minute using Google Colab

Описание

Text-to-video is a generative diffusion model with 1.7b parameters which inputs a description and returns a video that matches it. Available in Hugging Face. Can simply use it in Google Colab without fancy GPUs. Will give the video within less than a minute. Room for improvement, but looks promising.

Hugging Face model card - https://huggingface.co/damo-vilab/text-to-video-ms-1.7b
Notebook - https://colab.research.google.com #scrollTo=CFmTs4ftecDU&fileId=https%3A//huggingface.co/multimodalart/diffusers_text_to_video/blob/main/Text_to_Video_with_Diffusers.ipynb

Thank you for watching, make sure to subscribe!

Buy me a coffee to show support https://www.buymeacoffee.com/geekavenueyt

#text2vide #chatgpt #generativeai #huggingface #googlecolab