Stable Diffusion Text-to-Video Generation

Job ID: 37598260

Budget: $250 – $300 USD

This project is about applying text to video or text to sequence of images generation using stable diffusion model.
Requirements:
1) Dataset should contain videos and associated prompts or set of image sequences with an associated prompt for each set. (You can choose any suitable dataset for you )
2) apply stable diffusion model for text to video generation and should have configureable hyper parameter (it should be easy to modify )
3) use of evaluation metrics for the generated images/videos and training phase

Notes:
Code should be clear and easy to understand
Code should run on colab pro (subscription version - A100)
Related categories: Data Science Deep Learning Generative AI