Skip to content

Conversation

ishan0102
Copy link

Storybook Generation

Overview

Storybook generation involves generating a video from text. This workflow has the following steps:

  • takes text as input
  • splits text into sentences
  • calls StableDiffusionWalker on pairs of sentences
  • adds captions to generated video clips
  • stitches video clips together

This allows a user to visualize a paragraph of writing with subtitles. In the future, this could be improved by having an LLM generate prompts from sentences, to make the StableDiffusionWalker output better.

Example

Prompt

Once upon a time, there was a small bird named Poppy. Poppy was a curious bird who loved to explore the world around her. One day, as she was flying over the fields, she noticed a beautiful flower in the distance. Poppy flew closer to the flower and was amazed by its vibrant colors and sweet fragrance.

Output

poppy.mp4

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant