Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Concept B: Book 2.0 as a generative and unique visual reading experience #3

Open
truedat101 opened this issue Nov 9, 2024 · 0 comments

Comments

@truedat101
Copy link
Owner

image

This is Yoda-san's concept. The idea is to prompt in text from a book either through OCR or QR code reading of remote text, and kick off a pipeline of text encoding and generative AI to generate assets.

I imagine even a sketchy or hazy version of the gist of a story being generated with each page turn is incredibly engaging.

As a general rule in english, you take the first and last sentence of a paragraph to gather the meaning of a paragraph. Or, we ask the LLM to take the paragraph or a page (context length is an issue... also speed) and give us a summary. From there we need a pipeline

  • 3D asset gen
  • 2d asset gen
  • audio asset gen
  • a textual headline for the scene
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

No branches or pull requests

1 participant