First run with creating the video manually using Premier and a free robot TTS but generated images using #stablediffusion

First page of the book text of Atlas Shrugged by Ayn Rand

Need to do other books and check them out

#machinelearning #visualaudiobook #cuda
#books

First run with creating the video manually using Premier and a free robot TTS but generated images using #stablediffusion

First page of the book text of Atlas Shrugged by Ayn Rand

Need to do other books and check them out

#machinelearning #visualaudiobook #stablediffusion
#books

Will update code at https://github.com/dev-burningpixel/visualaudiobook-ml

#dev #opensource #visualaudiobook #machinelearning #github #books

Initial testing with #deepai seems encouraging but I need to research more that I can roll my own.

There are limits to #paid that I might need to go over at some point.

Possibly, after getting this going having it as a learning set for a new #machinelearning model but looking forward to see what more there can be.

Here is paragraph 1, page 1 of Catcher of the Rye for #deepai

2 / 2

#catcherintherye #books #machinelearning #ml #visualaudiobook

What is the future of reading physical #books?

Does anyone want to sit down and read or is a audiobook with #ml generated images in a video running in the background the way forward?

My newest #project will explore using some #paid and #diy #api Text-to-Image #machinelearning model to create visual audiobooks from book text.

First came across this with Do Androids Dream of Sleep but I will use Catcher in the Rye. 1 / 2

#opensource #machinelearning #api #books #audiobook #visualaudiobook