Greetings, this video is a experiment in using Stable Diffusion for video content.
Stable Diffusion is an Open-Source Text to Image generator that can also do imgtoimg.

I used the deforum extension for the automatic111 webui
https://github.com/deforum-art/deforum-for-automatic1111-webui

Getting the math right to create better video content with deforum is going to take more practice.
I used the following site to help with one of the formulas
https://www.framesync.xyz/

I used realesrgan to upscale which did cause some artifacts, I would have liked to have used SD Upscale to restore details but that would have taken too much time for all 4823 frames of the video.

Prompt examples:
“0”: “A Jedi in a bar, Star Wars, highly detailed, sci-fi”,
“96”: “A wookie in a bar, Star Wars, highly detailed, sci-fi”,
“192”: “C-3PO in a bar, Star Wars, highly detailed, sci-fi”,
“288”: “Beautiful Princess Leia at a bar, Star Wars, highly detailed, sci-fi”,

Music: Cantina Rag by Jackson F. Smith is licensed under a Attribution-NonCommercial-NoDerivatives (aka Music Sharing) 3.0 International License.