How to partially animate an image

Updated Categorized as Workflow Tagged , , 11 Comments on How to partially animate an image

This workflow uses Stable Diffusion to generate this partially animated AI image in AUTOMATIC1111 with animateDiff and inpainting.

To read this content, become a member of this site

Already a member? Log in here.


By Andrew

Andrew is an experienced engineer with a specialization in Machine Learning and Artificial Intelligence. He is passionate about programming, art, photography, and education. He has a Ph.D. in engineering.


  1. Hi Andrew, I get this error: “IndexError: index 0 is out of bounds for dimension 0 with size 0
    Time taken: 1.3 sec.” Which I found no solution for on google. (At least don’t understand). Is it because I use this text2image model: “realisticVisionV60B1_v20Novae.safetensors [c0d1994c73]” ? My dimensions are width: 512px and height: 768px. Thank you very much for your help.

  2. Great info, as always! Side-question sorta: when I put in your initial prompts and setting, I always end up with TWO girls, both in red dresses, etc. I suspect it’s due to the width of the image vs. height, but not sure how to fix it without changing the dimensions. (And why did you choose 1216×832 as a dimension? Seems counterintuitive to the 512/768 standard).

      1. Yeah, that’s what I ended up doing. But in the workflow it listed 1216×832 for dimensions, so I had entered that. (Under Step 2). Maybe clarify for others? I dunno, maybe I’m just not that smart! 🙂

        Thanks for the reply and keep up the great work!

Leave a comment

Your email address will not be published. Required fields are marked *