Its video input. from tfa:

Stochastic Similarity Filter reduces processing during video input by minimizing conversion operations when there is little change from the previous frame, thereby alleviating GPU processing load, as shown by the red frame in the above GIF

I think it’s just img2img with a prompt & rcfg scale and no controlnet since theres a GitHub issue about adding controlnet support open at the moment.

So left is the source image and right is the resultant image?

yes. compare to animatediff.