Looks like standard DeepDream to me so not really the same thing. In OP they combine pictures while this just apply DeepDream over and over until it looks like that.
Do you know how they get stable videos from DeepDream? I've seen it elsewhere too, but my initial guess would have been that DeepDream would give ridiculous results if you ran it on each frame individually. I expect it's sensitive to tiny differences between frames.
