Gen-3: Experimenting with Reanimation

On Wednesday evening I was thinking about Gen-3’s image-to-video feature, that’s the one that can create a video from a single image. Then I had this strange idea; what if you used it to bring taxidermied animals back to life?

So yesterday afternoon, I headed off to the museum’s taxidermy section and started snapping away with my phone:

Back at the studio, I uploaded the images and ran them through Gen-3 with prompts such as “steady camera shot of live animals behind glass, looking around” and... it worked! Some of the results were a bit funky but after a few reattempts I managed to get a selection of videos together. I sent them onto Rob and he put this together:

Wild, right? It’s crazy we were able to turn this around so quickly, I guess that’s one of the superpowers of generative AI. The quality is a little lacking, Gen-3 only produces videos at 1280x768 currently and there’s “AI weirdness” even in the best videos, but it got the concept across well and was a fun experiment!