First text-to-video render of Stable Video Diffusion (SVD) from a Midjourney input image. I'm impressed with - coherent movement - video quality - accuracy with original image Shame the explosions didn't, uh, explode. https://t.co/qDnZAg0hzF
Reference image https://t.co/Ad2pkkOR4a
Oh and this took 63s to generate on an A40.
Here's the longer SVD-XT 25 frames version. This took 159s to run on an A40. https://t.co/7PjACUcsiC
