The short answer
Two photos of two different people, one person per photo. Each photo should be head and shoulders, face forward, in even light, with the hair fully visible and no hat. Upload the Suit fighter first and the Barefoot fighter second. Both photos are required: the video cannot start with one. You then choose 720p or 1080p, which cost the same flat rate; the quote in the tool covers the whole 7 seconds.
