@Max....a practical and achievable DIY strategy might be to aim between the two. Use the leaf blower (or two or even 4 of them) and use a controller to control them (and/or control surfaces or vents) such that you can command motion in any direction like the big one, or maybe have an additional leaf blower or a fan for propulsion like a swamp buggy.
Just make sure not to fill it with eels........ :-)
For a practical hovercraft, (using a rather loose definition of "practical"), a flexible skirt is vital. Apart from increasing the ground clearance, and sealing the airflow, lifting panels can be used for control. Depending on the proportions, pressure, &c., control might be possible simply by titling the platform. Leaking air and Isaac Newton do the job.
I think perl_geek is closest: you need a skirt (like all hovercraft have). But also, I don't think it is cheating to have 4 tiny low-profile wheels spaced 90 degrees apart, to keep the leaning platform from nose-diving and biting into the pavement, thus spilling our Max in a most MAXimum way. By leaning, the leaking air will provide just a bit of thrust, at the expense of altitude on the leading edge (thus the need for the protecting wheel). Want more, just remove the governor (?) if it has one. If it doesn't, then shave the cylinder head to increase the compression; but watch out, it will get very hot, so you will need to adjust the fuel. Oh and by the way, the engine could spit its shaft, so have a metal plate between the engine and you. Just a thought or two.
Drones are, in essence, flying autonomous vehicles. Pros and cons surrounding drones today might well foreshadow the debate over the development of self-driving cars. In the context of a strongly regulated aviation industry, "self-flying" drones pose a fresh challenge. How safe is it to fly drones in different environments? Should drones be required for visual line of sight – as are piloted airplanes? Join EE Times' Junko Yoshida as she moderates a panel of drone experts.