Support for Multi-Controlnet, and using separate images for controlnet

[hzhou17]

Thanks for the code, it's been working really well!

But I'd like to have further precision with multi-controlnet. (I am using 3D software to create a video first) So I want to use both Canny and Depth. I'd like to use Canny thru the input video and depth images that I rendered myself. How can I modify the code to do so?