Tuning inference strength of a controlnet by region

Nobody has claimed this yet.

Is there anyway to turn off or modulate the inference strength of control net in an area of an image, it seems like it shouldnt be too hard to attenuate regionally if we can already tune it globally for the whole picture. This could intuitively be coupled to something like an alpha channel to make it easily drawable (either alpha channel can be appended to annotator or you could allow drawing a seperate alpha channel to combine right before inference). If possible and would allow for alot of powerful controlnet composability since you could nicely mix and match the same controlnet (or another model) to be dominant in certain regions of the image or vice versa.

No file, test, or entry point is named. Start by tracing how global ControlNet inference strength is applied and how annotator data reaches inference, then assess where a regional alpha mask could be combined. Done would mean supporting independently modulated ControlNet strength across image regions, with a drawable or appended alpha-channel workflow.

Written by the indexing model from the issue text.