Alternatives that support prompting?

I would love to use SAM because of how great the model is, but for my specific requirements I need to be able to extract the bounding boxes of only one specific object, which is currently impossible due to prompting being unavailable as of now.

Are there any other image segmentation models available right now that do support prompting or any other way to extract specific objects?

The issue does not name a file, test, or concrete change. Start by reviewing the repository's inference examples and example notebooks, then check the available model checkpoints and documented capabilities. Done would require identifying a supported prompting approach or alternative model that can isolate one object's bounding box, with the scope agreed in the issue.

Written by the indexing model from the issue text.