Post #3222285
2026-03-02 08:44 UTC
@felwert@fedihum.org @sarahalang@fedihum.org we've been using SAM2 in https://immarkus.xmarkus.org. Worked ok for us. SAM3 is something I'd like to try. But project didn't have the time/resources yet.
Overall, I guess it depends on:
i) your expectations :-)
ii) the material you're working with (obviously)
iii) whether you're using the prompted or unprompted mode (we're only using prompted in IMMARKUS)
iv) most importantly, the model size/variant
In our case, we used the "tiny" variant only, because that fits entirely into the browser – no server-side embedding needed. The larger variants would give better results I'm sure. (But then you'd need a separate server component which you need to maintain, fund, keep running... not DH-friendly as we know ;-)
Replies (2)
-
@aboutgeo@hcommons.social 2026-03-02 08:51
@felwert@fedihum.org @sarahalang@fedihum.org FWIW the IMMARKUS docs have a small screencast demo here: https://github.com/rsimon/immarkus/wiki/05-Annotating-Images#auto-select (But you can also just try it yourself by loading your own images into https://immarkus.xmarkus.org)
-
@sarahalang@fedihum.org 2026-03-02 13:48
@aboutgeo@hcommons.social @felwert@fedihum.org Thanks, that's really helpful!