search

storyicon / comfyui_segment_anything

Based on GroundingDino and SAM, use semantic strings to segment any element in an image. The comfyui version of sd-webui-segment-anything.
Apache License 2.0
676 stars 78 forks source link

The number of images input is not the same as the number output #29

Closed AInseven closed 9 months ago

AInseven commented 9 months ago

hey,I don't konw why, but increase the thresthold may decrease the output number. Maybe this is a bug, or how can I avoid this? Thank you. image

norgeous commented 9 months ago

I think this issue is a duplicate of https://github.com/storyicon/comfyui_segment_anything/issues/25

Perhaps both are related to a recent merge (30 Nov 2023) https://github.com/storyicon/comfyui_segment_anything/pull/24

A possible temporary workaround is to checkout the commit before #24 was merged:

cd ComfyUI/custom_nodes/comfyui_segment_anything
git checkout 906a51f9ef2784cde5ff5162d37d95604cfd46f4

Please let us know if that works!

Note: Updating ComfyUI will "undo" this workaround

AInseven commented 9 months ago

Hey, I've tried it, and it works well. Please let me know if your update is relevant to this issue. Thanks.

norgeous commented 9 months ago

reverted #24 :fist_right: https://github.com/storyicon/comfyui_segment_anything/pull/30

i guess this issue (and duplicate) can be closed now :partying_face: