ComfyUI Node: LocateAnything Grounding

Authored by alisson-anjos

Created

Updated

16 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Category

LocateAnything

Inputs

model LOCATEANYTHING_MODEL
image IMAGE
task
  • ground_multi
  • ground_single
  • detect
  • ground_text
  • detect_text
  • gui_box
  • gui_point
  • point
  • custom
query STRING
generation_mode
  • hybrid
  • fast
  • slow
max_new_tokens INT
temperature FLOAT
top_p FLOAT
top_k INT
repetition_penalty FLOAT
point_radius INT
mask_grow INT
mask_blur FLOAT
overlay_color STRING
overlay_opacity FLOAT
seed INT
verbose BOOLEAN

Outputs

STRING

STRING

IMAGE

MASK

IMAGE

Extension: ComfyUI-LocateAnything

ComfyUI nodes for NVIDIA LocateAnything-3B visual grounding, detection, text localization, GUI grounding, and pointing.

Authored by alisson-anjos

Looking for a different node?

More nodes in ComfyUI-LocateAnything

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Learn more