ComfyUI Node: Florence2

Authored by spacepxl

Created

Updated

81 stars

Category

Florence2

Inputs

FLORENCE2 FLORENCE2
image IMAGE
task
  • caption
  • detailed caption
  • more detailed caption
  • object detection
  • dense region caption
  • region proposal
  • caption to phrase grounding
  • referring expression segmentation
  • region to segmentation
  • open vocabulary detection
  • region to category
  • region to description
  • OCR
  • OCR with region
text_input STRING
max_new_tokens INT
num_beams INT
do_sample BOOLEAN
fill_mask BOOLEAN

Outputs

IMAGE

STRING

F_BBOXES

Extension: ComfyUI-Florence-2

a/https://huggingface.co/microsoft/Florence-2-large-ft Large or base model, support for captioning and bbox task modes, more coming soon.

Authored by spacepxl

View Nodes

Run ComfyUI workflows in the Cloud!

No downloads or installs are required. Pay only for active GPU usage, not idle time. No complex setups and dependency issues

Learn more