ComfyUI Node: Florence2 Describe Image 🐑

Authored by MieMieeeee

Created

Updated

53 stars

Category

🐑 Florence2Caption

Inputs

model MIE_FLORENCE2_MODEL
image IMAGE
task
  • caption
  • detailed_caption
  • more_detailed_caption
  • tags
  • mixed
  • extra_mixed
  • analyze
seed INT
max_new_tokens INT
num_beams INT
do_sample BOOLEAN
keep_model_loaded BOOLEAN

Outputs

STRING

Extension: ComfyUI_CaptionThis

Describe a single image or all images in a directory using models such as Janus Pro, Florence2, or JoyCaption (testing), with a particular focus on building datasets for training LoRA.

Authored by MieMieeeee

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