ComfyUI Node: š¾MiaoshouAI Caption Analyzer (Beta)
Category
MiaoshouAI Tagger
Inputs
analyze STRING
subject_index INT
camera_angle BOOLEAN
art_style BOOLEAN
location BOOLEAN
text BOOLEAN
distance_to_camera BOOLEAN
background BOOLEAN
position_in_image BOOLEAN
gender BOOLEAN
age BOOLEAN
hair_style BOOLEAN
hair_color BOOLEAN
facial_expression BOOLEAN
eye_direction BOOLEAN
facing_direction BOOLEAN
race BOOLEAN
ear BOOLEAN
expression BOOLEAN
body BOOLEAN
accessory BOOLEAN
pants BOOLEAN
clothing BOOLEAN
shoes BOOLEAN
action BOOLEAN
Outputs
STRING
Extension: ComfyUI-Miaoshouai-Tagger
Nodes to use Florence2 VLM for image tagging and captioning
Authored by miaoshouai
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