ComfyUI Node: Recognize Anything Model (RAM)

Authored by Hangover3832

Created 7 months ago

Updated 5 months ago

18 stars

Category

Hangover

Inputs

image IMAGE

model

• ram_swin_large_14m.pth
• ram_plus_swin_large_14m.pth
• tag2text_swin_14m.pth

device

• cpu

spec_tag2text STRING

Outputs

STRING

STRING

STRING

Extension: Recognize Anything Model (RAM) for ComfyUI

This is an image recognition node for ComfyUI based on the RAM++ model from a/xinyu1205. This node outputs a string of tags with all the recognized objects and elements in the image in English or Chinese language. For image tagging and captioning.

Authored by Hangover3832