rmokady/clip_prefix_caption

Simple image captioning model using CLIP and GPT-2

Capabilities

Reference Images

Community model (estimated from hardware time)

Name	Type	Description	Default	Constraints
`image`*	string(uri)	Input image	`—`	—
`model`	string	Choose a model	`"coco"`	cococonceptual-captions
`use_beam_search`	boolean	Whether to apply beam search to generate the output text	`false`	—

imagerequiredstring

Input image

modelstring

Choose a model

Default: "coco"

cococonceptual-captions

use_beam_searchboolean

Whether to apply beam search to generate the output text

Default: false

Version: 9a34a6339872Updated: 7/25/20261.7M runs