← Back to all generators

rmokady/clip_prefix_caption

Simple image captioning model using CLIP and GPT-2

Capabilities

Reference Images

Cost

Community model (estimated from hardware time)

Input Parameters

image required string

Input image

model string

Choose a model

Default: "coco"
coco conceptual-captions
use_beam_search boolean

Whether to apply beam search to generate the output text

Default: false
Version: 9a34a6339872 Updated: 2/26/2026 1.7M runs