← Back to all generators

j-min/clip-caption-reward

Fine-grained Image Captioning with CLIP Reward

Capabilities

Reference Images

Cost

Community model (estimated from hardware time)

Input Parameters

image required string

Input image.

reward string

Choose a reward criterion.

Default: "clips_grammar"
mle cider clips cider_clips clips_grammar
Version: de37751f7513 Updated: 2/26/2026 296.1K runs