望图生义(FuseCapImageCaptioning)

FuseCap: Leveraging Large Language Models for Enriched Fused Image Captions. A framework designed to generate semantically rich image captions.

使用

https://openi.pcl.ac.cn/cubeai-model-zoo/hfFuseCapImage_Captioning

模型来源

https://hf-mirror.com/noamrot/FuseCapImageCaptioning