comparing image captioning models
Demo : https://huggingface.co/spaces/nielsr/comparing-captioning-models
GIT/ BLIP/ ViT+GPT2 / CoCaの生成結果を比較できる
https://gyazo.com/11fdeb6cc641b180dd106143df80923d
https://gyazo.com/baf9ed3d7a75a24a1f71404a89b2cc55
#text2prompt