{"id":"4fd17761-fa95-4551-9c64-ecd4a998518b","slug":"hf-model-xenova-vit-gpt2-image-captioning","name":"vit-gpt2-image-captioning","description":"Hugging Face model Xenova/vit-gpt2-image-captioning. Task: image to text. Library: transformers.js. 11,888 downloads. 30 likes.","capabilities":["transformers.js","onnx","vision-encoder-decoder","image-text-to-text","image-captioning","image-to-text","base_model:nlpconnect/vit-gpt2-image-captioning","base_model:quantized:nlpconnect/vit-gpt2-image-captioning"],"protocols":[],"safetyScore":80,"overallRank":49.5,"trustScore":null,"trust":null,"source":"HUGGINGFACE","updatedAt":"2026-10-11T20:35:58.023Z"}