home/categories/llm-ai/davila7-claude-code-templates-cli-tool-components-skills-ai-research-multimodal-blip-2-skill-md
llm-aidata-ai
blip-2-vision-language
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.
maintainer
davila7
更新日 1/20/2026
スター
17577
フォーク
1576
quick start
Installation and usage
Vision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrieval, or multimodal chat with state-of-the-art zero-shot performance.
インストール
$ install --globalskills.sh
使い方
インストール後、ターミナルで以下のコマンドを実行してこのスキルを使用できます：
skills use blip-2-vision-language