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.
Install
npx skills add davila7/claude-code-templates --skill blip-2-vision-languagenpx skills add davila7/claude-code-templates --skill blip-2-vision-language -a claude-code -gnpx skills add davila7/claude-code-templates --skill blip-2-vision-language -a codex -ggemini skills install https://github.com/davila7/claude-code-templates.git --path cli-tool/components/skills/ai-research/multimodal-blip-2gh skill install davila7/claude-code-templates blip-2-vision-languagegit clone --depth 1 https://github.com/davila7/claude-code-templates /tmp/davila7__claude-code-templates
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/multimodal-blip-2 ~/.claude/skills/blip-2-vision-language # Claude Code
cp -R /tmp/davila7__claude-code-templates/cli-tool/components/skills/ai-research/multimodal-blip-2 ~/.agents/skills/blip-2-vision-language # Codex, Cursor, Gemini CLI, Copilot, OpenCode