Image Captioner Block

Generate alt-text captions for images with ViT-GPT2 (Xenova/vit-gpt2-image-captioning, ~230MB) entirely on-device, accumulating results in a gallery (caption as the card label, native per-card delete) with copy-caption-to-clipboard + transi.

Library

LocalMode

Framework

React

Type

block

License

MIT

Dependencies

@localmode/core, @localmode/react, @localmode/transformers, lucide-react

Install

npx shadcn add @localmode/ui/ui/blocks/image-studio/image-captioner

Files

• apps/ui/src/app/blocks/image-studio/image-captioner/image-captioner.tsx
• packages/react/src/index.ts
• packages/core/src/index.ts
• packages/transformers/src/index.ts
• apps/ui/registry/localmode/media-vision/media-dropzone/media-dropzone.tsx
• apps/ui/src/lib/browser-utils.ts
• apps/ui/registry/localmode/lib/utils.ts
• packages/transformers/src/provider.ts

Source

https://github.com/LocalMode-AI/LocalMode

Categories

• File Upload Components
• React File Upload Components
• Tailwind CSS File Upload Components
• Input Components
• React Input Components
• Tailwind CSS Input Components

More from LocalMode

• Audio Classifier Block
• Meeting Assistant Block
• Background Remover Block
• Image Enhancer Block
• Semantic Search Block
• Vector Data Manager Block
• Duplicate Finder Block
• Image Search Block
• Photo Categorizer Block
• Smart Gallery Block
• Object Detector Block
• Prompt Input Attachments