🖼️ Image & Visual (AI Art)

PDF Viewer

📁 Image & Visual (AI Art) 👤 Contributed by @f 🗓️ Updated
The prompt
Create a web-based PDF viewer using HTML5, CSS3, JavaScript and PDF.js. Build a clean interface with intuitive navigation controls. Implement page navigation with thumbnails and outline view. Add text search with result highlighting. Include zoom and fit-to-width/height controls. Implement text selection and copying. Add annotation tools including highlights, notes, and drawing. Support document rotation and presentation mode. Include print functionality with options. Create a responsive design that works on all devices. Add document properties and metadata display.

Example outputs

Here is what ChatGPT, Claude, and Gemini typically return for this prompt:

🚀 ChatGPT

I'll help you create a comprehensive PDF viewer! Here's a complete implementation using PDF.js with a modern interface. The viewer includes a navigation sidebar with thumbnail previews and document outline, zoom controls (25%-400%), text search with highlighted results across all pages, and annotation tools for highlighting and adding notes. I've implemented rotation, fullscreen presentation mode, and responsive design that adapts to mobile devices, along with a print dialog and metadata viewer for document properties.

✨ Claude

I can help you build this PDF viewer, though I should note that a full implementation would be quite extensive. I'll provide the core structure using PDF.js for rendering, a responsive layout with sidebar navigation, and implement the key features like search, zoom, and basic annotations. For production use, you'd want to add error handling, test across browsers thoroughly, and consider performance optimization for large PDFs—PDF.js can be memory-intensive with complex documents.

💎 Gemini

Here's a web-based PDF viewer implementation using Mozilla's PDF.js library (v3.11). The code includes a dual-pane interface with thumbnail sidebar, text search using PDF.js's TextLayer API for highlighting matches, zoom controls (fit-width, fit-height, custom percentages), and Canvas-based annotation overlays. The viewer supports touch gestures for mobile, implements Web Print API for printing, and extracts metadata using PDFDocumentProxy.getMetadata(). Total implementation is approximately 800 lines across HTML/CSS/JS files.

How to use this prompt

Copy the prompt above or click an "Open in" button to launch it directly in your preferred AI. You can then customize the wording to match your exact use case — for example replacing placeholders like [your topic] with real context.

Which AI model works best

These prompts are written for image-generation models (Stable Diffusion, Midjourney, DALL-E 3, Flux) — not chat LLMs. Copy them into your image tool. Midjourney v7 excels at photorealistic portraits; Stable Diffusion 3.5 is the best for fine-tuning and custom checkpoints; DALL-E 3 integrates seamlessly with ChatGPT.

How to customize this prompt

Keep the style descriptors and lighting keywords — these are what make the output consistent. Change the subject, background, and pose freely. Add or remove quality modifiers like "hyper-detailed", "cinematic lighting", "35mm film". For Stable Diffusion, use weight syntax: (keyword:1.3) to emphasize.

Common use cases

  • Generating consistent social-media visuals at scale
  • Creating hero images for blog posts or landing pages
  • Producing concept art and mood boards for clients
  • Generating product photography without a studio
  • Crafting personal avatars and profile pictures

Variations

Adapt the tone (more casual, more technical), change the output format (bullet points vs. paragraphs), or add constraints (word limits, target audience).

Related prompts