Models & Releases

Stop wasting your limited ChatGPT image uploads. I built a free tool that merges your clipboard images into a single smart grid before you upload them.

Free tool bypasses ChatGPT's image upload limit by stitching 9 clipboard images into a single smart grid.

Deep Dive

Developer Eul45 has released AI Upload Merger, a free and open-source Chrome extension designed to circumvent a common frustration for ChatGPT power users: the platform's restrictive image upload limits. The tool addresses the need to provide multiple visual references—such as screenshots, code snippets, or diagrams—by allowing users to paste up to nine images directly from their clipboard. It then intelligently arranges them into a single, cohesive grid image, preserving original aspect ratios to ensure AI vision models like GPT-4V can interpret the context accurately.

Once the grid is assembled, a single click on "Upload to Page" injects the composite image directly into the ChatGPT interface. This process effectively multiplies the visual context provided per interaction by ninefold while consuming only one of the user's limited upload tokens. The extension eliminates the manual, time-consuming step of using external image editors to stitch photos together, creating a seamless bridge between a user's clipboard and their AI assistant. As an open-source project hosted on GitHub, it offers transparency and the potential for community-driven improvements, positioning itself as a essential utility for developers, researchers, and professionals who rely on multimodal AI analysis.

Key Points
  • Merges up to 9 clipboard images into a single, aspect-ratio-perfect grid for ChatGPT.
  • Consumes only 1 upload token to provide 9x the visual context for AI vision models.
  • 100% free, open-source Chrome extension that auto-injects the final image into the chat.

Why It Matters

Dramatically improves efficiency for professionals using AI vision, turning a multi-step manual process into a one-click workflow.