Launched this week
Convly Image-to-Prompt
Reverse-engineer the prompt behind any AI image — free
5 followers
Reverse-engineer the prompt behind any AI image — free
5 followers
Free AI image-to-prompt generator. Upload or paste any image and instantly get a detailed text-to-image prompt, a style breakdown, and ready-to-use Midjourney and Stable Diffusion settings to recreate the look. No sign-up, no watermark, works in 7 languages. It's honest about the limits — you can't recover the exact seed from a finished image, so it gives a close, high-quality estimate. Part of Convly, a site of free AI tools and a live models database.
It would be great if you could let users upload a small batch of reference images at once and blend them into a single prompt, since matching a specific look often takes more than one example.
@sunakphh Great suggestion, Suna — thank you! Blending multiple reference images into one prompt is genuinely useful (one image rarely captures a full style). Adding it to the roadmap — the vision model behind the tool can already accept multiple images, so it's mostly a UI change. If you throw your hardest single image at it today, I'd love to hear how close the prompt gets. 🙏