The category default for AI products is dark backgrounds and gradient glow. Heron's audience is architects, so we built the visual system out of their working material instead.

Everything on the site is drawn as architectural line work. Plans, elevations, dimension strings, and annotation boxes styled like redline mark-ups, each one holding a genuine code reference rather than lorem text.

The system does two jobs. It reads as native to someone who spends their day inside Revit, and it supports the product story, because Heron works inside the drawing rather than beside it.

Super thoughtful! 👍

What happens when you take a hero frame from an AI-generated video and push it back into an image edit model?

This weekend I took a still from a recent Seedance 2.5 piece I made —depicting a solo mountaineer in a harsh alpine environment — and ran it through Midjourney's new v8.2 edit model to see how far I could iterate on a single frame without regenerating from scratch.

Tested wardrobe swaps, environment shifts, and style transfers.

Video walkthrough of the process coming in a separate post.

This looks cool