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

“You’re too expensive. I’ll just use AI.”

I think every designer has heard some version of this by now. 😅

Yes, AI can make something in 30 seconds or even less. But getting an image is very different from knowing what the brand ACTUALLY needs.

The tools are getting faster and more accessible. What still takes experience is knowing what works, what doesn't, what to change, and when to stop.

What do you think clients will value most from designers as AI keeps evolving?

The question is basically: what's the context behind the decision?

AI can generate 100 packaging options. It can't tell you which one makes sense for a brand expanding into a market where soft pink reads very differently than it does back home. Or why the typography from three...