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.
Crafting the Visual Identity for Elichi Coffee | Case Study
For Elichi, the goal was to build a brand identity that captures the ritual of craft coffee. The visual direction balances modern simplicity with a warm, sensory feel—creating a clean yet inviting identity across every touchpoint.
Design Highlights:
Custom Typography: Paired clean, modern letterforms with subtle editorial accents to establish an elevated, boutique feel.
Packaging & Collateral: Used generous white space and structured layout grids so the physical packaging feels premium in hand.
Palette & Materials: Blended deep, roasted tones with soft, muted neutrals to reflect the warmth of the space and the richness of the brew.
I’d love to get your feedback on this direction:
How does the balance between modern typography and warm tones feel to you?
Does the packaging strike the right balance between minimal and welcoming?