Title: THE OTHER JULIE - A Cinematic AI Reimagining of a Met Masterpiece Project Overview: Create...Title: THE OTHER JULIE - A Cinematic AI Reimagining of a Met Masterpiece Project Overview: Create...
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Title: THE OTHER JULIE - A Cinematic AI Reimagining of a Met Masterpiece
Project Overview:
Created for the #FLORAMuseum Challenge, this project transforms Élisabeth Louise Vigée Le Brun’s 1787 painting, "Julie Le Brun Looking in a Mirror," into a 7-shot psychological cinematic sequence.
The Inspiration:
The original painting from The Metropolitan Museum of Art plays with the allegorical concept of 'Sight', showing the subject twice. I reimagined this duality to tell the story of a young girl coping with her parents' separation, finding comfort in a mirror reflection that ultimately represents her isolated inner self.
The Process (Built in FLORA):
Instead of simply animating the existing image, I approached this as a production-ready film.
Workflow: Built a complex node-based canvas in FLORA.
Scripting: Used Claude Sonnet 3.5 to act as an AI director, ensuring accurate cinematic continuity, lighting (warm candlelight to daylight transition), and spatial framing.
Generation: Utilized Seedance 2.5 and King 3.0 Pro to maintain strict character consistency and deliver high-fidelity micro-expressions during the conversation with the mirror.
The Reveal: Engineered a seamless match-cut that pulls the viewer out of the live-action narrative and back into the physical painting hanging in The Met.
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.
Experimented a bit today with Krea and image generation for a case study I’m putting together around AI EarPods connected to OpenAI.
The focus has been on creating fashion-forward product imagery and art directing a world that feels specific to the identity, rather than just generating nice-looking AI images.
The trickiest part has been product consistency. Especially getting the EarPods to actually sit snug in the ear. If you’ve worked through this process, you probably know the struggle 😅
Simply telling AI to “make it fit more snug or in the ear” doesn’t always work. It loves to reinterpret the product every time.
Still experimenting, but getting closer. If anyone has found a good workflow for keeping products consistent across AI-generated shoots, I’d love to hear it!
30+ pages, 3 weeks, and honestly one of my favorite projects in a while.
I'd been wanting to design something more tech-driven for a long time, and Gryd, a platform turning construction permit data into intelligence for insurers, lenders, and real estate teams, was exactly that.
Wireframes first, then UI across every page, fully responsive, with animation on the key screens, all built inside the brand the client had already set.