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
Back to feedPost
AI CHARACTER IDENTITY DEVELOPMENT
One character. Multiple worlds.
This project shows how a consistent AI-generated character can be adapted across different visual environments while maintaining recognizability, personality and visual identity.
From lifestyle and urban scenes to luxury and tactical storytelling, the goal was to build a flexible character system suitable for social media, music branding, digital campaigns and short-form video content.
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
Related posts
AFTERCUBE — AI Visual Worlds From Raw Ideas
For the Google Stitch Challenge, I created AFTERCUBE — a dark cinematic AI visual studio that turns raw ideas into website concepts, brand systems, motion direction, and immersive digital worlds.
The idea was simple:
What if one rough prompt could become a complete visual direction?
Not just a layout.
Not just a dashboard.
A full world.
AFTERCUBE is designed as a premium creative engine where users can start with a raw idea and generate cinematic website concepts, visual identity direction, interface systems, brand atmospheres, featured world concepts, and motion-ready digital experiences.
The final landing page tells a clear story:
Raw idea → visual engine → generated worlds → start creating
Process
I spent around [add hours here] hours exploring, designing, breaking, rebuilding, and refining this concept.
This was not a one-shot design. I went through 20+ iterations before finding the final direction.
Some early versions felt too much like generic SaaS dashboards. Some sections looked like separate websites instead of one continuous experience. A few visual directions were too cluttered, too flat, or not premium enough.
So I kept stripping things back and rebuilding around one stronger visual language:
dark cinematic background
burnt-orange energy
oversized editorial typography
3D character and engine visuals
subtle grid texture
premium Framer-style spacing
animated interactions
strong section rhythm
The biggest challenge was keeping the page consistent while moving from hero to product explanation to showcase sections. I wanted the whole page to feel like one visual world, not random screens stitched together.
How I used Stitch
I used Stitch to rapidly explore different layouts, test visual directions, refine the brand system, and push the final landing page into a more polished prototype direction.
The workflow included:
Exploring multiple concepts and brand names
Testing different dark visual systems
Locking the final direction around AFTERCUBE
Building the cinematic hero section
Creating the Visual Engine section
Adding Featured Worlds as generated concept examples
Creating a final prompt-driven CTA
Adding motion ideas, hover states, glow interactions, and scroll animation direction
What I focused on
My goal was not to create another generic AI landing page.
I focused on:
strong first impression
cinematic art direction
bold typography
premium dark UI
orange energy system
clear product storytelling
interactive motion
visual consistency
a page that feels like a real creative AI product
Future direction
If I had more time, I would expand AFTERCUBE into a deeper product prototype with:
a full AI generation flow
additional inner product pages
more generated world examples
more custom 3D elements
animated world-building states
a detailed brand system page
export screens for Framer, Figma, and campaign assets
interactive prompt-to-world transitions
This version focuses on the core brand, landing page, and product story first. The next step would be turning it into a fuller interactive product experience.
Feedback on Stitch
Stitch was useful for fast ideation and visual exploration. It helped me test multiple directions quickly and move from rough concept to polished landing page much faster than starting from a blank canvas.
The hardest part was maintaining consistency across sections. Some outputs looked like separate pages, so I had to keep refining prompts around continuity, layout rhythm, spacing, and brand discipline.
Overall, Stitch was powerful for exploration, but the best results came from treating it like a creative partner — testing, correcting, refining, and pushing the design direction intentionally.
Final concept
AFTERCUBE is an AI visual studio for turning rough creative thoughts into cinematic digital worlds.
One prompt.
One engine.
A complete visual world.
premium
A brand system built around ideas needed images that could hold abstract thinking without turning literal. So I went looking for dreamlike spaces: small worlds a concept could live inside, recognisable as a family but never quite repeating.
Reve made the exploring genuinely fun, and most of the work was in the nipping and tucking, chasing the small details until everything clicked.
Love this!
1. Project Link
https://stitch.withgoogle.com/projects/9509844389363739472
website link
https://rupendrajnv.github.io/stitch/
----------
What I built:
A cinematic Web3 fintech landing page for a fictional startup called Fluxora — featuring a full-screen AI character video background, glassmorphism stat cards with animated count-ups, a custom cursor, scroll-triggered reveals, and a deep navy-blue color system. The experience is designed to feel alive from the first second — motion-forward, conversion-focused, and premium.
🔧 How I Used Stitch
I came to Stitch with a clear creative direction and one asset — an AI-generated character video from Kling. I prompted Stitch to build a full landing page around it: cinematic overlay system, glassmorphism UI components, animated statistics, and a partner bar. Stitch generated the entire interface in one pass, and I used in-place AI edits to refine the color theme from red to a clean navy-blue system and tighten the typography hierarchy. The native motion and animation support let me get scroll-triggered reveals and count-up animations without writing a single line of JS manually.
💬 Feedback on Stitch
Stitch's streaming canvas generation is genuinely fast — watching the interface build itself in real time made iteration feel low-friction. The in-place edit workflow (prompt + point-and-click) was the standout feature for me. Being able to say "change the overlay to blue" and see it apply contextually — without rebuilding from scratch — is exactly how AI tools should work in a design workflow. The motion and animation support on the HTML canvas is a real differentiator. For someone coming from a video and motion design background, having that baked in natively felt natural. Would love deeper control over animation easing curves in a future update.
--
Post on X
https://x.com/techupd59581740/status/2060750926793879905?s=20
sleek 👌🏽
Trending
Claude
Claude has entered the design space. How are you using Claude Design?
Contra University
Learn from expert creatives how to earn more using next-gen AI tools.
creativeaiflow
Creative AI workflows are evolving. What tools do you use, and what are their strengths and weaknesses?
portfolioreview
The best portfolios tell a story, not just show a grid. Share yours for feedback.
freelancerlife
Freelancer life is wins, pivots, and everything in between. What’s yours right now?