AI Video Producer for Campaigns, UGC & Brand Films
AI Video Producer for Campaigns, UGC & Brand Films
Original Animated Micro-Series — THE THINGS WE CARRY
In a city where humans and monsters live side by side, Spindle runs a small repair shop for things that are not always meant to be repaired.
The pilot follows Tobias Mourn, a quiet, imposing monster who comes to Spindle with a problem he can't explain: his heart hurts, even though there is nothing physically wrong with it.
After trying to fix it himself, Tobias encounters a young woman in the city who looks at him as if she already knows him.
“Dad?”
Tobias doesn't remember her.
But something inside him does.
Each episode follows another unusual repair and the character who brings it through Spindle's shop — gradually revealing the lives, relationships and histories hidden behind the things they want fixed.
At the centre of the series is Tobias and the mystery of what happened to him before he became the person he is now.
I wanted The Things We Carry to feel like a world that already existed before the camera arrived: strange, human, quietly funny, and a little melancholic.
1
597
Making a Fictional AI Vlog Feel Real
A creative experiment exploring how far generative video can go when the goal is to make a fictional vlog feel real — spontaneous, imperfect and believable rather than obviously AI-generated.
The project was inspired by the current wave of speculation around a possible Kanye West visit to Russia, as well as the unexpected viral spread of 'Silver Night' in Kanye West’s voice. Both became starting points for imagining an entirely fictional trip through Saint Petersburg.
The idea was to place a highly recognisable public figure into a completely different cultural and visual environment and explore how naturally the two could coexist on screen. Everyday locations, cultural details, movement and sound became part of the storytelling rather than simply serving as background.
The visual language deliberately moves away from the polished aesthetic often associated with generative AI, experimenting instead with a more naturalistic, vlog-like approach. The character needed to remain consistent across different locations and situations while the footage retained a sense of spontaneity and imperfection.
Created for the SYNTX AI challenge.
3
10
1.4K
One-take cinematic AI film production
This is an FPV drone flight through a city during a solar eclipse.
The camera moves from a crowded square to a football stadium without any cuts or transitions. I wanted to show how people react when something unusual happens, and routine becomes ritual
As the eclipse shadow advances, people who don't know each other start moving in sync — looking up at the same time, adjusting their position together, reacting as one group. The drone follows this rhythm from quiet individual moments in the city to a massive collective gasp in the stadium
Built in CapCut Video Studio with Seedance 2.5.
#contraseedancechallenge #CapCutCPP
35
137
24.3K
AI music video / Creative direction
I guess everyone’s had a chance to play with Seedance 2.5 by now, right?
Here’s what actually stood out to me.
The biggest difference isn’t resolution or motion quality — it’s how well the model holds a visual reference. When I fed it a specific aesthetic — early 2000s digital, raw grain, handheld imperfection — 2.5 preserved the character of it. Camera movement felt stylistically consistent, not just technically correct.
The previous version tended to simplify, smoothing things out toward something more generic.
For this experiment, I used a Charli xcx track as the starting point and built the visual around its energy and aesthetic.
For anyone doing editorial or narrative AI work, that distinction matters a lot. A tool that interprets your reference rather than flattening it changes what’s possible in the creative direction process.
2
9
1.8K
Cinematic AI Director for Brand Films & Commercials
Cinematic AI Director for Brand Films & Commercials
Where AI and Motion Converge.
Where AI and Motion Converge.
AI Photography & Video Content for Brands
AI Photography & Video Content for Brands
AI Video Creator & Creative Director | Script & Prompt Strat
AI Video Creator & Creative Director | Script & Prompt Strat
A movie-style close-up of a vampire holding a melting ice cream in his left hand. He slowly and delicately licks the ice cream to savor its flavor never biting it. His tongue gently touches the soft scoop, as the ice cream is light and airy, meant to be enjoyed only by licking.
A bat rests on his shoulder, calmly watching and leaning closer to sniff the ice cream without interrupting him.
The camera is slightly shaky, creating a natural handheld feel. In the background, the amusement park is alive with movement (no visible people), and the carousel on the left rotates left from the camera’s perspective.
1
69
This photorealistic cinematic portrait explores dominance and mythic elegance.
A platinum-haired woman stands calmly before a massive black dragon, her icy-blue gaze steady and commanding. Dressed in a forest-green corset gown embroidered with black vines, she radiates controlled strength.
The dragon looms behind her, its glowing red eyes and obsidian scales embodying restrained destruction. A stream of fire flows inches from her cheek without touching her symbolising absolute control. Smoke and heat intertwine with her hair as dramatic, high-contrast lighting enhances the apocalyptic cinematic mood.
1
69
This project presents a photorealistic cinematic close-up exploring power, elegance, and dominance through visual duality.
A powerful woman stands in profile beside her massive black dragon, both framed in sharp silhouette against a dark, high-contrast background. Her deep crimson lips and piercing icy-blue eyes contrast with the dragon’s obsidian scales and glowing red gaze, creating a striking balance between beauty and destruction.
Wisps of smoke curl from the dragon’s nostrils, blending seamlessly with her platinum-white hair to add motion and atmospheric tension. Dramatic side lighting sculpts their profiles, enhancing the emotional intensity and mythic scale of the composition.
A bold, high-contrast “Visione Apocalittica” aesthetic reinforces the apocalyptic mood, elevating the scene into a powerful cinematic statement.
1
70
This project explores a high-fantasy cinematic concept set within an enchanted forest environment.
The scene centers on Mavka, portrayed as a powerful yet serene nature spirit. Her flowing green hair, adorned with ethereal blooms, reflects her deep connection to the natural world. Through deliberate visual framing and atmospheric lighting, the composition enhances her majestic presence.
Soft, radiant magical energy swirls around her raised hands, emitting vibrant green and golden particles. The medium low-angle shot reinforces her strength and authority, while dappled sunlight and environmental glow create an immersive, living forest atmosphere.
This project shows my ability to craft immersive AI-driven fantasy visuals that combine storytelling, environmental design, and emotional tone to create captivating cinematic moments.
1
75
Full-Stack & AI Dev | TypeScript, Next.js, React, Node
- $50k+
- Earned
- 5x
- Hired
- 5.0
- Rating
- 137
- Followers
Full-Stack & AI Dev | TypeScript, Next.js, React, Node
Built a little Mac app called Flip, and it somehow went viral on Twitter.
The idea is pretty simple. What if every window on your Mac had a back side where you could keep notes? So I built exactly that.
Flip any window, jot something down, flip back. Your notes stay attached to that window.
No extra apps to switch between.
Built natively for macOS, completely local, and free.
Check it out: https://flip.pylondev.com
Here’s the original tweet:
https://x.com/skimmycat20/status/2096580098506084400
2
3
192
Creative Technologist
Speculative ad brief for DefendUAS. Shifting the needle from basic product animation to high-stakes military storytelling.
Visually contrasting a gritty, hyper-realistic urban terrain with sharp, tactical holographic wireframes to show exactly how a distributed mesh network reclaims the decision window. Using a scene-by-scene strategy in Melius, starting with a master script that fed into storyboards and hero keyframes for total visual continuity across the cinematic clips. This workflow allowed me to lock the moody tactical aesthetic before generating the final video scenes, deep-voice narration, and orchestral score. Everything is laid out from left to right, showing the journey from concept to final assets. The project screenshots/canvas video are in the comments.
1
3
711
A budding film director is told her ideas are too ambitious and impossible to produce. Working alone in a small apartment, she turns to Luma Dream Machine and begins creating the scenes she was once denied. In seconds, her world expands into cinematic visuals that defy cost, risk, and limitation. What was once rejected becomes real, proving that imagination no longer needs permission.
2
6
759
- The Archivist of Tomorrow -
A quiet, introspective short film that follows the Archivist, a historian from the year 2140 who preserves humanity’s most meaningful memories. As he moves through layers of archival flashbacks, he uncovers a history of how humans and AI evolved together.
2
2
515
This project involved a comprehensive archival reconstruction aimed at distilling the legacy of Harvey Mackay into a series of high-impact sizzle reels. The workflow required a deep immersion into a diverse repository of assets, including magazine prints, book covers, and raw footage reels, to identify the most resonant narrative moments. The technical approach balanced traditional restoration with cutting-edge synthesis: colour correcting legacy footage and applying an intentional analogue aesthetic, while strategically integrating VEO 3.1 and Grok Imagine to bridge visual gaps. By layering refined sound design and exploratory revisions across four distinct durations, the final deliverables translate a vast professional history into a modern, energetic visual identity that both informs and excites.
0
559
Fractional CTO / AI Specialist Award Winning AI Engineer
- $5k+
- Earned
- 1x
- Hired
- 11
- Followers
Fractional CTO / AI Specialist Award Winning AI Engineer
I created THE TABLE because the most uncomfortable human moments deserve to be witnessed without the mercy of a camera cut.
We have all seen dramatic cafe encounters on film, but they are usually softened by edits and reaction shots. I wanted to create an experience that traps the audience in a continuous reality, making the viewer feel the tension of a silent conflict unfolding in real time.
What if we watched a bizarre fracture between two people in a cozy space, and the camera simply refused to look away? That question became THE TABLE.
The Production Workflow
I had a vision but no traditional crew. CapCut Video Studio and the Seedance 2.5 model made a complex one-take sequence entirely possible.
Prompt-Driven Choreography: I mapped out a 30-second physical space in a single text prompt. Every action, from the walk to the aggressive muffin snatch, was engineered to unfold sequentially.
Unbroken Camera Control: To ensure the "one-take" rule was followed, I instructed the AI to use physical camera movements. Seedance 2.5 maintained the spatial consistency flawlessly.
The Assembly: The magic of this workflow was the lack of assembly. The final output is a raw, continuous generation with no manual splicing.
Platform Feedback
Seedance 2.5 brilliantly held the entire world together. When the camera whip-pans back from the street to the interior at the end, Table 1 and Table 2 are exactly where they should be. It felt like directing a steady-cam operator on a live set.
One honest piece of feedback: generating timed character interactions in a continuous 30-second shot requires immense trial and error. Optimized rendering costs for long-form visual storytellers would make a meaningful difference, also if specific editing can take place at point notes that will change massive things.
Ultimately, Seedance 2.5 helped me protect the awkward silence at the end of the film.
X: https://x.com/AshishSandhu/status/2090161080857223462?s=20
4
7
414
Local businesses—from neighborhood bakeries and specialty coffee roasters to barbershops and lounges—spend years building 5-star reputations on Google Maps. Yet their actual websites are often broken, outdated, or non-existent, costing them direct bookings and forcing them to pay hefty third-party platform fees.
The Solution: DimensionLocal (Built on Base44)
DimensionLocal transforms any raw Google Maps listing into both a tactile 3D neighborhood discovery experience and a production-ready, high-converting flagship website in seconds.
Key Design & Engineering Highlights:
Infinite 2D/3D Spatial Neighborhood Canvas: Instead of a static landing page, the homepage is an infinite, seamlessly wrapping cartography board populated with volumetric 3D storefronts. Each shop dynamically reflects real-world status—cycling through live venue photos when open, or dropping physical roller shutters when closed.
Live Google Places API Extraction: Paste any Google Maps URL or search any business worldwide. The backend automatically pulls high-resolution place photos, aggregate ratings, customer testimonials, 7-day Monday–Sunday schedules, phone numbers, and exact coordinates.
4 Polymorphic Website Archetypes: No two businesses look the same. With one click, any storefront transforms across 4 complete design systems:
Obsidian Flagship: Dark carbon & champagne gold luxury one-pager.
Spatial Glass: Frosted acrylic cards over an ambient blurred aura generated from the venue's own photography.
Tactile Craft: Warm limestone paper, exposed architectural grids, and mechanical offset shadows.
Swiss Editorial: High-contrast gallery typography and asymmetric lookbook layouts.
Closed-Loop Automation & Owner OS: Customers can book tables or appointments directly on the generated microsite. Flipping to the Owner Automation OS reveals a live reservation dispatch pipeline, local competitor radar analysis, and an AI Review Autopilot that drafts tailored responses to customer reviews in one click.
Built With:
Base44 (Frontend UI, Database, Backend Functions & AI Superagents), Google Places API (New), CSS 3D Transforms & Custom SVG Cartography.
3
4
496
📺 90s RETRO INFOMERCIAL
A late-night broadcast ad that puts your product in prime time.
Tuesday, 2:14 a.m. Special Broadcast.
A communicator exploded into five floating layers of pure silicon.
Callers flooded the switchboard. Operators urged viewers to stay on the line.
Friday night, a titanium smartphone outlived the entire weekend.
Its charger was reported missing, presumed retired.
Saturday, 3:30 a.m.
Dual cooling turbines spun up inside a creator laptop.
The studio stayed completely cold.
Sunday morning, marathon carbon sneakers hit the pavement.
The stopwatch gave up.
None of it aired on cable.
All of it broadcast on Channel 90.
📼 Every product wants to feel iconic.
Most of them get a generic banner.
I could not find a single vintage cathode-ray infomercial in SVGator's template gallery.
So I built one.
Mobile
Laptop
Shoes
Juice
Four editions, One template, Zero redraws.
Retype the headline, swap the product image, update the logo. or Directly connect your MCP and ask the agent to "Change the Image with "PRODUCT" and use these images" or "Create images using Nano Banana and Generate this for New Pair of Headphones named "BOKE NICE 2.0"
Every word is live text. Every element has a clean name: logo, headline, product-image.
The 5-layer isometric explosion never breaks.
The best part? I did not touch the canvas inside SVGator once.
Not a single keyframe was dragged by hand. Every geometry node, 5-layer isometric physics curve, phosphor flash, and color palette was architected and synced directly into SVGator Cloud purely via the SVGator MCP. That is how frictionless the programmatic integration is.
So what are you broadcasting tonight?
Operators are standing by. 📞✨
🛠️ 100% Built Programmatically via the SVGator MCP. Zero manual GUI editing. 5 live cloud projects deployed through code with authentic CRT scanlines, corner light leaks, and 1,270 named elements.
14
11
947
I've spent the last few days building something I genuinely wish existed years ago.
When I was job hunting, I had a PDF. A white rectangle with my name, dates, and bullet points. The same format invented in 1482. I was competing with thousands of people who had the exact same white rectangle.
I'm a builder. I ship products. I've worked with real companies, shipped real things, have real skills. None of that showed in a CV. It couldn't. A PDF wasn't built to show it.
And building a personal website? That's a project in itself. Design it, code it, host it, maintain it. Most people never do. So their career stays a white rectangle forever.
So I built RoomCV. (https://roomcv.figma.site/)
You don't build anything. You paste your LinkedIn URL, your Contra profile, or upload your CV. In under 60 seconds, your career has a home on the internet. A real one. With your name on the door.
Not a template you fill in. Not a prettier PDF. A room that reads your data and builds itself with all your pretty links.
And then there are the portraits.
The AI photoshoot is unlike anything else in this space. It runs a 3-stage pipeline (thanks to Figma Weave):
Stage 1 - A casting director model analyses your reference photo and writes a precise physical description. Hair, skin tone, bone structure, build. This becomes a consistency anchor so every portrait is recognisably you.
Stage 2 - A photography director model reads your actual CV. Your job title, your company, your career highlights, your personal note. It writes a bespoke scene brief the way a Vogue photo director would. A founder gets a quiet boardroom at night with a city skyline. A developer gets a dark server room with terminal green glow. A designer gets mood boards and soft daylight.
Stage 3 - The image model takes that bespoke brief, your reference photo, and your character anchor and generates 6 editorial portraits. Hero. At work. Thinking. Off duty. Achievement. Environmental.
Every portrait is specific to you. Because the AI read their actual careers before picking up the camera.
The room is alive.
People can visit your room at its permanent URL. They can leave signed notes in your guestbook. They can react with rockets, fire, or lightbulbs. You can see who's browsing right now, live presence, like a real room. Every visit is counted. The whole city of rooms is browsable and is a directory of real people's careers, each one visually distinct.
Three visual themes:
Cinematic - moody contrast, 35mm grain, deep editorial shadows.
Brutalist - harsh direct light, raw concrete textures, technical glitch aesthetic.
Minimal - soft diffused window light, high-key, warm neutrals, conversion-focused.
The copywriting changes completely per theme too. Same person, three radically different editorial voices. Wieden+Kennedy wrote none of them — Gemini did, with a prompt that bans every CV cliché and demands specific references to real company names, real project names, real skills.
What I used to build it:
Figma Make - the entire app. Every component, every interaction, every route. Built in natural language, iterated in real time.
Figma Weave - the portrait pipeline visualised as a node-based workflow. The casting director, the photography director, the 6 parallel image generation nodes. The hero background video on the landing page. The logo.
Figma MCP - connecting the design token system into the Make build so the three themes stayed consistent with the Figma source of truth.
Supabase - backend, auth, KV storage, private portrait bucket, signed URLs, edge functions.
Gemini - character extraction, photography direction, copywriting, profile parsing, room generation from raw LinkedIn/Contra/CV data.
The numbers that matter:
60 seconds from paste to published room.
6 portraits per person, all unique.
3 complete design systems per room.
0 templates. Every room is generated, not filled in.
1 permanent URL per person.
Unlimited visitors, reactions, guestbook notes.
Who this is for:
Designers who are tired of Behance looking like everyone else's Behance.
Developers whose GitHub is invisible to anyone who isn't technical.
Founders who have a LinkedIn but not a story.
Freelancers on Contra who want their profile to stop at the URL and start in the room.
Anyone who has ever felt like their career deserved better than a white rectangle.
Yesterday a dev called Andrei pasted his LinkedIn URL. 30 seconds later he had six editorial portraits and a career room that looked like the cover of Wired. He sent me a voice note. He said it was the first time his career had felt like his, and here it is for everyone to try.
Try it. Paste whatever you have. LinkedIn URL, Contra URL, raw CV text, PDF.
Your room is waiting.
roomcv.figma.site
(http://roomcv.figma.site)Figma Make: https://www.figma.com/make/3kpbdErsXVZqPSkZS2LdvY/Design-RoomCV-Creatively?t=ZnnNnUei4aE16P6e-1
Figma Weave: https://app.weavy.ai/flow/RK8qIG0eKBpyoJLOg4JgrC
Figma Community: https://www.figma.com/community/file/1649649240602428392/roomcv?fuid=1004476920505329686
X: https://x.com/AshishSandhu/status/2067821599223316662
(https://x.com/AshishSandhu/status/2067821599223316662?s=20)https://x.com/AshishSandhu/status/2067824940154269961
Drop your room link in the comments. I want to see every single one.
Built for the Figma Config Makeathon. Figma Make + Figma Weave + Figma MCP + Supabase + Gemini.
#ConfigMakeathon #Figma #FigmaMake #AI #Portfolio #CareerDesign
2
3
339