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
I created a cinematic one-take short about an unexpected encounter between two strangers on a busy city street. A simple accidental collision becomes a small emotional story built through natural reactions, subtle expressions, and continuous camera movement.
I wanted to explore how Seedance 2.5 can turn an everyday moment into something cinematic while maintaining character consistency, realistic motion, and visual continuity from the first frame to the last.
A one-take built around a coffee spill sounds simple on paper but is brutal to pull off with consistent character and continuous camera movement. What ended up being the biggest giveaway that broke the illusion before you fixed it?
Honestly, I got lucky with this one the final result came from the first generation. The part I was watching most closely was the hand and coffee interaction, because that’s usually where the illusion can break fastest. Seedance 2.5 handled it surprisingly well
First-generation luck like that is rare enough to savor. If it hadn't landed clean on the hand and coffee moment, what would the backup plan have been, more generations or switching to a cutaway?
If it hadn’t worked, I would’ve refined the prompt and tried again. With Seedance 2.5, you don’t always need to generate separate shots you can adjust the prompt until the whole scene works naturally in one take
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
Trending
retrofuturism
Share your favorite designs from the past exploring the distant future. Or your own take on the aesthetic 🚀
halftone
Dots. Texture. Grain. Let's see your designs using the halftone technique.
Midjourney
Creatives are showing off what they're making with Midjourney.
colorgrade
Video editors sound off: How do you enhance the mood of your video in color grading?
Related posts
I used to think the secret to better AI video was writing longer prompts.
This project changed how I approach prompting.
I took one of my actual Seedance 2.5 prompts and broke it apart. What looked like one detailed prompt was actually several different shots, camera movements, actions, and cinematic directions competing for the model's attention.
So I started treating AI video prompts more like shot direction:
SHOT → SUBJECT → ACTION → ENVIRONMENT → CAMERA → MOTION → LOOK → CONSTRAINTS
In this walkthrough, I show the real process, including how I structure the prompt, generate the scene, identify what isn't working, and refine the instructions.
The lesson is simple:
Don't make the prompt longer. Make the instructions clearer.
Think like a director, not a novelist.
https://share.descript.com/view/iYh2ZNB0bt1
https://web.descript.com/3c176614-948b-4aad-81d8-392fd2c09c2d
Thank you!
This one has 3 different animations exploring Promethist’s AI coaching platform, UI, and product features.
I’m also putting together a full case study for this project on Contra, where I’ll show more of the process, from the start to the final animation.
Coming soon.✨
Looks amazing
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.
Impressive