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
The era of the specialist is over, and honestly, good.
First Data Scientist, then UI/UX, and lately I've been making AI visuals- both pictures and videos.
Here's what I got wrong first.
Most AI videos are bad because people ask it to make a whole scene. You write a paragraph, hope for the best, and do it again. It's like a slot machine with a monthly fee.
So I stopped writing prompts and started giving it pictures.
I made a still first. A still is easy to judge and easy to throw away. If the light and the crop are right, I have made every decision before anything moves.
Then I animated that still. Six seconds. One job. Nothing else moves.
Then the fun part. I took the last frame of that clip and used it as the first frame of the next one.
That frame had a hairline crack across a mirror. So the second generation didn't need a mirror described to it. It already had one. Cracked. Lit the way I lit it. All it had to do was break the thing.
And lo and behold, within three iterations, I achieved my anticipated result and merged the videos together.
So, personal lesson is to develop such videos upon last frames from the desired output produced- akin to the software development WATERFALL model- damn, once a techie, always a techie :P - what a complex and narrowly understandable analogy.
So: how was it? Be honest.
And what say you? Do you agree with my hook?
Great, and thanks for sharing your process
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
How do you make a logo feel alive without making it feel like a gimmick? 🤖
Quickchat AI builds no-code AI Agents that handle real work - customer support, sales, internal ops - reading docs and resolving conversations on their own. As the product scaled, the brand needed to catch up: something as sharp and credible as the tech itself, in a market where every AI startup looks the same.
I could have leaned into something loud - a mark morphing through wild transformations, motion for the sake of motion. Instead the direction was restraint. The wordmark reveals with one clean underline stroke. The icon wakes up letter by letter before landing on the final mark, closing on a small wink instead of a flourish 😉.
Every timing decision was intentional: fast enough to feel instant, controlled enough to feel trustworthy. That's the whole brief in one sentence.
The palette stayed just as disciplined 🎨 - one electric blue carrying the energy, one warm yellow breaking up the dark neutrals. Nothing decorative, everything load-bearing.
Where do you draw the line between motion that shows a product's personality and motion that's just there to show off?
"Only One Flame Survives the Storm" — a single continuous one-take anime battle, entirely AI-generated in CapCut Video Studio with Seedance 2.5.
Two original warriors, one arena, no cuts: a lightning-wielding swordsman vs. a fire-fisted fighter, clashing across a storm-lit rooftop until only one is left standing.
🎬 Built with: CapCut Video Studio (Seedance 2.5)
⚙️ Workflow: Wrote a detailed single-shot prompt covering subject, action, and camera movement, then used 1-second timestamp control to direct each beat of the fight — the clash, the escalation, the simultaneous final attack, and the win. Negative prompting kept it clean (no jump cuts, no extra characters, no artifacts) to preserve the illusion of one unbroken take.
Prompt used: "A single unbroken continuous cinematic shot in high-quality anime style, dynamic camera circling and tracking through an epic battle between two original anime warriors on a destroyed rooftop city arena at dusk..." [continued in comments/caption card if platform truncates]
30 seconds. One shot. No cuts.
#contraseedancechallenge #CapCutCPP
contraseedancechallengeAI Video ProductionCopywritingFramer Website DesignWeb DesignFigmaFramerWebflowAI Content CreationSocial Media ManagementCapCut
good looking.
Hi! I’m Briana. I’m a storyteller with a background in broadcast journalism, communications, and video production, and I love turning ideas into content that feels clear, creative, and engaging. From video editing and voiceover to social content and AI-assisted production, my goal is always the same: create work that connects with people and brings the story to life.
Welcome to the feed! The jump from broadcast journalism into freelance content and voiceover work is a real shift in pacing and client relationships. What's translated most directly from the newsroom, and what did you have to unlearn?