A 60-second fan short made entirely with AI video, with my own face as the lead. Nine shots, seven characters, built from one selfie and a set of reference images. No cameras were used.
I started from a public prompt guide by kaye_creatives on Higgsfield and treated it like a shooting script: built my own character sheet, cast the missing character, generated each shot separately, then cut, captioned, titled and mixed it myself.
What I'd pass on to anyone trying this:
Give every reference image one job. Face, room, prop or camera angle, never two at once.
Put exact counts in the prompt. Models add people and props unless you tell them how many.
Generate long, cut short. My first assembly was 67 seconds. The final is 60, and the pace is where the quality came from.
EMBER ONE is a concept we built at Codevibe. No client, no store. Just one question: can a product website and its launch film come from the same 3D model?
They can. This 34-second film is rendered from the exact model that runs on the website. Nothing was rebuilt in another tool.
What's on the site:
• Drag to turn the lighter: front, side, back, base and lid open
• Scroll and it comes apart into six assemblies, then puts itself back together
• Click the lighter to light it
• A small refill sequence and three finishes: Obsidian, Titanium and Burnished
One model for both means the film and the site never drift apart. Change a detail once and both update.
Film first, site the same day: the film earns the click and the site keeps people playing. One model for both is the part I'd copy. On my Nothing Phone concept the hardest bit was holding detail up in the macro shots. Did the close-ups in the film need a heavier version of the model, or does the web one hold up?
A quick update on my Director’s Console.
Finally got the red shuttle lever to feel just right — heavy, mechanical, and with that spring return when you let go.
It’s built for the browser, but I wanted it to feel like an actual machine you could touch.
Turn the sound on and tell me what you think.