Get in touch

I'm Eric Hsiao. A decade spent cutting film for brands like Google, Anthropic, Figma, and The North Face. Now I make generative film and AI-native products too. HARD8 is my bet that the hard way still pays.

FUJIN

Generative study 02

FUJIN

A wordless launch sequence cut as one scene: a study in keeping a character and a world consistent, shot to shot

Role
Creative / Generative / Edit / Sound
Stills
GPT Image 2 · Nano Banana Pro
Motion
Seedance 2.0
Finished in
Premiere Pro · Twixtor · Topaz Video AI
Year
2026

Wind, the hard way.

A young pilot walks the length of the bay and takes his machine to the sky, and the crew that built it stops to watch him go. The actual subject is consistency: keeping one character the same person, and one world the same place, across an entire sequence: the hardest open problem in generative video. Both are original, designed for this study. A single beautiful clip is easy now. A scene is not.

Reference before generation. The pilot and his world were locked as fixed references before a single frame was rendered: a face that has to survive every angle and expression, a hangar that has to stay the same building from every camera.

The character bible: same face, every angle, in armor and out.

The world locked the same way: one hangar, one door, one light.

Every shot was planned, shot-listed, and storyboarded before generation, then keyframed as stills and animated one controlled camera move at a time. The hard beats were pinned with first-and-last-frame control: the dice study’s trick, now doing character work. A smile, an ignition, an eyeline.

Locked endpoint frames for the hard beats: the eyeline, the smile, the launch.

Continuity was always an illusion. On a real set no two takes match; the editor hides the seams and the cutaway does the lying. Generative video just makes that old trick load-bearing. Shoot coverage: wide, medium, insert, reaction. Control exactly what the audience sees, and cut around the drift. Clips are a party trick. Scenes are the job.

The reaction shot is the editor’s oldest tool: while she watches, the cut gets away with everything.

Upscaled in Topaz, retimed in Premiere with Twixtor. Sound designed and placed by hand. When anyone can generate anything, the work isn’t making the shot. It’s knowing which one to keep.

FUJIN, for Fūjin, god of wind. His mark, 風, rides on the machine.

All original IP · Made under these principles

/ /

When anyone can generate anything, the hard part isn't making more. It's knowing what to keep. Editors got here early.

What changed

The editor's job is deciding what stays. Hundreds of takes come in, maybe twenty make the cut, and the film is made of everything you said no to.

That judgment used to live downstream. The shoot happened, then the footage came to me. Generative tools flip it: the person who decides what to keep now gets to make. Direct the shot instead of receiving it, design the world instead of inheriting it, start at the idea instead of the handoff. Building an app runs the same loop: generate wide, judge hard, keep the one that's right. Same eye, moved upstream.

The rules I keep with generative tools

Why the name

In craps, a hard 8 is eight rolled the hard way: two fours, one exact combination. Worse odds, honest work, better payout. That's my bet.

For me, it has a second meaning: in Chinese, four (四) sounds like death (死) and eight (八) like fortune (發). A hard 8 is alchemy: double death into gold.

Anyone can roll an eight. The hard 8 is a choice.

Capabilities

Film & post

  • Editorial / offline edit
  • Post-production supervision
  • Direction
  • Motion & finishing
  • Brand film & campaign content

AI & product

  • Generative film, commercials & imagery
  • AI-native product design
  • Full-stack app builds (solo)
  • Creative systems & automation

Brands I’ve cut for

Google · Anthropic · Adobe · Figma · LinkedIn · Canva · The North Face · Specialized · Zoox · LG

Co-founder & creative director, Desmond Studio, 2016 to 2025