Generative systems for fashion, music & installation art

Q: Do you train a custom model for every project, or reuse existing ones?

Every project gets its own trained or fine-tuned model. Reused generic models are how you end up with the "AI look" — that's exactly what I avoid.

Q: Can generative visuals run live, or is it always pre-rendered?

Both. Installations and events often run real-time systems; campaigns and brand visuals are usually curated and rendered for final delivery.

Q: How do you handle real-time data integration for visuals?

Live input — audience sound, sensor feeds, an API, whatever the piece needs — gets piped straight into the generative engine, so the visual reacts as data comes in instead of looping a pre-rendered clip. That's the same pipeline behind Echo Chamber: it responds, it doesn't just replay.

Q: What do you need from us to start?

A creative brief, any brand or reference assets you want the system trained on, and a sense of what "never seen before" means for you.

Q: Do you work with brands who've never done anything with AI before?

Yes — most clients haven't. Part of the job is translating the technical process into something a non-technical team can approve with confidence.

Building moving images with code and machine learning — generative systems, AI film, and real-time visuals for brands who want to feel ahead.

View the work

Start a project

Generative systems for fashion, music & installation art

Building moving images with code and machine learning — generative systems, AI film, and real-time visuals for brands who want to feel ahead.

Start a project

View the work

Generative systems for fashion, music & installation art

Building moving images with code and machine learning — generative systems, AI film, and real-time visuals for brands who want to feel ahead.

Start a project

View the work

A woman's silhouette sitting curled inside the petals of a large purple iris flower, covered in dewdrops and glowing softly in violet and pink light

Three blurred figures walking past a large glowing crystalline sculpture in a minimalist gallery space

$Close-up portrait of a woman with glossy, holographic skin and light refractions across her cheek and lips$

Album cover art titled Luminescence by Aurora Veil, showing a silhouetted figure standing beneath a swirling ring of light against a night sky

Drift — Generative Film

A generative film system for a fashion week opener, trained on 40,000 frames of fabric motion and rendered live on-site.

Echo Chamber — AI Installation

An installation that repaints itself from live audience audio — no two visitors see the same piece twice.

Synthskin — Beauty Campaign

A custom diffusion model for a beauty campaign, generating impossible textures no camera could capture.

Halflight — Brand Identity

A generative identity system for a music label — album art that mutates with every stream.

$Close-up portrait of a woman with glossy, holographic skin and light refractions across her cheek and lips$

Drift — Generative Film

A generative film system for a fashion week opener, trained on 40,000 frames of fabric motion and rendered live on-site.

Echo Chamber — AI Installation

An installation that repaints itself from live audience audio — no two visitors see the same piece twice.

Synthskin — Beauty Campaign

A custom diffusion model for a beauty campaign, generating impossible textures no camera could capture.

Halflight — Brand Identity

A generative identity system for a music label — album art that mutates with every stream.

How it works

From brief to a system nobody's seen before.

Every model trained from scratch. No reused generic checkpoints, no off-the-shelf "AI look."

Step 1 — Discover

Understand the brief, the brand world, and what "never seen before" means for this client.

Low-angle view looking up through flowers at a person mid-jump against a blue sky, framed by prismatic light flares

Step 2 — Train & prompt

Build or fine-tune the model on the right dataset — this is where the look gets found.

Close-up texture of wavy green fur or grass catching soft light

Step 3 — Generate, curate & deliver

Run generations, curate ruthlessly, then hand off final renders or a live generative build.

How it works

From brief to a system nobody's seen before.

Every model trained from scratch. No reused generic checkpoints, no off-the-shelf "AI look."

A wooden door standing open atop a grassy hill under a sky filled with soft clouds

Step 1 — Discover

Understand the brief, the brand world, and what "never seen before" means for this client.

Step 2 — Train & prompt

Build or fine-tune the model on the right dataset — this is where the look gets found.

Step 3 — Generate, curate & deliver

Run generations, curate ruthlessly, then hand off final renders or a live generative build.

Silhouette of a woman standing on a hilltop at night, encircled by a swirling ring of light trails glowing gold and blue against the dark sky

Seven years at the edge of art and machine learning.

I train my own models, break other people's, and turn both into images nobody has seen before — for fashion houses, labels, and studios who want their visuals to feel five minutes ahead. No stock AI look: every piece is trained, tuned, and art-directed by hand.

Close-up of a glass astronaut helmet resting in a field of pink and white flowers at golden hour, reflecting the sunset

Four ways to build something no one's seen.

Generative systems

Custom-built systems that keep producing new, on-brand visuals long after the first delivery.

AI film & motion

Moving images generated frame by frame, not edited together from stock footage.

Custom model training

Every model trained on your own references — never a generic, off-the-shelf checkpoint.

Creative direction

Curating and shaping the output until it has a point of view, not just volume.

$Portrait with dark hair, orange petals and refracted cyan and amber light$

7 years

Seven years training and directing generative systems.

40,000+ frames

40,000+ frames used to train a single film system (Drift).

A man in sunglasses standing against a mountain landscape, surrounded by floating music player widgets showing song titles and playback controls

A woman in a metallic teal shirt and pink satin pants posing inside a glowing washing machine drum

3 industries

3 industries — fashion, music, and installation art — run on the same process.

$Portrait with dark hair, orange petals and refracted cyan and amber light$

7 years

Seven years training and directing generative systems.

40,000+ frames

40,000+ frames used to train a single film system (Drift).

3 industries

3 industries — fashion, music, and installation art — run on the same process.

Testimonials

They didn't know what to expect. That was the point.

A few of the studios and labels who've had Nova build something for them.

View the work

Trusted by+50 brands

"Nova doesn't just generate images — she directs them. The work looked like nothing else in the show."
Elena Marsh
Creative Director, Statistic Season
"We asked for something that felt impossible. She trained a model from scratch and delivered exactly that, on time."
Darius Okafor
Founder, Halo Studios
"Technically sharp and genuinely artistic — a rare combination in this space. Our album art has never gotten this reaction."
Sasha Lind
A&R, Field Records

"Nova doesn't just generate images — she directs them. The work looked like nothing else in the show."
Elena Marsh
Creative Director, Statistic Season
"We asked for something that felt impossible. She trained a model from scratch and delivered exactly that, on time."
Darius Okafor
Founder, Halo Studios
"Technically sharp and genuinely artistic — a rare combination in this space. Our album art has never gotten this reaction."
Sasha Lind
A&R, Field Records