Visual direction
Defining the generative language and pipeline; your team executes.
Services
AI and generative pipelines used as art direction, not as a prompt lottery.
The difference between an AI visual that works and one that looks like everyone else's is almost never the model. It is dataset work, curation volume, and someone making art direction decisions across thousands of outputs.
Ötme Bülbül Ötme landed in early 2023, before usable commercial AI video tools existed. Stable Diffusion 1.2 produced muddy output, so custom dataset training — including on the performer's face — became necessary to keep portraits anchored to the music instead of drifting into generic synthetic faces. Roughly six months of synthesis and curation produced more than five thousand images and a thousand video generations, shaped into a single visual line.
That is what this service actually is: building and curating at scale so the result reads as one continuous world rather than a collage of experiments.
What the piece should look like and, more importantly, what it should not. Generative work without this becomes noise very quickly.
Model selection, dataset preparation, and training where a specific subject or look has to stay consistent across thousands of frames.
Generating far more material than the final piece will use, because selection is where the quality actually comes from.
The selection and sequencing pass, plus compositing against recorded or stock material where the piece needs an anchor in something real.
Handover in the form your editor, installation, or broadcast pipeline requires.
Defining the generative language and pipeline; your team executes.
Direction through delivery, including dataset work, generation volume, and curation.
Your team has the tools but the outputs are not holding together. Usually a dataset and curation problem, not a model problem.
Public projects that show this work in practice, with credits and venues.
Ötme Bülbül Ötme is an AI music video for Doğukan Polat, exploring creation, nature, and self-awareness through electronic textures, nefes tradition, and...
View case study →Lovotic is Soundwalk Collective's concept album turned music video, featuring Charlotte Gainsbourg, Willem Dafoe, and Atom™. It is a study of intimacy...
View case study →Nine-channel audiovisual installation combining AI, motion capture, and live improvisation into a synchronized spiral of video and sound.
View case study →No, and projects that treat it that way tend to look like it. The work is dataset preparation, training where consistency demands it, generating far more material than gets used, and then curating hard. On Ötme Bülbül Ötme that meant over five thousand images and a thousand video generations for one music video.
Longer than people expect, because volume is the mechanism. Six months went into the synthesis and curation on Ötme Bülbül Ötme. Modern tools have compressed that considerably, but a piece that needs a specific, consistent world still needs weeks rather than days.
Send the rough scope, the venue, and the dates. If it is not a good fit I will say so, and where I can I will point you to someone better placed.
Start a conversation