Research

Donkm.Tech Labs — pushing the frontier of generative imaging.

As a bootstrapped startup, we explore focused questions in model quality, controllability, efficiency and safety, then apply what works to practical products.

Current work

What we are exploring.

2026In progress

Practical model evaluation

Developing repeatable ways to compare quality, reliability and cost for real customer workflows.

2026Exploration

Brand-consistent generation

Testing lightweight approaches that help generated visuals stay closer to a customer's brand system.

2025Foundation

Safer image workflows

Establishing responsible review and moderation practices for the products and client solutions we build.

Research focus

Four questions we care about.

Controllability

How do we let users steer composition, lighting and style without losing fidelity?

Efficiency

Smaller, faster, cheaper inference — without giving up image quality.

Safety & IP

Building generative systems that respect creators, trademarks and consent.

Evaluation

Better metrics for what humans actually consider a 'good' generated image.

Want to collaborate?

We work with academic labs, independent researchers and partner companies.

Get in touch