Language & orchestration
- ChatGPT (OpenAI)
- Grok (xAI)
AI Lab
Experiments first. Business model later.
The best way to understand new technology is to work with it. We test, combine and discard — and the outcome does not have to be known at the beginning.
Why an AI Lab?
An experiment may become a product. It may lead to a client project. It may simply produce new knowledge. Or it may show that an idea does not work.
That is a result too.
Systems & workflows
Many systems. One workflow.
We work hands-on with language, image, video and voice AI, connecting different systems with each other. We combine cloud services with local models and continuously test which system actually works best for a given task.
The goal is not to collect AI tools. The goal is to understand their strengths, limits and interfaces — and turn them into reliable workflows.
Image generation
- ChatGPT Images (OpenAI)
- Grok Imagine (xAI)
- FLUX (Black Forest Labs)
- Stable Diffusion XL / SDXL (Stability AI)
- Juggernaut XL (KandooAI)
Video generation
- Grok Imagine (xAI)
- Seedance (ByteDance Seed)
Voice generation & synthesis
- ElevenLabs (ElevenLabs)
- MiniMax Audio (MiniMax)
Local workflow infrastructure
- ComfyUI (Comfy)
Grok and Grok Imagine are trademarks of X.AI LLC.
In the wild
The test does not end in the studio.
A synthetic character only becomes interesting when it also works under demanding visual conditions: real sunlight, complex outdoor environments, changing perspectives and backgrounds that must not look like an AI demo.
More experiments
More experiments will appear here when there is something genuinely worth showing.