One pipeline, four ways in
Studio to create in, the generator explained, the platform underneath and an API to build on. Every surface runs on the same model, the same safety layer and the same privacy guarantee.
Studio
CreateThe text-to-image workspace. Write a sentence or shuffle one from the library, pick a style family and a ratio, and watch it resolve.
Generator
UnderstandWhat the engine does and what you can steer. The trained aesthetics, the controls that make an output repeatable, and what happens in the seconds after you press generate.
Platform
ScaleThe architecture underneath: the diffusion core, the safety layer that runs on every render, brand fine-tuning, and the privacy guarantee that applies to all of it.
Developer API
ShipGenerative imaging as one REST call. Submit a job, stream previews while the full-resolution frame finishes, take delivery by signed webhook.
What they share
These are four doors into one system, not four products bolted together. Anything true of the pipeline is true wherever you reach it.
The same diffusion core answers Studio, the API and everything between. A prompt that works in one place works in the others, and a seed reproduces the same frame wherever you use it.
Screening runs on every render before it is returned — not as a setting you can switch off, and not only on the surfaces where it is convenient.
Prompts and outputs stay private to your account and are never used to train our models. That holds for API calls exactly as it does for Studio.