Talk to us Generate image
GeneratorPromptsPlatformAbout usContact Generate image

One model. Four surfaces. Built to scale on demand.

Studio to create in, an editor to finish in, a brand layer for teams and an API for engineers — all on the same pipeline, with the same safety layer and the same privacy guarantee.

The four surfaces

Studio

Create

The text-to-image workspace. Write a prompt, pick a style family, get four studio-quality variations, and iterate in real time while previews stream. Seeds and negative prompts are one click away when a frame is nearly right.

4K output9 style familiesseedsnegative promptsaspect presets

Smart Editor

Refine

Fix the frame you have instead of rolling the dice again. Inpaint a region, extend the canvas past its original edges, swap a background, erase an object — the pixels around your edit stay untouched.

inpaintingoutpaintingbackground swapobject erase

Brand Engine

Brand

Fine-tune Metabob on your own products, palette and lock-ups, then generate campaign assets that stay on identity across a whole set. Adapters train from as few as a dozen references and stay isolated to your workspace — never merged into the base model.

LoRA adaptersbrand lockasset libraryteam seatsper-tenant isolation

Developer API

Ship

Generative imaging as an API call inside your own product. Predictable REST semantics, streaming responses, idempotent job submission and signed webhooks, with SDKs for JavaScript, Python and Go.

RESTstreamingidempotent jobssigned webhooks
EndpointDoesReturns
POST /v1/imagesGenerate from a prompt, style family and ratioJob id, then streamed previews
POST /v1/editsInpaint, outpaint or erase within an existing frameJob id, then the edited frame
POST /v1/variationsRe-roll around a chosen seedJob id, then n variations
POST /v1/upscaleDetail-recovery pass to 4KJob id, then the upscaled asset
GET /v1/jobs/:idPoll a job when you would rather not hold a streamStatus and asset URLs
POST /v1/finetunesTrain a brand adapter from a reference setAdapter id and training status

This is the endpoint contract we publish for integrators, so teams can design against it before they write a line of code. Request access and we will set you up with keys.

Architecture

A multi-model pipeline: we route each prompt to the right model, refine composition and detail, then stream the result back. Inference runs on a pooled fleet of cloud GPUs behind an autoscaling scheduler, renders land in object storage and serve from a global edge cache — so capacity follows demand instead of running ahead of it.

  1. Latent diffusion core

    A latent diffusion backbone producing both photoreal and stylised output, with a refinement pass that recovers detail at 4K. Nine trained style families, stackable on one prompt.

  2. Multimodal text encoders

    Hybrid encoders capture style cues and compositional intent, so a longer prompt adds control rather than noise.

  3. Autoscaling GPU fleet

    Inference runs in containers scheduled across a pooled GPU fleet, with a warm pool sized to live traffic so queue depth stays flat at peak instead of spiking with it.

  4. Streaming delivery

    Render jobs move through a durable queue, land in object storage and serve from a global edge cache, so a preview reaches the browser while the full-resolution frame is still finishing.

  5. Safety and IP filtering

    Layered moderation runs on every generation — NSFW, trademark and likeness checks — before an image is ever returned to a user.

  6. Brand fine-tuning

    LoRA adapters train per customer on a small reference set, kept isolated per tenant and never mixed into the base model.

Pooled GPU fleetKubernetesObject storage Global edge cacheDurable job queueManaged PostgreSQL Container registryMetrics & tracing PyTorchTritonCUDAFastAPINext.jsTerraform

What we do with your work: nothing

The commercial case for a generative tool collapses if customers cannot trust it with a brief. So the guarantees are structural, not policy footnotes.

No training on your data

Your prompts, uploads and outputs are private to your account and are never used to train or evaluate our models. There is no opt-out to find, because there is no opt-in.

Isolated fine-tunes

A brand adapter trained on your references belongs to your workspace. It is never merged into the base model and never serves another customer's prompt.

Moderation on every render

NSFW, trademark and likeness screening runs inline before an image is returned — not as a nightly sweep after the fact.

Commercial rights. Paid plans include a commercial-use licence: what you generate is yours to ship in campaigns, product pages and client work. The free tier is for personal use and evaluation.

Put the whole pipeline behind your product