Generative media platform

How to use
Stability AI.

Building applications that generate, edit, upscale, control, and transform images through Stable Image services and related Stability AI models.

Open Stability AI ↗ Official download ↗
What it isgenerative image, editing, upscaling, control, video, audio, and 3D model API platform Workflows2 UpdatedSeptember 2026

Stability AI is a generative image, editing, upscaling, control, video, audio, and 3D model API platform. Building applications that generate, edit, upscale, control, and transform images through Stable Image services and related Stability AI models. This guide covers the whole path in one place: official access, a first session that produces something reviewable, the checks that make output trustworthy, and the permissions worth limiting before you connect real work.

Troiana principle

AI should make the work easier to inspect. If the workflow removes the source, the owner, or the review step, redesign the workflow.

01

Access & setup

Find, install, and sign in to Stability AI

Get into the official Stability AI experience with the right account and a setup you understand.

  1. 01

    Start at https://platform.stability.ai/ and confirm the domain before entering account or payment information.

  2. 02

    Availability: Stability AI is available through its web developer platform, REST APIs, hosted partners, and separately licensed model weights rather than a required desktop application.

  3. 03

    A Stability Platform account, API key and credits, a secure server-side environment, and authorized prompts and input assets.

  4. 04

    Sign in with the account you intend to keep using, then review plan, data, notification, and permission settings.

  5. 05

    Run one low-risk test task before connecting sensitive files, repositories, or workspace data.

  • Use official download pages.
  • Review permissions during setup.
  • Keep installers and applications updated.
02

First session

Your first useful Stability AI session

Learn the interaction loop using a small task with a clear outcome.

  1. 01

    Create a development key, store it outside source control, and add a small credit budget.

  2. 02

    Choose Stable Image Core or another current v2beta service for one low-risk test asset.

  3. 03

    Send an explicit prompt, aspect ratio, output format, and recorded seed from a trusted backend.

  4. 04

    Inspect the full-resolution result, moderation outcome, request settings, and credits before saving or sharing it.

  • State the outcome before the background.
  • Provide the real source material.
  • Review the result before expanding the task.
03

Quality control

Check the quality of Stability AI output

Turn a promising generation into an asset you can legally and safely ship.

  1. 01

    Restate the brief, the deliverable format, and where the asset will appear before judging any output.

  2. 02

    Inspect at full resolution: generated media hides its errors at thumbnail size.

  3. 03

    Check the details these systems reliably get wrong — hands, text, logos, reflections, symmetry, and edge artefacts.

  4. 04

    Confirm the licence and commercial-use terms for your plan, and check the output does not reproduce a recognisable style, mark, or likeness you have no right to use.

  5. 05

    Review for accessibility and delivery: alt text, contrast, colour profile, file size, and the exact export format.

  • Inspect at full resolution before approving anything.
  • Confirm commercial-use rights before an asset reaches a client.
  • Keep the prompt and settings with the asset so it can be reproduced.
04

Privacy & permissions

Use Stability AI safely

Use the platform without surrendering rights, likenesses, or client material you do not control.

  1. 01

    Confirm you hold the rights to every reference image, voice, or clip before uploading it.

  2. 02

    Check whether your plan trains on submitted content, and opt out before uploading client work.

  3. 03

    Never upload a real person's likeness or voice without their explicit, documented consent.

  4. 04

    Review the output for marks, styles, or likenesses you have no licence to reproduce.

  5. 05

    Label synthetic media where your client, platform, or jurisdiction requires disclosure.

  • Generated and edited media can contain unsafe, biased, deceptive, infringing, or unwanted likeness content. Use current endpoints, protect keys, confirm rights and consent for inputs, retain originals, minimize uploaded data, record model settings and seeds, review outputs at full resolution, disclose material edits, handle moderation and rate limits explicitly, and track model deprecations, licensing, and credit use.
  • Follow your organisation's approved-use policy.
  • Never treat fluent output as authorization to act.
05

Core workflows

Step-by-step ways to use Stability AI for the work it does best.

Each workflow below has its own outcome, steps and review checkpoints.

01 WorkflowBuild a reproducible Stable Image generation workflow

Compare Stability AI image services with controlled prompts, parameters, seeds, costs, and review criteria.

 02 WorkflowEdit an owned image safely with Stability AI

Use inpaint, outpaint, erase, search-and-replace, or relighting while preserving source rights and edit history.

Workflow 01

Build a reproducible Stable Image generation workflow

Compare Stability AI image services with controlled prompts, parameters, seeds, costs, and review criteria.

Outcome: Select an API service and configuration using traceable creative and operational evidence.

  1. 01

    Define the asset purpose, audience, dimensions, style, prohibited content, rights constraints, quality rubric, latency target, and credit budget.

  2. 02

    Create a project API key in a secret store and use the REST v2beta service with explicit accept, output format, model, and application identifiers.

  3. 03

    Run a fixed prompt set across suitable Stable Image services, recording prompt, negative prompt, seed, aspect ratio, model, response ID, and credits.

  4. 04

    Review prompt adherence, anatomy, text, artifacts, bias, safety-filter outcomes, source similarity, and suitability for the intended context.

  5. 05

    Save approved outputs with configuration and human-review status, monitor rate and credit use, and rerun the benchmark before service changes.

What good use looks like

  • Use the current v2beta services.
  • Record seeds and model settings.
  • Review outputs before publication.

Workflow 02

Edit an owned image safely with Stability AI

Use inpaint, outpaint, erase, search-and-replace, or relighting while preserving source rights and edit history.

Outcome: Produce a controlled image edit whose source, mask, instructions, transformations, and approvals remain auditable.

  1. 01

    Confirm ownership or permission for the image and depicted people, then define the exact edit, protected regions, output size, and prohibited changes.

  2. 02

    Remove unnecessary metadata, retain an immutable original, and create a precise mask or prompt with supported dimensions and request size.

  3. 03

    Call the narrowest edit endpoint with a server-side key, explicit output format and seed, and no unrelated reference images or sensitive data.

  4. 04

    Compare output against the original for unintended identity, logo, text, background, lighting, and safety changes at full resolution.

  5. 05

    Store the original, mask, prompt, endpoint, seed, and approved result separately; disclose material edits and delete rejected assets on schedule.

What good use looks like

  • Keep an immutable original.
  • Use the narrowest edit endpoint.
  • Document material alterations.
06

Official references

Check the current product documentation.

Features, plan limits, availability, and data controls change. These official pages are the starting points used for this guide.

Explore the Troiana AI Hub →