Stability AI

Image generation models: create, edit, and upscale images from text prompts

Signs in with: API token
Runs on: Cloud or On-Prem Worker
Operations: 36
Ready-made triggers: 0

Connect Stability AI

In Neblex open Connect › Connections and click New Connection.
Search for Stability AI and give the connection a clear name.
Fill in the fields. Secret values are encrypted and never shown again.
Click Test, then Create Connection.

Field	What to enter
Access tokenRequiredSecret

Use it in a flow

Open a flow, open the node library and search for Stability AI.
Drag it onto the canvas and choose an Operation and your connection.
Map the operation's fields from earlier steps, or click Map with Matt.
Use Test this step to see what it returns, then save.

To start a flow from Stability AI without a ready-made trigger: a Poll for changes trigger can check one of its list operations on a schedule and pass on only what is new; if Stability AI can send webhooks, a Webhook trigger receives them at its own URL.

Operations

36 operations in 7 groups. Each one is a step you can add to a flow.

3D2

Stable Fast 3D`stableFast3d`	POST	Generate a 3D asset (glTF) from an image.
Stable Point Aware 3D`stablePointAware3d`	POST	Generate a 3D asset with point-aware editing.

Account3

Get account`getAccount`	GET	The account's profile and organizations.
Get balance`getBalance`	GET	The account's credit balance.
List engines`listEngines`	GET	Available legacy v1 engines.

Audio7

Audio inpaint (SA1)`audioInpaintV1`	POST	Regenerate a masked span with Stable Audio 1.
Audio inpaint (SA2)`audioInpaint`	POST	Regenerate a masked span of audio.
Audio to audio (SA1)`audioToAudioV1`	POST	Transform audio with Stable Audio 1.
Audio to audio (SA2)`audioToAudio`	POST	Transform audio with a prompt.
Fetch audio result`getAudioResult`	GET	Fetch an async audio generation's result.
Text to audio (SA1)`textToAudioV1`	POST	Generate audio with Stable Audio 1.
Text to audio (SA2)`textToAudio`	POST	Generate audio from a prompt with Stable Audio 2.

Control4

Sketch`controlSketch`	POST	Generate from a sketch with prompt guidance.
Structure`controlStructure`	POST	Generate preserving an input image's structure.
Style guide`controlStyle`	POST	Generate in an input image's style.
Style transfer`styleTransfer`	POST	Restyle an image from a style reference.

Edit8

Erase`erase`	POST	Remove masked objects from an image.
Inpaint`inpaint`	POST	Fill or replace masked regions from a prompt.
Inpaint (v2alpha)`inpaintV2alpha`	POST	Legacy alpha inpaint: mask mode or search-prompt mode.
Outpaint`outpaint`	POST	Extend an image in any direction.
Remove background`removeBackground`	POST	Segment out the background.
Replace background and relight`replaceBackgroundRelight`	POST	Swap the background and relight the subject (async).
Search and recolor`searchAndRecolor`	POST	Recolor prompt-selected objects.
Search and replace`searchAndReplace`	POST	Replace prompt-selected objects.

Generate6

Fetch async result`getResult`	GET	Fetch any async generation's result by ID.
Image to image (v1 SDXL)`imageToImage`	POST	Legacy SDXL image-to-image.
Stable Diffusion 3.5`generateSd3`	POST	Text-to-image or image-to-image with SD3.5 models.
Stable Image Core`generateCore`	POST	Fast, affordable text-to-image.
Stable Image Ultra`generateUltra`	POST	Highest-quality text-to-image (optionally image-guided).
Text to image (v1 SDXL)`textToImage`	POST	Legacy SDXL text-to-image.

Upscale6

Conservative upscale`upscaleConservative`	POST	Upscale to ~4MP with minimal changes.
Creative upscale (async)`upscaleCreative`	POST	Upscale heavily degraded images (poll the result).
Creative upscale (v2alpha)`upscaleV2alpha`	POST	Legacy alpha creative upscale (poll the result).
Creative upscale result`getCreativeUpscaleResult`	GET	Fetch a creative-upscale job's result.
Fast upscale`upscaleFast`	POST	4x upscale, speed-optimized.
Upscale result (v2alpha)`getUpscaleV2alphaResult`	GET	Fetch a legacy alpha upscale's result.