Stability AI
Connects to the Stability AI image generation API (Stable Diffusion 3 / SDXL). An agent can generate images from text prompts.
Add to an agent node's tools array with _node_type: "tool-stability". See Connector Reference — How connectors are used.
Authentication
| Field | Required | Description |
|---|---|---|
api_key | Yes (or stability_api_key) | Stability AI API key, sent as Authorization: Bearer <api_key>. |
stability_api_key | Yes (if api_key not set) | Used if api_key is not set. |
{
"name": "stability",
"_node_type": "tool-stability",
"api_key": "{{ secret.STABILITY_API_KEY }}"
}
Tools
stability_generate
Generate an image from a text prompt using Stability AI (SD3 or SDXL). Returns base64-encoded PNG.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Yes | Image description |
negative_prompt | string | No | What to avoid in the image |
model | string | No | sd3 | sd3-turbo | stable-diffusion-xl-1024-v1-0 (default: sd3) |
width | number | No | Image width (default 1024) |
height | number | No | Image height (default 1024) |
steps | number | No | Inference steps (default 25) |
cfg_scale | number | No | Guidance scale (default 7) |
seed | number | No | Random seed (-1 for random) |
When model is sd3 or sd3-turbo, the request goes to /v2beta/stable-image/generate/sd3 (only prompt, model, negative_prompt, and seed apply — width/height/steps/cfg_scale are ignored). For other models, the request goes to /v1/generation/{model}/text-to-image using width, height, cfg_scale, steps, and seed.
Returns: JSON with image_base64 (base64-encoded PNG), format ("png"), model, and provider ("stability").