Stability AI Image Generation - Roboflow Inference

Name	Type	Description	Refs
`name`	`str`	Enter a unique identifier for this step..	❌
`strength`	`float`	controls how much influence the image parameter has on the generated image. A value of 0 would yield an image that is identical to the input. A value of 1 would be as if you passed in no image at all..	✅
`prompt`	`str`	Prompt to generate new images from text (what you wish to see).	✅
`negative_prompt`	`str`	Negative prompt to image generation model (what you do not wish to see).	✅
`model`	`str`	choose one of {'core', 'ultra', 'sd3'}. Default 'core' .	✅
`api_key`	`str`	Your Stability AI API key.	✅

Compatible Blocks

Check what blocks you can connect to Stability AI Image Generation in version v1.

inputs: Morphological Transformation, Classification Label Visualization, Crop Visualization, Stability AI Outpainting, Blur Visualization, Reference Path Visualization, OpenAI, Anthropic Claude, Camera Focus, Model Comparison Visualization, Florence-2 Model, Trace Visualization, Background Color Visualization, Label Visualization, Image Convert Grayscale, Florence-2 Model, Text Display, Qwen-VL, Llama 3.2 Vision, Image Blur, Keypoint Detection Model, Absolute Static Crop, CSV Formatter, LMM, Qwen 3.5 API, Qwen 3.6 API, Camera Focus, Clip Comparison, Google Gemma API, Contrast Enhancement, Halo Visualization, Color Visualization, Morphological Transformation, MoonshotAI Kimi, Stitch OCR Detections, Event Writer, Stability AI Inpainting, Roboflow Asset Library Attributes, Microsoft SQL Server Sink, OpenAI, Roboflow Vision Events, Identify Outliers, CogVLM, Detections Consensus, Object Detection Model, OPC UA Writer Sink, Dynamic Crop, Bounding Box Visualization, Qwen3.5-VL, OpenAI, OCR Model, Single-Label Classification Model, Slack Notification, OpenRouter, SIFT Comparison, Pixelate Visualization, Google Vision OCR, Google Gemma, Halo Visualization, Stitch OCR Detections, GLM-OCR, Image Threshold, Stitch Images, Twilio SMS/MMS Notification, Icon Visualization, VLM As Classifier, MoonshotAI Kimi, Google Gemini, Webhook Sink, QR Code Generator, MQTT Writer, Ellipse Visualization, Dot Visualization, Perspective Correction, Roboflow Dataset Upload, SIFT, Google Gemini, EasyOCR, Local File Sink, Triangle Visualization, Contrast Equalization, Polygon Visualization, OpenAI, Heatmap Visualization, Google Gemini, LMM For Classification, VLM As Detector, Identify Changes, Llama 3.2 Vision, Polygon Visualization, Email Notification, Mask Visualization, Anthropic Claude, Keypoint Visualization, Background Subtraction, Multi-Label Classification Model, Twilio SMS Notification, Email Notification, Image Slicer, Image Contours, Line Counter Visualization, Image Preprocessing, Depth Estimation, Current Time, Corner Visualization, Polygon Zone Visualization, Camera Calibration, Roboflow Dataset Upload, Grid Visualization, Stability AI Image Generation, S3 Sink, Circle Visualization, Image Slicer, Roboflow Custom Metadata, Relative Static Crop, Instance Segmentation Model, Model Monitoring Inference Aggregator, OpenAI-Compatible LLM, Anthropic Claude
outputs: Template Matching, Morphological Transformation, Classification Label Visualization, Crop Visualization, Stability AI Outpainting, Blur Visualization, Reference Path Visualization, OpenAI, YOLO-World Model, Anthropic Claude, Camera Focus, Track Class Lock, Instance Segmentation Model, Mask Edge Snap, Model Comparison Visualization, Florence-2 Model, Trace Visualization, SmolVLM2, Label Visualization, Image Convert Grayscale, Florence-2 Model, Text Display, Llama 3.2 Vision, Qwen-VL, Image Blur, Keypoint Detection Model, Absolute Static Crop, Gaze Detection, Keypoint Detection Model, LMM, OC-SORT Tracker, QR Code Detection, Qwen 3.5 API, Qwen 3.6 API, Qwen2.5-VL, Camera Focus, SORT Tracker, VLM As Detector, Qwen3-VL, Multi-Label Classification Model, Detections Stitch, Clip Comparison, Google Gemma API, Contrast Enhancement, Halo Visualization, MoonshotAI Kimi, Color Visualization, Morphological Transformation, Event Writer, Buffer, Stability AI Inpainting, Time in Zone, OpenAI, Roboflow Vision Events, Dominant Color, CogVLM, Object Detection Model, Semantic Segmentation Model, Dynamic Crop, Byte Tracker, Bounding Box Visualization, Qwen3.5-VL, Clip Comparison, SAM 3, OpenAI, Single-Label Classification Model, OCR Model, OpenRouter, SIFT Comparison, Pixelate Visualization, Google Vision OCR, SAM3 Video Tracker, Google Gemma, CLIP Embedding Model, Halo Visualization, GLM-OCR, Image Threshold, SAM 3 Interactive, Stitch Images, Twilio SMS/MMS Notification, VLM As Classifier, Icon Visualization, MoonshotAI Kimi, ByteTrack Tracker, Google Gemini, Single-Label Classification Model, Single-Label Classification Model, Instance Segmentation Model, Ellipse Visualization, Anthropic Claude, Object Detection Model, Keypoint Detection Model, BoT-SORT Tracker, Dot Visualization, Perspective Correction, Instance Segmentation Model, Seg Preview, Roboflow Dataset Upload, Detections Stabilizer, SIFT, Google Gemini, EasyOCR, SAM 3, Triangle Visualization, Contrast Equalization, Polygon Visualization, OpenAI, SAM2 Video Tracker, Heatmap Visualization, Perception Encoder Embedding Model, Google Gemini, LMM For Classification, VLM As Detector, Llama 3.2 Vision, Multi-Label Classification Model, Image Stack, Polygon Visualization, Mask Visualization, Anthropic Claude, Barcode Detection, Keypoint Visualization, Background Subtraction, Multi-Label Classification Model, Email Notification, Semantic Segmentation Model, Image Slicer, Image Contours, Line Counter Visualization, Image Preprocessing, SAM 3, VLM As Classifier, Depth Estimation, Pixel Color Count, Motion Detection, Qwen3.5, Roboflow Dataset Upload, Corner Visualization, Camera Calibration, Segment Anything 2 Model, Polygon Zone Visualization, Stability AI Image Generation, Moondream2, Circle Visualization, Image Slicer, Relative Static Crop, Instance Segmentation Model, Object Detection Model, Background Color Visualization

Bindings

input
- image (image): The image to use as the starting point for the generation..
- strength (float_zero_to_one): controls how much influence the image parameter has on the generated image. A value of 0 would yield an image that is identical to the input. A value of 1 would be as if you passed in no image at all..
- prompt (string): Prompt to generate new images from text (what you wish to see).
- negative_prompt (string): Negative prompt to image generation model (what you do not wish to see).
- model (string): choose one of {'core', 'ultra', 'sd3'}. Default 'core' .
- api_key (Union[string, secret]): Your Stability AI API key.
output
- image (image): Image in workflows.

Example JSON definition of step Stability AI Image Generation in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/stability_ai_image_gen@v1",
    "image": "$inputs.image",
    "strength": 0.3,
    "prompt": "my prompt",
    "negative_prompt": "my prompt",
    "model": "my prompt",
    "api_key": "xxx-xxx"
}

Stability AI Image Generation¶

Type identifier¶

Properties¶

Runtime compatibility¶

Available Connections¶

Input and Output Bindings¶