Stability AI Image Generation

Class: StabilityAIImageGenBlockV1

Source: inference.core.workflows.core_steps.models.foundation.stability_ai.image_gen.v1.StabilityAIImageGenBlockV1

The block wraps Stability AI image generation API and let users generate new images from text, or create variations of existing images.

Type identifier

Use the following identifier in step "type" field: roboflow_core/stability_ai_image_gen@v1to add the block as as step in your workflow.

Properties

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.	✅

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Available Connections

Compatible Blocks

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

• inputs: Polygon Zone Visualization, Identify Outliers, LMM For Classification, VLM as Classifier, Dot Visualization, Morphological Transformation, Blur Visualization, Perspective Correction, Corner Visualization, LMM, Florence-2 Model, Grid Visualization, Image Threshold, Florence-2 Model, Halo Visualization, OpenAI, Multi-Label Classification Model, CogVLM, EasyOCR, Line Counter Visualization, Stitch OCR Detections, Stability AI Outpainting, Twilio SMS Notification, Keypoint Detection Model, Identify Changes, Google Vision OCR, Camera Focus, Roboflow Dataset Upload, SIFT, Email Notification, Clip Comparison, Image Slicer, Image Convert Grayscale, Keypoint Visualization, Instance Segmentation Model, OCR Model, Llama 3.2 Vision, Bounding Box Visualization, Reference Path Visualization, Dynamic Crop, Roboflow Dataset Upload, Mask Visualization, Image Preprocessing, Background Color Visualization, Local File Sink, Webhook Sink, Camera Calibration, OpenAI, Depth Estimation, Image Slicer, QR Code Generator, Trace Visualization, Object Detection Model, Contrast Equalization, Crop Visualization, Stability AI Image Generation, SIFT Comparison, Roboflow Custom Metadata, Model Comparison Visualization, Pixelate Visualization, Model Monitoring Inference Aggregator, Anthropic Claude, Relative Static Crop, Image Contours, Polygon Visualization, OpenAI, Slack Notification, Triangle Visualization, Classification Label Visualization, Circle Visualization, Image Blur, Label Visualization, Google Gemini, VLM as Detector, Absolute Static Crop, Stability AI Inpainting, Icon Visualization, Ellipse Visualization, Color Visualization, CSV Formatter, Single-Label Classification Model, Detections Consensus, Stitch Images
• outputs: VLM as Classifier, LMM For Classification, Polygon Zone Visualization, Dot Visualization, Morphological Transformation, Perspective Correction, Blur Visualization, Clip Comparison, Corner Visualization, LMM, Pixel Color Count, Florence-2 Model, Image Threshold, Florence-2 Model, Halo Visualization, OpenAI, Keypoint Detection Model, Multi-Label Classification Model, CogVLM, EasyOCR, Byte Tracker, Line Counter Visualization, Perception Encoder Embedding Model, VLM as Detector, Stability AI Outpainting, VLM as Classifier, Keypoint Detection Model, Google Vision OCR, CLIP Embedding Model, Camera Focus, Roboflow Dataset Upload, SIFT, Instance Segmentation Model, Clip Comparison, Image Slicer, Image Convert Grayscale, Keypoint Visualization, Template Matching, OCR Model, Llama 3.2 Vision, Bounding Box Visualization, Detections Stabilizer, Instance Segmentation Model, Reference Path Visualization, Dynamic Crop, Roboflow Dataset Upload, Mask Visualization, Image Preprocessing, Qwen2.5-VL, Background Color Visualization, OpenAI, Camera Calibration, Depth Estimation, Image Slicer, Detections Stitch, Dominant Color, Trace Visualization, Object Detection Model, Contrast Equalization, Buffer, Crop Visualization, Stability AI Image Generation, Stitch Images, SmolVLM2, SIFT Comparison, Object Detection Model, Model Comparison Visualization, Pixelate Visualization, Gaze Detection, Anthropic Claude, Time in Zone, QR Code Detection, Relative Static Crop, Polygon Visualization, Barcode Detection, Image Contours, OpenAI, Triangle Visualization, YOLO-World Model, Single-Label Classification Model, Classification Label Visualization, Circle Visualization, Image Blur, Label Visualization, VLM as Detector, Google Gemini, Multi-Label Classification Model, Stability AI Inpainting, Absolute Static Crop, Icon Visualization, Ellipse Visualization, Color Visualization, Single-Label Classification Model, Moondream2, Segment Anything 2 Model

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Stability AI Image Generation in version v1 has.

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"
}