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

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"
}