Stability AI Outpainting

Class: StabilityAIOutpaintingBlockV1

Source: inference.core.workflows.core_steps.models.foundation.stability_ai.outpainting.v1.StabilityAIOutpaintingBlockV1

The block wraps Stability AI outpainting API and let users use object detection results to change the content of images in a creative way.

The block sends crop of the image to the API together with directions where to outpaint. As a result, the API returns the image with outpainted regions. At least one of left, right, up, down must be provided, otherwise original image is returned.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
creativity	float	Creativity parameter for outpainting. Higher values result in more creative outpainting..	✅
left	int	Number of pixels to outpaint on the left side of the image. Max value is 2000..	✅
right	int	Number of pixels to outpaint on the right side of the image. Max value is 2000..	✅
up	int	Number of pixels to outpaint on the top side of the image. Max value is 2000..	✅
down	int	Number of pixels to outpaint on the bottom side of the image. Max value is 2000..	✅
prompt	str	Optional prompt to apply when outpainting the image (what you wish to see). If not provided, the image will be outpainted without any prompt..	✅
preset	StabilityAIPresets	Optional preset to apply when outpainting the image (what you wish to see). If not provided, the image will be outpainted without any preset. Avaliable presets: 3d-model, analog-film, anime, cinematic, comic-book, digital-art, enhance, fantasy-art, isometric, line-art, low-poly, modeling-compound, neon-punk, origami, photographic, pixel-art, tile-texture.	❌
seed	int	A specific value that is used to guide the 'randomness' of the generation. If not provided, a random seed is used. Must be a number between 0 and 4294967294.	✅
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 Outpainting in version v1.

• inputs: Google Vision OCR, Label Visualization, LMM For Classification, Blur Visualization, Background Color Visualization, Contrast Equalization, Bounding Box Visualization, Keypoint Visualization, Stability AI Outpainting, Reference Path Visualization, Image Slicer, Pixelate Visualization, Single-Label Classification Model, CSV Formatter, Image Preprocessing, Color Visualization, SIFT Comparison, Object Detection Model, Email Notification, Anthropic Claude, Circle Visualization, Image Contours, Polygon Zone Visualization, Ellipse Visualization, Line Counter, Clip Comparison, Email Notification, VLM as Classifier, Model Monitoring Inference Aggregator, OCR Model, Absolute Static Crop, Depth Estimation, LMM, Morphological Transformation, Roboflow Dataset Upload, Detections Consensus, Crop Visualization, OpenAI, Image Convert Grayscale, Florence-2 Model, CogVLM, Roboflow Custom Metadata, VLM as Detector, Classification Label Visualization, Stitch OCR Detections, Keypoint Detection Model, SIFT Comparison, Line Counter, Camera Calibration, Polygon Visualization, Icon Visualization, Identify Changes, Triangle Visualization, Template Matching, Roboflow Dataset Upload, Anthropic Claude, Model Comparison Visualization, Corner Visualization, Distance Measurement, Florence-2 Model, Google Gemini, Google Gemini, EasyOCR, Line Counter Visualization, Grid Visualization, Halo Visualization, Stability AI Image Generation, Identify Outliers, QR Code Generator, Twilio SMS Notification, Relative Static Crop, Dot Visualization, Llama 3.2 Vision, Image Blur, Slack Notification, OpenAI, Local File Sink, Multi-Label Classification Model, Image Slicer, OpenAI, Stability AI Inpainting, Dynamic Crop, Camera Focus, Pixel Color Count, Webhook Sink, Image Threshold, Instance Segmentation Model, Perspective Correction, Mask Visualization, Trace Visualization, OpenAI, Stitch Images, SIFT
• outputs: Google Vision OCR, Label Visualization, LMM For Classification, Blur Visualization, Background Color Visualization, Contrast Equalization, Reference Path Visualization, Keypoint Visualization, Stability AI Outpainting, Bounding Box Visualization, Image Slicer, Pixelate Visualization, Single-Label Classification Model, Clip Comparison, SAM 3, Perception Encoder Embedding Model, Seg Preview, Byte Tracker, Image Preprocessing, SAM 3, Color Visualization, SIFT Comparison, Qwen2.5-VL, Object Detection Model, Dominant Color, Anthropic Claude, Circle Visualization, Image Contours, Object Detection Model, QR Code Detection, Polygon Zone Visualization, Ellipse Visualization, Email Notification, Clip Comparison, Moondream2, VLM as Classifier, OCR Model, Absolute Static Crop, Depth Estimation, LMM, Time in Zone, Morphological Transformation, Roboflow Dataset Upload, Gaze Detection, Crop Visualization, OpenAI, Florence-2 Model, Barcode Detection, Image Convert Grayscale, SAM 3, CogVLM, VLM as Detector, Multi-Label Classification Model, Classification Label Visualization, Buffer, Keypoint Detection Model, Segment Anything 2 Model, Keypoint Detection Model, YOLO-World Model, Polygon Visualization, CLIP Embedding Model, Camera Calibration, Icon Visualization, Triangle Visualization, Template Matching, Roboflow Dataset Upload, Anthropic Claude, Model Comparison Visualization, Corner Visualization, Florence-2 Model, Google Gemini, Google Gemini, EasyOCR, VLM as Detector, Line Counter Visualization, SmolVLM2, Halo Visualization, Stability AI Image Generation, Relative Static Crop, Dot Visualization, Detections Stitch, Llama 3.2 Vision, Image Blur, OpenAI, Instance Segmentation Model, Multi-Label Classification Model, Image Slicer, OpenAI, Stability AI Inpainting, Dynamic Crop, Single-Label Classification Model, Camera Focus, Pixel Color Count, Detections Stabilizer, Instance Segmentation Model, VLM as Classifier, Mask Visualization, Perspective Correction, Image Threshold, OpenAI, Trace Visualization, Stitch Images, SIFT

Input and Output Bindings

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

Bindings

• input

  • image (image): The image to outpaint..
  • creativity (float_zero_to_one): Creativity parameter for outpainting. Higher values result in more creative outpainting..
  • left (integer): Number of pixels to outpaint on the left side of the image. Max value is 2000..
  • right (integer): Number of pixels to outpaint on the right side of the image. Max value is 2000..
  • up (integer): Number of pixels to outpaint on the top side of the image. Max value is 2000..
  • down (integer): Number of pixels to outpaint on the bottom side of the image. Max value is 2000..
  • prompt (string): Optional prompt to apply when outpainting the image (what you wish to see). If not provided, the image will be outpainted without any prompt..
  • seed (integer): A specific value that is used to guide the 'randomness' of the generation. If not provided, a random seed is used. Must be a number between 0 and 4294967294.
  • api_key (Union[string, secret]): Your Stability AI API key..

• output

  • image (image): Image in workflows.

Example JSON definition of step Stability AI Outpainting in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/stability_ai_outpainting@v1",
    "image": "$inputs.image",
    "creativity": 0.5,
    "left": 200,
    "right": 200,
    "up": 200,
    "down": 200,
    "prompt": "my prompt",
    "preset": "3d-model",
    "seed": 200,
    "api_key": "xxx-xxx"
}