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

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"
}