> For the complete documentation index, see [llms.txt](https://docs.roboflow.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.roboflow.com/workflows/blocks.md).

# Blocks

- [Workflow Blocks](https://docs.roboflow.com/workflows/blocks/blocks.md): Explore the ecosystem of Blocks you can use in a Workflow.
- [Custom Blocks](https://docs.roboflow.com/workflows/blocks/blocks/custom-blocks.md): Write and run your own logic in a Workflow with custom Python blocks.
- [Enterprise](https://docs.roboflow.com/workflows/blocks/blocks/enterprise.md): Connect Roboflow to enterprise systems and protocols.
- [Advanced Blocks](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks.md): Advanced blocks for specific use cases: expressions, caching, embeddings similarity, image slicing, and prediction post-processing.
- [Cache Get](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/cache-get.md): Fetches a previously stored value from a cache entry.
- [Cache Set](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/cache-set.md): Stores a value in a cache entry for later retrieval.
- [Cosine Similarity](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/cosine-similarity.md): Calculate the cosine similarity between two embeddings.
- [Current Time](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/current-time.md): Output the current date and time for a given timezone.
- [Detection Event Log](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/detection-event-log.md): Tracks detection events over time, logging when objects first appear and persist.
- [Detections Classes Replacement](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/detections-classes-replacement.md): Replace classes of detections with classes predicted by a chained classification model.
- [Detections Difference](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/detections-difference.md): Match detections across before/after images and report removed, persisted and new objects.
- [Detections List Roll-Up](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/detections-list-roll-up.md): Roll up multiple levels of dimensionality back to a single dimension.
- [Detections Stitch](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/detections-stitch.md): Merges detections made against multiple pieces of input image into single detection.
- [Dimension Collapse](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/dimension-collapse.md): Collapse dimensionality by aggregating nested data into a single list.
- [Dynamic Zone](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/dynamic-zone.md): Simplify polygons so they are geometrically convex and contain only the requested amount of vertices.
- [Environment Secrets Store](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/environment-secrets-store.md): Fetch secrets from environmental variables.
- [Expression](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/expression.md): Create a specific output based on defined input variables and configured rules.
- [First Non Empty Or Default](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/first-non-empty-or-default.md): Take the first non-empty data element or the configured default value.
- [Image Slicer](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/image-slicer.md): Tile the input image into a list of smaller images to perform small object detection.
- [JSON Parser](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/json-parser.md): Parse raw string into JSON.
- [Model Monitoring Inference Aggregator](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/model-monitoring-inference-aggregator.md): Periodically report an aggregated sample of inference results to Roboflow Model Monitoring.
- [Overlap Analysis](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/overlap-analysis.md): Compute pairwise overlap between two sets of detections.
- [Perspective Correction](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/perspective-correction.md): Adjust detection coordinates from a polygon-defined plane to a straight rectangular plane with specified width and height.
- [Property Definition](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/property-definition.md): Define a variable from model predictions, such as the class names, confidences, or number of detections.
- [Roboflow Custom Metadata](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/roboflow-custom-metadata.md): Add custom metadata to the Roboflow Model Monitoring dashboard.
- [Roboflow Visual Search](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/roboflow-visual-search.md): Find visually similar image candidates in a Roboflow project.
- [Stitch OCR Detections](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/stitch-ocr-detections.md): Combines OCR detection results into a coherent text string by organizing detections spatially.
- [VLM As Classifier](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/vlm-as-classifier.md): Parse a raw string into a classification prediction.
- [VLM As Detector](https://docs.roboflow.com/workflows/blocks/blocks/advanced-blocks/vlm-as-detector.md): Parses raw string into object-detection prediction.
- [Classical Computer Vision](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision.md): Run classical computer vision operations such as blurring, thresholding, contour detection, template matching, and size measurement.
- [Auto Rotate on Edges](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/auto-rotateon-edges.md): Automatically rotate an image so its dominant straight edges become vertical and/or horizontal.
- [Camera Focus](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/camera-focus.md): Calculate a score to indicate how well-focused a camera is.
- [Contrast Enhancement](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/contrast-enhancement.md): Enhance image contrast by normalizing the histogram to use the full dynamic range.
- [Contrast Equalization](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/contrast-equalization.md): Apply contrast equalization to an image.
- [Distance Measurement](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/distance-measurement.md): Calculate the distance between two bounding boxes on a 2D plane.
- [Dominant Color](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/dominant-color.md): Get the dominant color of an image in RGB format.
- [Image Blur](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/image-blur.md): Apply a blur to an image.
- [Image Contours](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/image-contours.md): Find and count the contours on an image.
- [Image Convert Grayscale](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/image-convert-grayscale.md): Convert an RGB image to grayscale.
- [Image Preprocessing](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/image-preprocessing.md): Resize, flip, or rotate an image.
- [Image Threshold](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/image-threshold.md): Apply a threshold to an image.
- [Mask Area Measurement](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/mask-area-measurement.md): Measure the area of detected objects and optionally convert to real-world units.
- [Mask Edge Snap](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/mask-edge-snap.md): Refine instance segmentation masks by snapping edges to detected boundaries.
- [Morphological Transformation](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/morphological-transformation.md): Apply morphological transformation to color images.
- [Nearest Neighbor Detection Match](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/nearest-neighbor-detection-match.md): Find the closest target detection for each query detection using pixel distance.
- [Pixel Color Count](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/pixel-color-count.md): Count the number of pixels that match a specific color within a given tolerance.
- [SIFT Comparison](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/sift-comparison.md): Compare SIFT descriptors from multiple images.
- [SIFT](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/sift.md): Apply SIFT to an image.
- [Size Measurement](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/size-measurement.md): Measure the dimensions of objects in relation to a reference object.
- [Template Matching](https://docs.roboflow.com/workflows/blocks/blocks/classical-computer-vision/template-matching.md): Locate instances of a given template within a specified image.
- [Data Storage](https://docs.roboflow.com/workflows/blocks/blocks/data-storage.md): Save images, predictions, and workflow data to Roboflow, local files, cloud buckets, or external APIs.
- [CSV Formatter](https://docs.roboflow.com/workflows/blocks/blocks/data-storage/csv-formatter.md): Create CSV files with specified columns.
- [Data Aggregator](https://docs.roboflow.com/workflows/blocks/blocks/data-storage/data-aggregator.md): Aggregate workflow data to produce time-based statistics.
- [Local File Sink](https://docs.roboflow.com/workflows/blocks/blocks/data-storage/local-file-sink.md): Save data to a local file.
- [Roboflow Asset Library Attributes](https://docs.roboflow.com/workflows/blocks/blocks/data-storage/roboflow-asset-library-attributes.md): Update attributes and tags for Asset Library images.
- [Roboflow Dataset Upload](https://docs.roboflow.com/workflows/blocks/blocks/data-storage/roboflow-dataset-upload.md): Save images and predictions to your Roboflow Dataset.
- [Roboflow Vision Events](https://docs.roboflow.com/workflows/blocks/blocks/data-storage/roboflow-vision-events.md): Send vision events to the Roboflow Vision Events API.
- [S3 Sink](https://docs.roboflow.com/workflows/blocks/blocks/data-storage/s3-sink.md): Upload data to an AWS S3 bucket.
- [Write Vision Event Bundle](https://docs.roboflow.com/workflows/blocks/blocks/data-storage/vision-event-bundle.md): Write vision events as self-contained tarball bundles to a local directory.
- [Webhook Sink](https://docs.roboflow.com/workflows/blocks/blocks/data-storage/webhook-sink.md): Send a request to a remote API with Workflow results.
- [Logic and Branching](https://docs.roboflow.com/workflows/blocks/blocks/logic-and-branching.md): Control the flow of a Workflow: filter detections, branch on conditions, and combine model outputs.
- [Continue If](https://docs.roboflow.com/workflows/blocks/blocks/logic-and-branching/continue-if.md): Conditionally stop execution of a branch.
- [Delta Filter](https://docs.roboflow.com/workflows/blocks/blocks/logic-and-branching/delta-filter.md): Allow the execution of workflow to proceed if the input value has changed.
- [Detections Consensus](https://docs.roboflow.com/workflows/blocks/blocks/logic-and-branching/detections-consensus.md): Combine predictions from multiple detections models to make a decision about object presence.
- [Detections Filter](https://docs.roboflow.com/workflows/blocks/blocks/logic-and-branching/detections-filter.md): Conditionally filter out model predictions.
- [Inner Workflow](https://docs.roboflow.com/workflows/blocks/blocks/logic-and-branching/inner-workflow.md): Run a nested workflow definition with parameters mapped from the parent workflow.
- [Overlap Filter](https://docs.roboflow.com/workflows/blocks/blocks/logic-and-branching/overlap-filter.md): Filter objects overlapping some other class
- [Per-Class Confidence Filter](https://docs.roboflow.com/workflows/blocks/blocks/logic-and-branching/per-class-confidence-filter.md): Filter detections by applying a per-class confidence threshold.
- [Rate Limiter](https://docs.roboflow.com/workflows/blocks/blocks/logic-and-branching/rate-limiter.md): Limits the rate at which a branch of the Workflow will run.
- [Switch Case](https://docs.roboflow.com/workflows/blocks/blocks/logic-and-branching/switch-case.md): Route execution to one of several branches based on the value of an input.
- [Notifications](https://docs.roboflow.com/workflows/blocks/blocks/notifications.md): Send alerts from a Workflow over email, Slack, or SMS/MMS.
- [Email Notification](https://docs.roboflow.com/workflows/blocks/blocks/notifications/email-notification.md): Send notification via e-mail.
- [Slack Notification](https://docs.roboflow.com/workflows/blocks/blocks/notifications/slack-notification.md): Send notification via Slack.
- [Twilio SMS Notification](https://docs.roboflow.com/workflows/blocks/blocks/notifications/twilio-sms-notification.md): Send notification via Twilio SMS service.
- [Twilio SMS/MMS Notification](https://docs.roboflow.com/workflows/blocks/blocks/notifications/twilio-smsmms-notification.md): Send SMS/MMS notifications via Twilio.
- [Run a Model](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model.md): Run fine-tuned models trained on Roboflow, foundation models, and third-party VLMs and LLMs directly in a Workflow.
- [Anthropic Claude](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/anthropic-claude.md): You can call the Anthropic's Claude API from a Workflow.
- [Barcode Detection](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/barcode-detection.md): Detect and read barcodes in an image.
- [Clip Comparison](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/clip-comparison.md): Compare CLIP image and text embeddings.
- [CLIP Embedding Model](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/clip-embedding-model.md): Generate an embedding of an image or string.
- [CogVLM](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/cog-vlm.md): DEPRECATED! Run a self-hosted vision language model.
- [Cosmos 3](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/cosmos3.md): Reason about physical scenes with NVIDIA Cosmos 3.
- [Depth Estimation](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/depth-estimation.md): Run Depth Estimation on an image.
- [EasyOCR](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/easy-ocr.md): Extract text from an image using EasyOCR optical character recognition.
- [Florence-2 Model](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/florence2-model.md): Run Florence-2 on an image
- [Gaze Detection](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/gaze-detection.md): Detect faces and estimate gaze direction (deprecated).
- [GLM-OCR](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/glmocr.md): Run GLM-OCR on an image to recognize text.
- [Google Gemini](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/google-gemini.md): Run Google's Gemini model with vision capabilities.
- [Google Gemma API](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/google-gemma-api.md): Run Google's Gemma model with vision capabilities via OpenRouter.
- [Google Gemma](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/google-gemma.md): Run Google's Gemma model with vision capabilities via OpenRouter.
- [Google Vision OCR](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/google-vision-ocr.md): Detect text in images using Google Vision API
- [Instance Segmentation Model](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/instance-segmentation-model.md): Predict the shape, size, and location of objects.
- [Keypoint Detection Model](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/keypoint-detection-model.md): Predict skeletons on objects.
- [Llama 3.2 Vision](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/llama3-2-vision.md): Run Llama 3.2 Vision via OpenRouter.
- [LMM For Classification](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/lmm-for-classification.md): Run a large multimodal model such as ChatGPT-4v for classification.
- [LMM](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/lmm.md): Run a large multimodal model such as ChatGPT-4v.
- [Moondream2](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/moondream2.md): Run Moondream2 on an image.
- [MoonshotAI Kimi](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/moonshot-ai-kimi.md): Run Moonshot AI Kimi vision-language models via OpenRouter.
- [Multi-Label Classification Model](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/multi-label-classification-model.md): Apply multiple tags to an image.
- [Object Detection Model](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/object-detection-model.md): Run an object detection model in a Workflow.
- [OCR Model](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/ocr-model.md): Extract text from an image using DocTR optical character recognition.
- [OpenAI-Compatible LLM](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/open-ai-compatible-llm.md): Send prompts to any OpenAI-compatible API endpoint.
- [OpenAI](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/open-ai.md): Run OpenAI's GPT models with vision capabilities.
- [OpenRouter](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/open-router.md): Run any OpenRouter model by pasting its model slug.
- [Perception Encoder Embedding Model](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/perception-encoder-embedding-model.md): Generate an embedding of an image or string.
- [PP-OCR](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/ppocr.md): Extract text from an image using PP-OCR (PaddleOCR) optical character recognition.
- [QR Code Detection](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/qr-code-detection.md): Detect and read QR codes in an image.
- [Qwen-VL](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/qwen-vl.md): Run any Qwen vision model - natively or via OpenRouter.
- [Qwen2.5-VL](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/qwen2-5-vl.md): Run Qwen2.5-VL on an image.
- [Qwen 3.5 API](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/qwen3-5-api.md): Run Qwen 3.5 vision-language models via OpenRouter.
- [Qwen3.5-VL](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/qwen3-5-vl.md): Run Qwen3.5-VL on an image.
- [Qwen3.5](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/qwen3-5.md): Run Qwen3.5 on an image.
- [Qwen 3.6 API](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/qwen3-6-api.md): Run Qwen 3.6 vision-language models via OpenRouter.
- [Qwen3-VL](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/qwen3-vl.md): Run Qwen3-VL on an image.
- [Roboflow Visual Search Classifier](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/roboflow-visual-search-classifier.md): Classify an image by finding the most visually similar annotated image.
- [SAM 3 Interactive](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/sam3-interactive.md): Segment a specific object with SAM3 using point and/or bounding box prompts.
- [SAM 3](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/sam3.md): Run SAM3 with text prompts for zero-shot segmentation.
- [Seg Preview](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/seg-preview.md): Seg Preview
- [Segment Anything 2 Model](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/segment-anything2-model.md): Convert bounding boxes to polygons, or run SAM2 on an entire image to generate a mask.
- [Semantic Segmentation Model](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/semantic-segmentation-model.md): Assign a class label to every pixel in the image.
- [Single-Label Classification Model](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/single-label-classification-model.md): Run a single-label classification model in a Workflow.
- [SmolVLM2](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/smol-vlm2.md): Run SmolVLM2 on an image.
- [SpaceXAI](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/spacexai.md): Run SpaceXAI Grok models with vision capabilities.
- [Stability AI Image Generation](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/stability-ai-image-generation.md): generate new images from text, or create variations of existing images.
- [Stability AI Inpainting](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/stability-ai-inpainting.md): Use segmentation masks to inpaint objects within an image.
- [Stability AI Outpainting](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/stability-ai-outpainting.md): Use object detection bounding box to crop the image and to outpaint within given directions.
- [YOLO-World Model](https://docs.roboflow.com/workflows/blocks/blocks/run-a-model/yolo-world-model.md): Run a zero-shot object detection model.
- [Transformations](https://docs.roboflow.com/workflows/blocks/blocks/transformations.md): Manipulate images and prediction data: crop, merge, offset, project, and stitch detections and images.
- [Absolute Static Crop](https://docs.roboflow.com/workflows/blocks/blocks/transformations/absolute-static-crop.md): Crop an image using fixed pixel coordinates.
- [Bounding Rectangle](https://docs.roboflow.com/workflows/blocks/blocks/transformations/bounding-rectangle.md): Find the minimal bounding box surrounding the detected polygon.
- [Camera Calibration](https://docs.roboflow.com/workflows/blocks/blocks/transformations/camera-calibration.md): Remove camera lens distortions from an image using a calibration table.
- [Detection Offset](https://docs.roboflow.com/workflows/blocks/blocks/transformations/detection-offset.md): Add padding around detected regions.
- [Detections Combine](https://docs.roboflow.com/workflows/blocks/blocks/transformations/detections-combine.md): Combines two sets of predictions into a single prediction.
- [Detections Merge](https://docs.roboflow.com/workflows/blocks/blocks/transformations/detections-merge.md): Merge multiple detections into a single bounding box.
- [Detections Transformation](https://docs.roboflow.com/workflows/blocks/blocks/transformations/detections-transformation.md): Apply transformations on detected bounding boxes.
- [Dynamic Crop](https://docs.roboflow.com/workflows/blocks/blocks/transformations/dynamic-crop.md): Crop an image using bounding boxes from a detection model.
- [GeoTag Detection](https://docs.roboflow.com/workflows/blocks/blocks/transformations/geo-tag-detection.md): Project detections from pixel coordinates to real-world GPS positions.
- [QR Code Generator](https://docs.roboflow.com/workflows/blocks/blocks/transformations/qr-code-generator.md): Generate a QR code image from text input.
- [Relative Static Crop](https://docs.roboflow.com/workflows/blocks/blocks/transformations/relative-static-crop.md): Crop an image proportional (%) to its dimensions.
- [Stitch Images](https://docs.roboflow.com/workflows/blocks/blocks/transformations/stitch-images.md): Stitch two images by common parts.
- [Video Processing](https://docs.roboflow.com/workflows/blocks/blocks/video-processing.md): Analyze video with object tracking, time-in-zone analysis, line crossing, motion detection, and velocity estimation.
- [Background Subtraction](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/background-subtraction.md): Subtract an image from its background history.
- [BoT-SORT Tracker](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/bo-tsort-tracker.md): ByteTrack-style association with optional camera motion compensation (BoT-SORT).
- [Buffer](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/buffer.md): Returns an array of the last \`length\` values passed to it.
- [ByteTrack Tracker](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/byte-track-tracker.md): Tracks objects across frames. Best for most scenes.
- [Byte Tracker](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/byte-tracker.md): Track and update object positions across video frames using ByteTrack.
- [Detections Stabilizer](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/detections-stabilizer.md): Apply a smoothing algorithm to reduce noise and flickering across video frames.
- [Frame Delay](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/frame-delay.md): Reference a value from an earlier frame of the same video stream (N-k, into the past).
- [Identify Changes](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/identify-changes.md): Identify changes compared to prior data via embeddings.
- [Identify Outliers](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/identify-outliers.md): Identify outlier embeddings compared to prior data.
- [Image Stack](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/image-stack.md): Accumulate compressed video frames into a fixed-size FIFO stack.
- [Line Counter](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/line-counter.md): Count detections passing a line.
- [Motion Detection](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/motion-detection.md): Detect motion in a video using OpenCV.
- [OC-SORT Tracker](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/ocsort-tracker.md): Tracks objects through occlusion and unpredictable movement.
- [Path Deviation](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/path-deviation.md): Calculate Fréchet distance of object from the reference path.
- [PTZ Tracking (ONVIF)](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/ptz-trackingonvif.md): Control an ONVIF compatible PTZ camera to follow an object
- [SAM2 Video Tracker](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/sam2-video-tracker.md): Segment and track objects across video frames with SAM2's streaming camera predictor.
- [SAM3 Video Tracker](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/sam3-video-tracker.md): Segment and track objects across video frames from text prompts with SAM3's streaming concept tracker.
- [SORT Tracker](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/sort-tracker.md): Fast, lightweight object tracking. Works best when objects are clearly visible.
- [Time in Zone](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/timein-zone.md): Track object time in zone.
- [Track Class Lock](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/track-class-lock.md): Lock the class of each tracked object by majority voting to eliminate class flicker.
- [Velocity](https://docs.roboflow.com/workflows/blocks/blocks/video-processing/velocity.md): Calculate the velocity and speed of tracked objects with smoothing and unit conversion.
- [Visualize Predictions](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions.md): Use visualization blocks to draw model predictions - boxes, masks, labels, and more - onto an image.
- [Background Color Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/background-color-visualization.md): Draw a colour in regions not detected by a model.
- [Blur Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/blur-visualization.md): Blur detected objects in an image.
- [Bounding Box Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/bounding-box-visualization.md): Show bounding boxes from an object detection model on an image.
- [Circle Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/circle-visualization.md): Draw a circle around a detected region in an image.
- [Classification Label Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/classification-label-visualization.md): The Classification Label Visualization block adds a classification model's predicted label to an image.
- [Color Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/color-visualization.md): Paint a solid color on detected objects in an image.
- [Corner Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/corner-visualization.md): Draw the corners of detected objects in an image.
- [Crop Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/crop-visualization.md): The Crop Visualization block crops detected regions from an image and enlarges them to highlight detections.
- [Dot Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/dot-visualization.md): Draw dots on an image at specific coordinates based on provided detections.
- [Ellipse Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/ellipse-visualization.md): Draw ellipses that highlight detected objects in an image.
- [Grid Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/grid-visualization.md): Shows an array of images in a grid.
- [Halo Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/halo-visualization.md): Paint a halo around detected objects in an image.
- [Heatmap Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/heatmap-visualization.md): Draw a heatmap based on detections in an image.
- [Icon Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/icon-visualization.md): Draw icons on an image either at specific static coordinates or dynamically based on detections.
- [Keypoint Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/keypoint-visualization.md): Draw keypoints on detected objects in an image.
- [Label Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/label-visualization.md): Show labels from a model on an image.
- [Line Counter Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/line-counter-visualization.md): Apply a mask over a line zone in an image.
- [Mask Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/mask-visualization.md): Apply a mask over detected objects in an image.
- [Model Comparison Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/model-comparison-visualization.md): Visualize the difference between two models' detections.
- [Pixelate Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/pixelate-visualization.md): Pixelate detected objects in an image.
- [Polygon Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/polygon-visualization.md): Draw a polygon around detected objects in an image.
- [Polygon Zone Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/polygon-zone-visualization.md): Apply a mask over a polygon zone in an image.
- [Reference Path Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/reference-path-visualization.md): Draw a reference path in the image.
- [Text Display](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/text-display.md): Display customizable text on an image with styling and positioning options.
- [Trace Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/trace-visualization.md): Draw traces based on detections tracking results.
- [Triangle Visualization](https://docs.roboflow.com/workflows/blocks/blocks/visualize-predictions/triangle-visualization.md): Draw triangle markers on an image at specific coordinates based on provided detections.
- [Blocks Governance](https://docs.roboflow.com/workflows/blocks/blocks-governance.md): Fine grained control of enabled workflow blocks on a workspace