Use LMM to Build Computer Vision Pipelines and Applications

Workflows allows you to integrate LMM with models, logic, and applications.

Build a Workflow

Connect LMM to other blocks to build a custom workflow

Ask a question to a Large Multimodal Model (LMM) with an image and text. You can specify arbitrary text prompts to an LMMBlock. The LLMBlock supports two LMMs: - OpenAI's GPT-4 with Vision, and; - CogVLM. You need to provide your OpenAI API key to use the GPT-4 with Vision model. You do not need to provide an API key to use CogVLM. _If you want to classify an image into one or more categories, we recommend using the dedicated LMMForClassificationBlock._

Start a Workflow

Filter

Conditionally filter and output data fields based on boolean conditions from a preceding workflow step.

AWS Secrets Retriever

Retrieve and manage secrets from AWS Secrets Manager for use in workflow automation.

GPT-4 with Vision

GPT-4 with Vision is a type of LMM.

CogVLM

CogVLM is a type of LMM.

YOLOv8 Classification

YOLOv8 Classification is a type of Roboflow Classification Model.

YOLOv8 Keypoint Detection

YOLOv8 Keypoint Detection is a type of Roboflow Keypoint Detection Model.

YOLOv7 Instance Segmentation

YOLOv7 Instance Segmentation is a type of Roboflow Instance Segmentation Model.

YOLOv8 Instance Segmentation

YOLOv8 Instance Segmentation is a type of Roboflow Instance Segmentation Model.

YOLOv5 Instance Segmentation

YOLOv5 Instance Segmentation is a type of Roboflow Instance Segmentation Model.

YOLOv5

YOLOv5 is a type of Roboflow Object Detection Model.

YOLO-NAS

YOLO-NAS is a type of Roboflow Object Detection Model.

YOLOv9

YOLOv9 is a type of Roboflow Object Detection Model.

YOLOv8

YOLOv8 is a type of Roboflow Object Detection Model.

Relative Static Crop

Use relative coordinates for cropping.

Crop

Create dynamic crops from a detections model.

Absolute Static Crop

Use absolute coordinates for cropping.

Model

LMM

Run a large language model.

Webhook Publish

Securely transmit data to specified webhooks using HMAC-SHA512 for payload authentication, ensuring data integrity and confidentiality.

Filter

Conditionally filter and output data fields based on boolean conditions from a preceding workflow step.

Kafka Publish

Publish data to a Kafka topic, with server connection and topic configuration, ensuring data propagation within distributed systems.

GPT-4 with Vision

GPT-4 with Vision is a type of LMM.

CogVLM

CogVLM is a type of LMM.

YOLOv8 Classification

YOLOv8 Classification is a type of Roboflow Classification Model.

YOLOv8 Keypoint Detection

YOLOv8 Keypoint Detection is a type of Roboflow Keypoint Detection Model.

YOLOv7 Instance Segmentation

YOLOv7 Instance Segmentation is a type of Roboflow Instance Segmentation Model.

YOLOv8 Instance Segmentation

YOLOv8 Instance Segmentation is a type of Roboflow Instance Segmentation Model.

YOLOv5 Instance Segmentation

YOLOv5 Instance Segmentation is a type of Roboflow Instance Segmentation Model.

YOLOv5

YOLOv5 is a type of Roboflow Object Detection Model.

YOLO-NAS

YOLO-NAS is a type of Roboflow Object Detection Model.

YOLOv9

YOLOv9 is a type of Roboflow Object Detection Model.

YOLOv8

YOLOv8 is a type of Roboflow Object Detection Model.

Detection Offset

Apply a fixed offset on the width and height of detections.

Detection Filter

Filter predictions from detection models based on defined conditions.

Detections Consensus

Combine predictions from multiple detections models to make a decision about object presence.

Build a Custom Vision AI Application

Connect pre-trained models, open source models, LLM APIs, advanced logic, and external applications. Deploy as an API endpoint, on-prem, or at the edge.

Filter

Transformation

Filter

Conditionally filter and output data fields based on boolean conditions from a preceding workflow step.

This is some text inside of a div block.

AWS Secrets Retriever

Transformation

AWS Secrets Retriever

Retrieve and manage secrets from AWS Secrets Manager for use in workflow automation.

This is some text inside of a div block.

GPT-4 with Vision

Model

GPT-4 with Vision

GPT-4 with Vision is a type of LMM.

This is some text inside of a div block.

CogVLM

Model

CogVLM

CogVLM is a type of LMM.

This is some text inside of a div block.

YOLOv8 Classification

Model

YOLOv8 Classification

YOLOv8 Classification is a type of Roboflow Classification Model.

This is some text inside of a div block.

YOLOv8 Keypoint Detection

Model

YOLOv8 Keypoint Detection

YOLOv8 Keypoint Detection is a type of Roboflow Keypoint Detection Model.

This is some text inside of a div block.

Webhook Publish

Sink

Webhook Publish

Securely transmit data to specified webhooks using HMAC-SHA512 for payload authentication, ensuring data integrity and confidentiality.

This is some text inside of a div block.

Filter

Transformation

Filter

Conditionally filter and output data fields based on boolean conditions from a preceding workflow step.

This is some text inside of a div block.

Kafka Publish

Transformation

Kafka Publish

Publish data to a Kafka topic, with server connection and topic configuration, ensuring data propagation within distributed systems.

This is some text inside of a div block.

GPT-4 with Vision

Model

GPT-4 with Vision

GPT-4 with Vision is a type of LMM.

This is some text inside of a div block.

CogVLM

Model

CogVLM

CogVLM is a type of LMM.

This is some text inside of a div block.

YOLOv8 Classification

Model

YOLOv8 Classification

YOLOv8 Classification is a type of Roboflow Classification Model.

This is some text inside of a div block.

Find Other Blocks in the Model Category

GPT-4 with Vision

GPT-4 with Vision is a type of LMM.

CogVLM

CogVLM is a type of LMM.

YOLOv8 Classification

YOLOv8 Classification is a type of Roboflow Classification Model.

YOLOv8 Keypoint Detection

YOLOv8 Keypoint Detection is a type of Roboflow Keypoint Detection Model.

YOLOv7 Instance Segmentation

YOLOv7 Instance Segmentation is a type of Roboflow Instance Segmentation Model.

YOLOv8 Instance Segmentation

YOLOv8 Instance Segmentation is a type of Roboflow Instance Segmentation Model.

YOLOv5 Instance Segmentation

YOLOv5 Instance Segmentation is a type of Roboflow Instance Segmentation Model.

YOLOv5

YOLOv5 is a type of Roboflow Object Detection Model.

YOLO-NAS

YOLO-NAS is a type of Roboflow Object Detection Model.

YOLOv9

YOLOv9 is a type of Roboflow Object Detection Model.

YOLOv8

YOLOv8 is a type of Roboflow Object Detection Model.

QR Code Detector

Detect the location of QR codes in an image.

Barcode Detector

Run Optical Character Recognition on a model.

Roboflow Object Detection Model

Detect objects using an object detection model.

Roboflow Multi Label Classification Model

Run a multi-label classification model.

Roboflow Classification Model

Run a classification model.

Roboflow Keypoint Detection Model

Run inference on a keypoint detection model.

Roboflow Instance Segmentation Model

Run an instance segmentation model.

Yolo World Model

Run a zero-shot object detection model.

OCR Model

Run Optical Character Recognition on a model.

LMM For Classification

Run a large language model for classification.

Clip Comparison

Compare CLIP image and text embeddings.

This is some text inside of a div block.

Explore Popular Combinations Using LMM

No items found.

Customize Your Pipeline

Connect models from OpenAI or Meta AI, applications like Slack or Pager Duty, and logic like filtering or cropping.

View All Blocks