Llama 3.2 Vision¶
Class: LlamaVisionBlockV1
Source: inference.core.workflows.core_steps.models.foundation.llama_vision.v1.LlamaVisionBlockV1
Ask a question to Llama 3.2 Vision model with vision capabilities.
You can specify arbitrary text prompts or predefined ones, the block supports the following types of prompt:
-
Open Prompt (
unconstrained
) - Use any prompt to generate a raw response -
Text Recognition (OCR) (
ocr
) - Model recognizes text in the image -
Visual Question Answering (
visual-question-answering
) - Model answers the question you submit in the prompt -
Captioning (short) (
caption
) - Model provides a short description of the image -
Captioning (
detailed-caption
) - Model provides a long description of the image -
Single-Label Classification (
classification
) - Model classifies the image content as one of the provided classes -
Multi-Label Classification (
multi-label-classification
) - Model classifies the image content as one or more of the provided classes -
Structured Output Generation (
structured-answering
) - Model returns a JSON response with the specified fields
Issues with structured prompting
Model tends to be quite unpredictable when structured output (in our case JSON document) is expected.
That problems may impact tasks like structured-answering
, classification
or multi-label-classification
.
The cause seems to be quite sensitive "filters" of inappropriate content embedded in model.
🛠️ API providers and model variants¶
Llama Vision 3.2 model is exposed via OpenRouter API and we require passing OpenRouter API Key to run.
There are different versions of the model supported:
-
smaller version (
11B
) is faster and cheaper, yet you can expect better quality of results using90B
version -
Regular
version is paid (and usually faster) API, whereasFree
is free for use for OpenRouter clients (state at 01.01.2025)
As for now, OpenRouter is the only provider for Llama 3.2 Vision model, but we will keep you posted if the state of the matter changes.
API Usage Charges
OpenRouter is external third party providing access to the model and incurring charges on the usage. Please check out pricing before use:
💡 Further reading and Acceptable Use Policy¶
Model license
Check out model license before use.
Click here for the original model card.
Usage of this model is subject to Meta's Acceptable Use Policy.
Type identifier¶
Use the following identifier in step "type"
field: roboflow_core/llama_3_2_vision@v1
to add the block as
as step in your workflow.
Properties¶
Name | Type | Description | Refs |
---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
task_type |
str |
Task type to be performed by model. Value determines required parameters and output response.. | ❌ |
prompt |
str |
Text prompt to the Llama model. | ✅ |
output_structure |
Dict[str, str] |
Dictionary with structure of expected JSON response. | ❌ |
classes |
List[str] |
List of classes to be used. | ✅ |
api_key |
str |
Your Llama Vision API key (dependent on provider, ex: OpenRouter API key). | ✅ |
model_version |
str |
Model to be used. | ✅ |
max_tokens |
int |
Maximum number of tokens the model can generate in it's response.. | ❌ |
temperature |
float |
Temperature to sample from the model - value in range 0.0-2.0, the higher - the more random / "creative" the generations are.. | ✅ |
max_concurrent_requests |
int |
Number of concurrent requests that can be executed by block when batch of input images provided. If not given - block defaults to value configured globally in Workflows Execution Engine. Please restrict if you hit limits.. | ❌ |
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 Llama 3.2 Vision
in version v1
.
- inputs:
Keypoint Visualization
,Google Gemini
,Keypoint Detection Model
,Image Contours
,Circle Visualization
,Image Threshold
,Absolute Static Crop
,Perspective Correction
,Color Visualization
,Gaze Detection
,Instance Segmentation Model
,Reference Path Visualization
,Stitch Images
,Image Blur
,Florence-2 Model
,Blur Visualization
,Local File Sink
,Relative Static Crop
,Halo Visualization
,Clip Comparison
,Cosine Similarity
,Stability AI Inpainting
,SIFT Comparison
,Icon Visualization
,Roboflow Custom Metadata
,Dimension Collapse
,Polygon Zone Visualization
,Depth Estimation
,Stability AI Image Generation
,Dynamic Zone
,Dynamic Crop
,Grid Visualization
,Crop Visualization
,Stitch OCR Detections
,Camera Calibration
,VLM as Classifier
,QR Code Generator
,SIFT
,Size Measurement
,Camera Focus
,Model Comparison Visualization
,Twilio SMS Notification
,Llama 3.2 Vision
,Triangle Visualization
,Line Counter Visualization
,Clip Comparison
,Email Notification
,LMM
,Roboflow Dataset Upload
,CSV Formatter
,Image Slicer
,Mask Visualization
,Single-Label Classification Model
,OCR Model
,Pixelate Visualization
,Webhook Sink
,Object Detection Model
,Slack Notification
,Dot Visualization
,Image Slicer
,Roboflow Dataset Upload
,Classification Label Visualization
,OpenAI
,Model Monitoring Inference Aggregator
,Polygon Visualization
,OpenAI
,Buffer
,LMM For Classification
,Stability AI Outpainting
,Trace Visualization
,Bounding Box Visualization
,Image Preprocessing
,Multi-Label Classification Model
,Image Convert Grayscale
,Google Vision OCR
,Label Visualization
,CogVLM
,Corner Visualization
,Background Color Visualization
,Florence-2 Model
,Identify Changes
,VLM as Detector
,Ellipse Visualization
,OpenAI
,Anthropic Claude
- outputs:
Keypoint Visualization
,Google Gemini
,Keypoint Detection Model
,Circle Visualization
,Path Deviation
,Image Threshold
,Perspective Correction
,Color Visualization
,Instance Segmentation Model
,Reference Path Visualization
,Image Blur
,Florence-2 Model
,PTZ Tracking (ONVIF)
.md),Local File Sink
,Keypoint Detection Model
,Halo Visualization
,Clip Comparison
,Stability AI Inpainting
,SIFT Comparison
,Cache Get
,Icon Visualization
,Time in Zone
,Roboflow Custom Metadata
,Polygon Zone Visualization
,Instance Segmentation Model
,Stability AI Image Generation
,Dynamic Crop
,Grid Visualization
,Crop Visualization
,Time in Zone
,Detections Consensus
,VLM as Classifier
,Segment Anything 2 Model
,Perception Encoder Embedding Model
,VLM as Classifier
,Pixel Color Count
,QR Code Generator
,Size Measurement
,Model Comparison Visualization
,Twilio SMS Notification
,CLIP Embedding Model
,Object Detection Model
,Llama 3.2 Vision
,Line Counter Visualization
,Triangle Visualization
,Clip Comparison
,Email Notification
,LMM
,Roboflow Dataset Upload
,Time in Zone
,Path Deviation
,Mask Visualization
,JSON Parser
,Webhook Sink
,Object Detection Model
,Slack Notification
,Cache Set
,Dot Visualization
,Roboflow Dataset Upload
,Detections Classes Replacement
,YOLO-World Model
,Classification Label Visualization
,OpenAI
,Model Monitoring Inference Aggregator
,VLM as Detector
,Polygon Visualization
,OpenAI
,Buffer
,LMM For Classification
,Trace Visualization
,Stability AI Outpainting
,Line Counter
,Bounding Box Visualization
,Distance Measurement
,Moondream2
,Image Preprocessing
,Google Vision OCR
,Label Visualization
,Line Counter
,CogVLM
,Corner Visualization
,Detections Stitch
,Background Color Visualization
,Florence-2 Model
,VLM as Detector
,Ellipse Visualization
,OpenAI
,Anthropic Claude
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Llama 3.2 Vision
in version v1
has.
Bindings
-
input
images
(image
): The image to infer on..prompt
(string
): Text prompt to the Llama model.classes
(list_of_values
): List of classes to be used.api_key
(string
): Your Llama Vision API key (dependent on provider, ex: OpenRouter API key).model_version
(string
): Model to be used.temperature
(float
): Temperature to sample from the model - value in range 0.0-2.0, the higher - the more random / "creative" the generations are..
-
output
output
(Union[string
,language_model_output
]): String value ifstring
or LLM / VLM output iflanguage_model_output
.classes
(list_of_values
): List of values of any type.
Example JSON definition of step Llama 3.2 Vision
in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/llama_3_2_vision@v1",
"images": "$inputs.image",
"task_type": "<block_does_not_provide_example>",
"prompt": "my prompt",
"output_structure": {
"my_key": "description"
},
"classes": [
"class-a",
"class-b"
],
"api_key": "xxx-xxx",
"model_version": "11B (Free) - OpenRouter",
"max_tokens": "<block_does_not_provide_example>",
"temperature": "<block_does_not_provide_example>",
"max_concurrent_requests": "<block_does_not_provide_example>"
}