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:
Anthropic Claude
,Crop Visualization
,SIFT
,Stitch OCR Detections
,LMM For Classification
,Blur Visualization
,Line Counter Visualization
,Color Visualization
,Image Contours
,Camera Focus
,Mask Visualization
,Image Convert Grayscale
,Circle Visualization
,Google Gemini
,Cosine Similarity
,Absolute Static Crop
,VLM as Classifier
,Object Detection Model
,Dynamic Zone
,Stitch Images
,Trace Visualization
,Image Preprocessing
,Roboflow Custom Metadata
,OCR Model
,Clip Comparison
,Polygon Zone Visualization
,LMM
,QR Code Generator
,Size Measurement
,Halo Visualization
,Perspective Correction
,Florence-2 Model
,Stability AI Inpainting
,Buffer
,Label Visualization
,Webhook Sink
,VLM as Detector
,Stability AI Image Generation
,Triangle Visualization
,Keypoint Detection Model
,Background Color Visualization
,Relative Static Crop
,Slack Notification
,Corner Visualization
,Multi-Label Classification Model
,Icon Visualization
,Pixelate Visualization
,Image Blur
,Gaze Detection
,Model Comparison Visualization
,CSV Formatter
,Instance Segmentation Model
,Llama 3.2 Vision
,Image Threshold
,Google Vision OCR
,Reference Path Visualization
,Image Slicer
,Roboflow Dataset Upload
,CogVLM
,Depth Estimation
,Roboflow Dataset Upload
,Single-Label Classification Model
,OpenAI
,Classification Label Visualization
,Polygon Visualization
,Stability AI Outpainting
,Keypoint Visualization
,Dot Visualization
,Email Notification
,Grid Visualization
,Local File Sink
,OpenAI
,Bounding Box Visualization
,Camera Calibration
,Ellipse Visualization
,OpenAI
,Florence-2 Model
,Model Monitoring Inference Aggregator
,Image Slicer
,Twilio SMS Notification
,SIFT Comparison
,Dimension Collapse
,Identify Changes
,Clip Comparison
,Dynamic Crop
- outputs:
Anthropic Claude
,Crop Visualization
,Line Counter
,Line Counter
,LMM For Classification
,PTZ Tracking (ONVIF)
.md),Line Counter Visualization
,Color Visualization
,Cache Set
,Mask Visualization
,Circle Visualization
,Google Gemini
,VLM as Classifier
,Object Detection Model
,Keypoint Detection Model
,Detections Consensus
,Trace Visualization
,Image Preprocessing
,Roboflow Custom Metadata
,Object Detection Model
,Cache Get
,JSON Parser
,Clip Comparison
,Polygon Zone Visualization
,LMM
,QR Code Generator
,YOLO-World Model
,Size Measurement
,Halo Visualization
,CLIP Embedding Model
,Florence-2 Model
,Moondream2
,Perspective Correction
,Stability AI Inpainting
,Buffer
,Webhook Sink
,Label Visualization
,Distance Measurement
,VLM as Detector
,Pixel Color Count
,Segment Anything 2 Model
,Perception Encoder Embedding Model
,Stability AI Image Generation
,Triangle Visualization
,Keypoint Detection Model
,Background Color Visualization
,Slack Notification
,Corner Visualization
,Path Deviation
,Icon Visualization
,Image Blur
,Model Comparison Visualization
,VLM as Detector
,Llama 3.2 Vision
,Instance Segmentation Model
,Time in Zone
,Image Threshold
,Google Vision OCR
,Reference Path Visualization
,VLM as Classifier
,Roboflow Dataset Upload
,CogVLM
,Roboflow Dataset Upload
,OpenAI
,Classification Label Visualization
,Polygon Visualization
,Stability AI Outpainting
,Keypoint Visualization
,Dot Visualization
,Time in Zone
,Email Notification
,Grid Visualization
,Local File Sink
,OpenAI
,Bounding Box Visualization
,Detections Classes Replacement
,Ellipse Visualization
,OpenAI
,Florence-2 Model
,Path Deviation
,Model Monitoring Inference Aggregator
,Twilio SMS Notification
,Instance Segmentation Model
,SIFT Comparison
,Detections Stitch
,Clip Comparison
,Dynamic Crop
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>"
}