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