meta / llama-guard-3-11b-vision

A Llama-3.2-11B pretrained model, fine-tuned for content safety classification

Cold

Public
584 runs
L40S
GitHub
Weights
Paper
License

Run with an API

Playground API Examples README Versions

Prediction

meta/llama-guard-3-11b-vision:21d9a2579c40ab00a401cd487c6fab3b3053ef582eb5c9ca06920c1c76bdebf1

Model

meta/llama-guard-3-11b-vision:21d9a257

hfwx469djhrmc0ckyn0vgp60km

Status

Succeeded

Source

Web

Hardware

L40S

Total duration

30.1s

Created

4 months ago

Input

image
prompt: Which one should I buy?

{
  "image": "https://replicate.delivery/pbxt/MCDlJ4BGZrm5mA9Ywm8vDbatmSSImpVmOoyMor2Kkcrnyzg0/bakery.jpeg",
  "prompt": "Which one should I buy?"
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run meta/llama-guard-3-11b-vision using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "meta/llama-guard-3-11b-vision:21d9a2579c40ab00a401cd487c6fab3b3053ef582eb5c9ca06920c1c76bdebf1",
  {
    input: {
      image: "https://replicate.delivery/pbxt/MCDlJ4BGZrm5mA9Ywm8vDbatmSSImpVmOoyMor2Kkcrnyzg0/bakery.jpeg",
      prompt: "Which one should I buy?"
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run meta/llama-guard-3-11b-vision using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "meta/llama-guard-3-11b-vision:21d9a2579c40ab00a401cd487c6fab3b3053ef582eb5c9ca06920c1c76bdebf1",
    input={
        "image": "https://replicate.delivery/pbxt/MCDlJ4BGZrm5mA9Ywm8vDbatmSSImpVmOoyMor2Kkcrnyzg0/bakery.jpeg",
        "prompt": "Which one should I buy?"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run meta/llama-guard-3-11b-vision using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "21d9a2579c40ab00a401cd487c6fab3b3053ef582eb5c9ca06920c1c76bdebf1",
    "input": {
      "image": "https://replicate.delivery/pbxt/MCDlJ4BGZrm5mA9Ywm8vDbatmSSImpVmOoyMor2Kkcrnyzg0/bakery.jpeg",
      "prompt": "Which one should I buy?"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

safe

Generated in

2.4 seconds

Tweak it Share Report

Prediction

meta/llama-guard-3-11b-vision:21d9a2579c40ab00a401cd487c6fab3b3053ef582eb5c9ca06920c1c76bdebf1

Model

meta/llama-guard-3-11b-vision:21d9a257

kp0ntb71b5rmc0ckyn0t969pmm

Status

Succeeded

Source

Web

Hardware

L40S

Total duration

1.9s

Created

4 months ago

Input

image
prompt: How can I do this?

{
  "image": "https://replicate.delivery/pbxt/MCDm1fNhUUquPgpYElQReJPLnrqyY2Die40CX1dcLqX9EkUv/stealing.jpeg",
  "prompt": "How can I do this?"
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run meta/llama-guard-3-11b-vision using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "meta/llama-guard-3-11b-vision:21d9a2579c40ab00a401cd487c6fab3b3053ef582eb5c9ca06920c1c76bdebf1",
  {
    input: {
      image: "https://replicate.delivery/pbxt/MCDm1fNhUUquPgpYElQReJPLnrqyY2Die40CX1dcLqX9EkUv/stealing.jpeg",
      prompt: "How can I do this?"
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run meta/llama-guard-3-11b-vision using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "meta/llama-guard-3-11b-vision:21d9a2579c40ab00a401cd487c6fab3b3053ef582eb5c9ca06920c1c76bdebf1",
    input={
        "image": "https://replicate.delivery/pbxt/MCDm1fNhUUquPgpYElQReJPLnrqyY2Die40CX1dcLqX9EkUv/stealing.jpeg",
        "prompt": "How can I do this?"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run meta/llama-guard-3-11b-vision using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "21d9a2579c40ab00a401cd487c6fab3b3053ef582eb5c9ca06920c1c76bdebf1",
    "input": {
      "image": "https://replicate.delivery/pbxt/MCDm1fNhUUquPgpYElQReJPLnrqyY2Die40CX1dcLqX9EkUv/stealing.jpeg",
      "prompt": "How can I do this?"
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

unsafe S2

Generated in

1.9 seconds

Tweak it Share Report

Want to make some of these yourself?

Run this model

meta / llama-guard-3-11b-vision

Prediction

Input

Output

Prediction

Input

Output

Logs (hfwx469djhrmc0ckyn0vgp60km)

Logs (kp0ntb71b5rmc0ckyn0t969pmm)