cuuupid / qwen2-vl-2b

SOTA open-source model for chatting with videos and the newest model in the Qwen family

Cold

Public
576 runs
A100 (80GB)
GitHub
Paper
License

Iterate in playground

Run with an API

Playground API Examples README Versions

Prediction

cuuupid/qwen2-vl-2b:d312c2be33a5ec3ab4787973aae74a485e194f4fccf106086b637afd6dd694b4

Model

cuuupid/qwen2-vl-2b:d312c2be

f2des9xkpnrj00chmt1sf9mdgw

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

16.4s

Created

11 months ago

Input

video
width: 128
height: 128
prompt: Describe the video in great detail.
max_tokens: 512
temperature: 0.7
max_duration: 180

{
  "video": "https://replicate.delivery/pbxt/LXVISWYD8Od0I7w6EW5VIO3sycOIcukn6H26wrkaOX95RK7E/dod_classification_training.mp4",
  "width": 128,
  "height": 128,
  "prompt": "Describe the video in great detail.",
  "max_tokens": 512,
  "temperature": 0.7,
  "max_duration": 180
}

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 cuuupid/qwen2-vl-2b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "cuuupid/qwen2-vl-2b:d312c2be33a5ec3ab4787973aae74a485e194f4fccf106086b637afd6dd694b4",
  {
    input: {
      video: "https://replicate.delivery/pbxt/LXVISWYD8Od0I7w6EW5VIO3sycOIcukn6H26wrkaOX95RK7E/dod_classification_training.mp4",
      width: 128,
      height: 128,
      prompt: "Describe the video in great detail.",
      max_tokens: 512,
      temperature: 0.7,
      max_duration: 180
    }
  }
);

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 cuuupid/qwen2-vl-2b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "cuuupid/qwen2-vl-2b:d312c2be33a5ec3ab4787973aae74a485e194f4fccf106086b637afd6dd694b4",
    input={
        "video": "https://replicate.delivery/pbxt/LXVISWYD8Od0I7w6EW5VIO3sycOIcukn6H26wrkaOX95RK7E/dod_classification_training.mp4",
        "width": 128,
        "height": 128,
        "prompt": "Describe the video in great detail.",
        "max_tokens": 512,
        "temperature": 0.7,
        "max_duration": 180
    }
)

print(output)

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

Run cuuupid/qwen2-vl-2b 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": "cuuupid/qwen2-vl-2b:d312c2be33a5ec3ab4787973aae74a485e194f4fccf106086b637afd6dd694b4",
    "input": {
      "video": "https://replicate.delivery/pbxt/LXVISWYD8Od0I7w6EW5VIO3sycOIcukn6H26wrkaOX95RK7E/dod_classification_training.mp4",
      "width": 128,
      "height": 128,
      "prompt": "Describe the video in great detail.",
      "max_tokens": 512,
      "temperature": 0.7,
      "max_duration": 180
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

[ "The video features a woman standing behind a podium, speaking to the camera. She is wearing a blue shirt and appears to be giving a presentation or lecture. The woman's facial expression suggests that she is engaged and passionate about the topic she is discussing. The background of the video is not visible, but it can be assumed that it is an indoor setting, possibly a conference room or lecture hall. The woman's speech is not audible, but her body language and gestures suggest that she is using hand movements to emphasize certain points. Overall, the video seems to be a formal presentation or lecture, with the woman as the main speaker." ]

Generated in

16.4 seconds

Tweak it Share Report

Prediction

cuuupid/qwen2-vl-2b:39932615ead975306d29c9ccb411a4ad1ec7df6c8adfafb68d565dccfa408883

Model

cuuupid/qwen2-vl-2b:39932615

m1qcx0fywnrj40chmtgaj60bd4

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

67.5s

Created

11 months ago

Input

video
width: 128
height: 128
prompt: what's the video about?
max_tokens: 512
temperature: 0.3
max_duration: 360
repetition_penalty: 1.1

{
  "video": "https://replicate.delivery/pbxt/LXVJfTgytEzj23YwWxoitrI1JgBcAIRopT80sNHxvEH8ZpqV/dod_classification_training.mp4",
  "width": 128,
  "height": 128,
  "prompt": "what's the video about?",
  "max_tokens": 512,
  "temperature": 0.3,
  "max_duration": 360,
  "repetition_penalty": 1.1
}

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 cuuupid/qwen2-vl-2b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "cuuupid/qwen2-vl-2b:39932615ead975306d29c9ccb411a4ad1ec7df6c8adfafb68d565dccfa408883",
  {
    input: {
      video: "https://replicate.delivery/pbxt/LXVJfTgytEzj23YwWxoitrI1JgBcAIRopT80sNHxvEH8ZpqV/dod_classification_training.mp4",
      width: 128,
      height: 128,
      prompt: "what's the video about?",
      max_tokens: 512,
      temperature: 0.3,
      max_duration: 360,
      repetition_penalty: 1.1
    }
  }
);

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 cuuupid/qwen2-vl-2b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "cuuupid/qwen2-vl-2b:39932615ead975306d29c9ccb411a4ad1ec7df6c8adfafb68d565dccfa408883",
    input={
        "video": "https://replicate.delivery/pbxt/LXVJfTgytEzj23YwWxoitrI1JgBcAIRopT80sNHxvEH8ZpqV/dod_classification_training.mp4",
        "width": 128,
        "height": 128,
        "prompt": "what's the video about?",
        "max_tokens": 512,
        "temperature": 0.3,
        "max_duration": 360,
        "repetition_penalty": 1.1
    }
)

print(output)

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

Run cuuupid/qwen2-vl-2b 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": "cuuupid/qwen2-vl-2b:39932615ead975306d29c9ccb411a4ad1ec7df6c8adfafb68d565dccfa408883",
    "input": {
      "video": "https://replicate.delivery/pbxt/LXVJfTgytEzj23YwWxoitrI1JgBcAIRopT80sNHxvEH8ZpqV/dod_classification_training.mp4",
      "width": 128,
      "height": 128,
      "prompt": "what\'s the video about?",
      "max_tokens": 512,
      "temperature": 0.3,
      "max_duration": 360,
      "repetition_penalty": 1.1
    }
  }' \
  https://api.replicate.com/v1/predictions

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