aodianyun/qwen2-vl-7b – Run with an API on Replicate

aodianyun / qwen2-vl-7b

Cold

Public
1.6K runs
L40S

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

Prompt to use for the video

Default: "Describe the video."

video

*file

Video to process

width

integer

(minimum: 128, maximum: 2048)

Width for the video

Default: 128

height

integer

(minimum: 128, maximum: 2048)

Height for the video

Default: 128

max_duration

number

(minimum: 1, maximum: 768)

Maximum duration of the video in seconds (above 360, may run out of VRAM).

Default: 60

max_tokens

integer

(minimum: 1, maximum: 8192)

Maximum number of tokens to generate

Default: 128

temperature

number

(minimum: 0.01, maximum: 1)

Temperature for the model (0.7 is a good default).

Default: 0.7

repetition_penalty

number

(minimum: 0.01, maximum: 1.5)

Repetition penalty for the model (1.1 is a good default).

Default: 1.1

Run this model in Node.js with one line of code:

npx create-replicate --model=aodianyun/qwen2-vl-7b

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

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

Run aodianyun/qwen2-vl-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "aodianyun/qwen2-vl-7b:9d135eb0b6b548c43fe0d5974abb7cb3c081d4a50de82d00406cc52b5a1954bc",
  {
    input: {
      video: "https://replicate.delivery/pbxt/LXVISWYD8Od0I7w6EW5VIO3sycOIcukn6H26wrkaOX95RK7E/dod_classification_training.mp4",
      width: 128,
      height: 128,
      prompt: "Describe the video.",
      max_tokens: 128,
      temperature: 0.7,
      max_duration: 60,
      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

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run aodianyun/qwen2-vl-7b using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "aodianyun/qwen2-vl-7b:9d135eb0b6b548c43fe0d5974abb7cb3c081d4a50de82d00406cc52b5a1954bc",
    input={
        "video": "https://replicate.delivery/pbxt/LXVISWYD8Od0I7w6EW5VIO3sycOIcukn6H26wrkaOX95RK7E/dod_classification_training.mp4",
        "width": 128,
        "height": 128,
        "prompt": "Describe the video.",
        "max_tokens": 128,
        "temperature": 0.7,
        "max_duration": 60,
        "repetition_penalty": 1.1
    }
)
print(output)

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

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run aodianyun/qwen2-vl-7b 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": "aodianyun/qwen2-vl-7b:9d135eb0b6b548c43fe0d5974abb7cb3c081d4a50de82d00406cc52b5a1954bc",
    "input": {
      "video": "https://replicate.delivery/pbxt/LXVISWYD8Od0I7w6EW5VIO3sycOIcukn6H26wrkaOX95RK7E/dod_classification_training.mp4",
      "width": 128,
      "height": 128,
      "prompt": "Describe the video.",
      "max_tokens": 128,
      "temperature": 0.7,
      "max_duration": 60,
      "repetition_penalty": 1.1
    }
  }' \
  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 an audience while displaying slides on a screen in front of her. The slides contain text and images related to the topic being discussed by the speaker. The woman appears to be giving a presentation or lecture on a specific subject matter. The slides provide additional information and visual aids to support the speaker's points. The setting suggests that this is likely taking place in a formal environment such as a conference room or auditorium. Overall, the video captures a professional presentation with a focus on delivering informative content through both verbal communication and visual aids." ]

Generated in

9.5 seconds

Tweak it Share Report

Run time and cost

This model costs approximately $0.0030 to run on Replicate, or 333 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 4 seconds.

Readme

This model doesn't have a readme.