uncensored-com/llava-next-video – Run with an API on Replicate

uncensored-com / llava-next-video

Input a video. Ask anything about it

Cold

Public
3.5K runs
A100 (80GB)
GitHub
License

Run with an API

Playground API Examples README Versions

Input

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

npx create-replicate --model=uncensored-com/llava-next-video

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 uncensored-com/llava-next-video using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "uncensored-com/llava-next-video:46eebc3684238da4c77ed67920e8f3cca934d6d544b8d7cc3e52604b3073740b",
  {
    input: {
      video: "https://www.shutterstock.com/shutterstock/videos/1104246027/preview/stock-footage-woman-friends-and-jumping-in-sea-holding-hands-for-fun-holiday-weekend-adventure-or-vacation-in.mp4",
      prompt: "Describe this video and the people in it in detail",
      num_frames: 10,
      max_new_tokens: 500
    }
  }
);
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 uncensored-com/llava-next-video using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "uncensored-com/llava-next-video:46eebc3684238da4c77ed67920e8f3cca934d6d544b8d7cc3e52604b3073740b",
    input={
        "video": "https://www.shutterstock.com/shutterstock/videos/1104246027/preview/stock-footage-woman-friends-and-jumping-in-sea-holding-hands-for-fun-holiday-weekend-adventure-or-vacation-in.mp4",
        "prompt": "Describe this video and the people in it in detail",
        "num_frames": 10,
        "max_new_tokens": 500
    }
)
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 uncensored-com/llava-next-video 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": "46eebc3684238da4c77ed67920e8f3cca934d6d544b8d7cc3e52604b3073740b",
    "input": {
      "video": "https://www.shutterstock.com/shutterstock/videos/1104246027/preview/stock-footage-woman-friends-and-jumping-in-sea-holding-hands-for-fun-holiday-weekend-adventure-or-vacation-in.mp4",
      "prompt": "Describe this video and the people in it in detail",
      "num_frames": 10,
      "max_new_tokens": 500
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

The video captures a group of four women enjoying a day at the beach. They are all wearing bikinis and are standing on a wooden pier that extends over the ocean. The women are holding hands, suggesting a sense of camaraderie and shared enjoyment. The water around them is calm, with gentle waves lapping at the pier's edge. The sky above them is clear and blue, indicating a sunny day. The women are facing the camera, their smiles radiating joy and relaxation. The pier they are standing on is weathered and wooden, with visible signs of age and use, adding a rustic charm to the scene. The ocean in the background is a deep blue, its surface rippling with small waves that add a sense of tranquility to the scene. The women's bikinis are colorful, adding a vibrant touch to the serene setting. The overall atmosphere is one of leisure and enjoyment, with the women seemingly taking a break from their daily routines to appreciate the beauty of nature and each other's company.

{
  "completed_at": "2024-07-09T18:48:59.289659Z",
  "created_at": "2024-07-09T18:47:51.915000Z",
  "data_removed": false,
  "error": null,
  "id": "g8acnxykddrj60cgk39bz1y0t0",
  "input": {
    "video": "https://www.shutterstock.com/shutterstock/videos/1104246027/preview/stock-footage-woman-friends-and-jumping-in-sea-holding-hands-for-fun-holiday-weekend-adventure-or-vacation-in.mp4",
    "prompt": "Describe this video and the people in it in detail",
    "num_frames": 10,
    "max_new_tokens": 500
  },
  "logs": "/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/transformers/feature_extraction_utils.py:142: UserWarning: Creating a tensor from a list of numpy.ndarrays is extremely slow. Please consider converting the list to a single numpy.ndarray with numpy.array() before converting to a tensor. (Triggered internally at ../torch/csrc/utils/tensor_new.cpp:274.)\nreturn torch.tensor(value)\nWe detected that you are passing `past_key_values` as a tuple and this is deprecated and will be removed in v4.43. Please use an appropriate `Cache` class (https://huggingface.co/docs/transformers/v4.41.3/en/internal/generation_utils#transformers.Cache)",
  "metrics": {
    "predict_time": 7.983898147,
    "total_time": 67.374659
  },
  "output": "The video captures a group of four women enjoying a day at the beach. They are all wearing bikinis and are standing on a wooden pier that extends over the ocean. The women are holding hands, suggesting a sense of camaraderie and shared enjoyment. The water around them is calm, with gentle waves lapping at the pier's edge. The sky above them is clear and blue, indicating a sunny day. The women are facing the camera, their smiles radiating joy and relaxation. The pier they are standing on is weathered and wooden, with visible signs of age and use, adding a rustic charm to the scene. The ocean in the background is a deep blue, its surface rippling with small waves that add a sense of tranquility to the scene. The women's bikinis are colorful, adding a vibrant touch to the serene setting. The overall atmosphere is one of leisure and enjoyment, with the women seemingly taking a break from their daily routines to appreciate the beauty of nature and each other's company.",
  "started_at": "2024-07-09T18:48:51.305761Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/g8acnxykddrj60cgk39bz1y0t0",
    "cancel": "https://api.replicate.com/v1/predictions/g8acnxykddrj60cgk39bz1y0t0/cancel"
  },
  "version": "46eebc3684238da4c77ed67920e8f3cca934d6d544b8d7cc3e52604b3073740b"
}

Generated in

8.0 seconds

Tweak it Share Report

Run time and cost

This model costs approximately $0.52 to run on Replicate, or 1 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 A100 (80GB) GPU hardware. Predictions typically complete within 7 minutes. The predict time for this model varies significantly based on the inputs.

Readme

deployed by uncensored.com

email me if you’d like anything changed (e.g. hardware config) -> hi@uncensored.com