aodianyun/minicpm-v-26-int4 – Run with an API on Replicate

aodianyun / minicpm-v-26-int4

Cold

Public
10 runs
T4

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=aodianyun/minicpm-v-26-int4

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/minicpm-v-26-int4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "aodianyun/minicpm-v-26-int4:bd591744b2f826dec0724825d05ef68ce1115571acee1a62de7e9dc681deaf1f",
  {
    input: {
      image: "https://replicate.delivery/pbxt/LYg9UV9q67McivPuwvpQPjClOZ7KqaOHH5F2DgbfCZspIhOQ/input.mp4",
      prompt: "Describe the video in great detail."
    }
  }
);

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/minicpm-v-26-int4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "aodianyun/minicpm-v-26-int4:bd591744b2f826dec0724825d05ef68ce1115571acee1a62de7e9dc681deaf1f",
    input={
        "image": "https://replicate.delivery/pbxt/LYg9UV9q67McivPuwvpQPjClOZ7KqaOHH5F2DgbfCZspIhOQ/input.mp4",
        "prompt": "Describe the video in great detail."
    }
)

# The aodianyun/minicpm-v-26-int4 model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/aodianyun/minicpm-v-26-int4/api#output-schema
    print(item, end="")

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/minicpm-v-26-int4 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": "bd591744b2f826dec0724825d05ef68ce1115571acee1a62de7e9dc681deaf1f",
    "input": {
      "image": "https://replicate.delivery/pbxt/LYg9UV9q67McivPuwvpQPjClOZ7KqaOHH5F2DgbfCZspIhOQ/input.mp4",
      "prompt": "Describe the video in great detail."
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

The video shows the process of cooking using a specialized kitchen appliance, which appears to be a deep fryer or wok with an integrated steam vent. Here's a detailed step-by-step description: 1. **Preparation**: The video starts with the appliance on a stovetop, and someone is holding a ladle filled with what looks like chopped vegetables or meat. 2. **Frying**: The person pours the contents into the frying section of the appliance. This section has a round opening through which food items are added for frying. 3. **Steaming**: After adding the ingredients, the lid is placed on top of the appliance. There is a steam vent visible at the top, indicating that it can also function as a steamer. 4. **Cooking**: Once the lid is sealed, the appliance seems to heat up, causing the steam to build up inside. The lid has perforations that allow steam to escape while keeping the food contained. 5. **Monitoring**: Throughout the cooking process, the person monitoring the appliance adjusts the position of the lid slightly to ensure proper ventilation and even cooking. 6. **Final Cooking**: The final frame shows the completed dish being removed from the appliance, ready to serve. 7. **Branding**: The last two frames show the branding or contact information for the manufacturer or distributor of this appliance. Overall, the video demonstrates the versatility of the appliance in both frying and steaming functions, showcasing its efficiency and ease of use in a commercial kitchen setting.

{
  "completed_at": "2024-09-13T09:09:33.842689Z",
  "created_at": "2024-09-13T09:08:53.195000Z",
  "data_removed": false,
  "error": null,
  "id": "d4npk7vs9drge0chxaj967mwc0",
  "input": {
    "image": "https://replicate.delivery/pbxt/LYg9UV9q67McivPuwvpQPjClOZ7KqaOHH5F2DgbfCZspIhOQ/input.mp4",
    "prompt": "Describe the video in great detail."
  },
  "logs": "video_duration 20.099\nframe_rate 0.49753719090502013",
  "metrics": {
    "predict_time": 40.620701359,
    "total_time": 40.647689
  },
  "output": [
    "",
    "",
    "The ",
    "video ",
    "shows ",
    "the ",
    "process ",
    "of ",
    "cooking ",
    "using ",
    "a ",
    "specialized ",
    "kitchen ",
    "",
    "appliance, ",
    "which ",
    "appears ",
    "to ",
    "be ",
    "a ",
    "deep ",
    "",
    "fryer ",
    "or ",
    "",
    "wok ",
    "with ",
    "an ",
    "integrated ",
    "steam ",
    "",
    "vent. ",
    "",
    "Here's ",
    "a ",
    "detailed ",
    "",
    "",
    "step-by-step ",
    "description:\n\n",
    "",
    "",
    "1. ",
    "",
    "",
    "",
    "**Preparation**: ",
    "The ",
    "video ",
    "starts ",
    "with ",
    "the ",
    "appliance ",
    "on ",
    "a ",
    "",
    "",
    "",
    "",
    "stovetop, ",
    "and ",
    "someone ",
    "is ",
    "holding ",
    "a ",
    "",
    "ladle ",
    "filled ",
    "with ",
    "what ",
    "looks ",
    "like ",
    "chopped ",
    "vegetables ",
    "or ",
    "meat.\n\n",
    "",
    "",
    "2. ",
    "",
    "",
    "",
    "**Frying**: ",
    "The ",
    "person ",
    "pours ",
    "the ",
    "contents ",
    "into ",
    "the ",
    "frying ",
    "section ",
    "of ",
    "the ",
    "",
    "appliance. ",
    "This ",
    "section ",
    "has ",
    "a ",
    "round ",
    "opening ",
    "through ",
    "which ",
    "food ",
    "items ",
    "are ",
    "added ",
    "for ",
    "frying.\n\n",
    "",
    "",
    "3. ",
    "",
    "",
    "",
    "**Steaming**: ",
    "After ",
    "adding ",
    "the ",
    "",
    "ingredients, ",
    "the ",
    "lid ",
    "is ",
    "placed ",
    "on ",
    "top ",
    "of ",
    "the ",
    "",
    "appliance. ",
    "There ",
    "is ",
    "a ",
    "steam ",
    "vent ",
    "visible ",
    "at ",
    "the ",
    "",
    "top, ",
    "indicating ",
    "that ",
    "it ",
    "can ",
    "also ",
    "function ",
    "as ",
    "a ",
    "",
    "steamer.\n\n",
    "",
    "",
    "4. ",
    "",
    "",
    "",
    "**Cooking**: ",
    "Once ",
    "the ",
    "lid ",
    "is ",
    "",
    "sealed, ",
    "the ",
    "appliance ",
    "seems ",
    "to ",
    "heat ",
    "",
    "up, ",
    "causing ",
    "the ",
    "steam ",
    "to ",
    "build ",
    "up ",
    "",
    "inside. ",
    "The ",
    "lid ",
    "has ",
    "",
    "perforations ",
    "that ",
    "allow ",
    "steam ",
    "to ",
    "escape ",
    "while ",
    "keeping ",
    "the ",
    "food ",
    "contained.\n\n",
    "",
    "",
    "5. ",
    "",
    "",
    "**Monitoring**: ",
    "Throughout ",
    "the ",
    "cooking ",
    "",
    "process, ",
    "the ",
    "person ",
    "monitoring ",
    "the ",
    "appliance ",
    "adjusts ",
    "the ",
    "position ",
    "of ",
    "the ",
    "lid ",
    "slightly ",
    "to ",
    "ensure ",
    "proper ",
    "ventilation ",
    "and ",
    "even ",
    "cooking.\n\n",
    "",
    "",
    "6. ",
    "",
    "**Final ",
    "",
    "Cooking**: ",
    "The ",
    "final ",
    "frame ",
    "shows ",
    "the ",
    "completed ",
    "dish ",
    "being ",
    "removed ",
    "from ",
    "the ",
    "",
    "appliance, ",
    "ready ",
    "to ",
    "serve.\n\n",
    "",
    "",
    "7. ",
    "",
    "",
    "",
    "**Branding**: ",
    "The ",
    "last ",
    "two ",
    "frames ",
    "show ",
    "the ",
    "branding ",
    "or ",
    "contact ",
    "information ",
    "for ",
    "the ",
    "manufacturer ",
    "or ",
    "distributor ",
    "of ",
    "this ",
    "appliance.\n\n",
    "",
    "",
    "Overall, ",
    "the ",
    "video ",
    "demonstrates ",
    "the ",
    "versatility ",
    "of ",
    "the ",
    "appliance ",
    "in ",
    "both ",
    "frying ",
    "and ",
    "",
    "steaming ",
    "",
    "functions, ",
    "showcasing ",
    "its ",
    "efficiency ",
    "and ",
    "ease ",
    "of ",
    "use ",
    "in ",
    "a ",
    "commercial ",
    "kitchen ",
    "",
    "",
    "setting."
  ],
  "started_at": "2024-09-13T09:08:53.221988Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us-central1.g.replicate.net/v1/streams/bucz34eavx2jwpg54iek256ezzuw3ywa323rtcyhujmkkabs5yjq",
    "get": "https://api.replicate.com/v1/predictions/d4npk7vs9drge0chxaj967mwc0",
    "cancel": "https://api.replicate.com/v1/predictions/d4npk7vs9drge0chxaj967mwc0/cancel"
  },
  "version": "bd591744b2f826dec0724825d05ef68ce1115571acee1a62de7e9dc681deaf1f"
}

Generated in

40.6 seconds

Tweak it Share Report

Run time and cost

This model runs on Nvidia T4 GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

This model doesn't have a readme.