meta/sam-2-video:33432afd – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

meta /sam-2-video:33432afd

Playground API Setup logs

Input

input_video

*file

Input video file path

click_coordinates

*string

Shift + Return to add a new line

Click coordinates as '[x,y],[x,y],...'. Determines number of clicks.

click_labels

string

Shift + Return to add a new line

Click types (1=foreground, 0=background) as '1,1,0,1'. Auto-extends if shorter than coordinates.

Default: "1"

click_frames

string

Shift + Return to add a new line

Frame indices for clicks as '0,0,150,0'. Auto-extends if shorter than coordinates.

Default: "0"

click_object_ids

string

Shift + Return to add a new line

Object labels for clicks as 'person,dog,cat'. Auto-generates if missing or incomplete.

Default: ""

mask_type

string

Mask type: binary (B&W), highlighted (colored overlay), or greenscreen

Default: "binary"

annotation_type

string

Annotation type: mask only, bounding box only, or both (ignored for binary and greenscreen)

Default: "mask"

Including output_video and 4 more...

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

npx create-replicate --model=meta/sam-2-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 meta/sam-2-video using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "meta/sam-2-video:33432afdfc06a10da6b4018932893d39b0159f838b6d11dd1236dff85cc5ec1d",
  {
    input: {
      mask_type: "binary",
      video_fps: 30,
      click_frames: "0",
      click_labels: "1",
      output_video: false,
      output_format: "webp",
      output_quality: 80,
      annotation_type: "mask",
      click_object_ids: "",
      output_frame_interval: 1
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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 meta/sam-2-video using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "meta/sam-2-video:33432afdfc06a10da6b4018932893d39b0159f838b6d11dd1236dff85cc5ec1d",
    input={
        "mask_type": "binary",
        "video_fps": 30,
        "click_frames": "0",
        "click_labels": "1",
        "output_video": False,
        "output_format": "webp",
        "output_quality": 80,
        "annotation_type": "mask",
        "click_object_ids": "",
        "output_frame_interval": 1
    }
)

# The meta/sam-2-video 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/meta/sam-2-video/api#output-schema
    print(item)

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 meta/sam-2-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": "33432afdfc06a10da6b4018932893d39b0159f838b6d11dd1236dff85cc5ec1d",
    "input": {
      "mask_type": "binary",
      "video_fps": 30,
      "click_frames": "0",
      "click_labels": "1",
      "output_video": false,
      "output_format": "webp",
      "output_quality": 80,
      "annotation_type": "mask",
      "click_object_ids": "",
      "output_frame_interval": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/meta/sam-2-video@sha256:33432afdfc06a10da6b4018932893d39b0159f838b6d11dd1236dff85cc5ec1d \
  -i 'mask_type="binary"' \
  -i 'video_fps=30' \
  -i 'click_frames="0"' \
  -i 'click_labels="1"' \
  -i 'output_video=false' \
  -i 'output_format="webp"' \
  -i 'output_quality=80' \
  -i 'annotation_type="mask"' \
  -i 'click_object_ids=""' \
  -i 'output_frame_interval=1'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/meta/sam-2-video@sha256:33432afdfc06a10da6b4018932893d39b0159f838b6d11dd1236dff85cc5ec1d
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "mask_type": "binary",
      "video_fps": 30,
      "click_frames": "0",
      "click_labels": "1",
      "output_video": false,
      "output_format": "webp",
      "output_quality": 80,
      "annotation_type": "mask",
      "click_object_ids": "",
      "output_frame_interval": 1
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

No output yet! Press "Submit" to start a prediction.