casia-iva-lab / fastsam

Fast Segment Anything

Cold

Public
25.1K runs
T4
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Input

input_image

*file

Input image

model_name

string

choose a model

Default: "FastSAM-x"

image_size

integer

Choose image size

Default: 640

iou

number

iou threshold for filtering the annotations

Default: 0.7

text_prompt

string

Shift + Return to add a new line

use text prompt eg: "a black dog"

conf

number

object confidence threshold

Default: 0.25

retina

boolean

draw high-resolution segmentation masks

Default: true

box_prompt

string

Shift + Return to add a new line

[x,y,w,h]

Default: "[0,0,0,0]"

point_prompt

string

Shift + Return to add a new line

[[x1,y1],[x2,y2]]

Default: "[[0,0]]"

point_label

string

Shift + Return to add a new line

[1,0] 0:background, 1:foreground

Default: "[0]"

withContours

boolean

draw the edges of the masks

Default: false

better_quality

boolean

better quality using morphologyEx

Default: false

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

npx create-replicate --model=casia-iva-lab/fastsam

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 casia-iva-lab/fastsam using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "casia-iva-lab/fastsam:371aeee1ce0c5efd25bbef7a4527ec9e59188b963ebae1eeb851ddc145685c17",
  {
    input: {
      iou: 0.9,
      conf: 0.4,
      retina: true,
      box_prompt: "[0,0,0,0]",
      image_size: 640,
      model_name: "FastSAM-x",
      input_image: "https://replicate.delivery/pbxt/J45o004GBhb0mvUJgqQlaMM7lmHkdcOF5e1FV2yFFXttNbCH/download.jpeg",
      point_label: "[0]",
      point_prompt: "[[0,0]]",
      withContours: true,
      better_quality: false
    }
  }
);
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 casia-iva-lab/fastsam using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "casia-iva-lab/fastsam:371aeee1ce0c5efd25bbef7a4527ec9e59188b963ebae1eeb851ddc145685c17",
    input={
        "iou": 0.9,
        "conf": 0.4,
        "retina": True,
        "box_prompt": "[0,0,0,0]",
        "image_size": 640,
        "model_name": "FastSAM-x",
        "input_image": "https://replicate.delivery/pbxt/J45o004GBhb0mvUJgqQlaMM7lmHkdcOF5e1FV2yFFXttNbCH/download.jpeg",
        "point_label": "[0]",
        "point_prompt": "[[0,0]]",
        "withContours": True,
        "better_quality": False
    }
)
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 casia-iva-lab/fastsam 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": "371aeee1ce0c5efd25bbef7a4527ec9e59188b963ebae1eeb851ddc145685c17",
    "input": {
      "iou": 0.9,
      "conf": 0.4,
      "retina": true,
      "box_prompt": "[0,0,0,0]",
      "image_size": 640,
      "model_name": "FastSAM-x",
      "input_image": "https://replicate.delivery/pbxt/J45o004GBhb0mvUJgqQlaMM7lmHkdcOF5e1FV2yFFXttNbCH/download.jpeg",
      "point_label": "[0]",
      "point_prompt": "[[0,0]]",
      "withContours": true,
      "better_quality": false
    }
  }' \
  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/casia-iva-lab/fastsam@sha256:371aeee1ce0c5efd25bbef7a4527ec9e59188b963ebae1eeb851ddc145685c17 \
  -i 'iou=0.9' \
  -i 'conf=0.4' \
  -i 'retina=true' \
  -i 'box_prompt="[0,0,0,0]"' \
  -i 'image_size=640' \
  -i 'model_name="FastSAM-x"' \
  -i 'input_image="https://replicate.delivery/pbxt/J45o004GBhb0mvUJgqQlaMM7lmHkdcOF5e1FV2yFFXttNbCH/download.jpeg"' \
  -i 'point_label="[0]"' \
  -i 'point_prompt="[[0,0]]"' \
  -i 'withContours=true' \
  -i 'better_quality=false'

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/casia-iva-lab/fastsam@sha256:371aeee1ce0c5efd25bbef7a4527ec9e59188b963ebae1eeb851ddc145685c17
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "iou": 0.9,
      "conf": 0.4,
      "retina": true,
      "box_prompt": "[0,0,0,0]",
      "image_size": 640,
      "model_name": "FastSAM-x",
      "input_image": "https://replicate.delivery/pbxt/J45o004GBhb0mvUJgqQlaMM7lmHkdcOF5e1FV2yFFXttNbCH/download.jpeg",
      "point_label": "[0]",
      "point_prompt": "[[0,0]]",
      "withContours": true,
      "better_quality": false
    }
  }' \
  http://localhost:5000/predictions

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

Output

Generated in

5.0 seconds

Tweak itReport

Examples

View more examples

Run time and cost

This model costs approximately $0.0042 to run on Replicate, or 238 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 T4 GPU hardware. Predictions typically complete within 19 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Fast Segment Anything

FastSAM Speed

The Fast Segment Anything Model(FastSAM) is a CNN Segment Anything Model trained by only 2% of the SA-1B dataset published by SAM authors. The FastSAM achieve comparable performance with the SAM method at 50× higher run-time speed.

FastSAM design

Citing FastSAM

If you find this project useful for your research, please consider citing the following BibTeX entry.

@misc{zhao2023fast,
      title={Fast Segment Anything},
      author={Xu Zhao and Wenchao Ding and Yongqi An and Yinglong Du and Tao Yu and Min Li and Ming Tang and Jinqiao Wang},
      year={2023},
      eprint={2306.12156},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}