adirik/marigold:1a363593 – Run with an API on Replicate

Version

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

adirik /marigold:1a363593

Playground API

Input

image

*file

Input image, use an RGB image for optimal results.

resize_input

boolean

Resize the original input resolution to max resolution.

Default: true

num_infer

integer

(minimum: 1, maximum: 20)

Number of inferences to be ensembled, a higher number gives better results but runs slower.

Default: 10

denoise_steps

integer

(minimum: 1, maximum: 50)

Inference denoising steps, more steps results in higher accuracy but slower inference speed.

Default: 10

regularizer_strength

number

(minimum: 0, maximum: 1)

Ensembling parameter, weight of optimization regularizer.

Default: 0.02

reduction_method

string

Ensembling parameter, method to merge aligned depth maps.

Default: "median"

max_iter

integer

(minimum: 1, maximum: 20)

Ensembling parameter, max optimization iterations.

Default: 5

seed

integer

Seed for reproducibility, set to random if left as None.

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

npx create-replicate --model=adirik/marigold

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 adirik/marigold using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "adirik/marigold:1a363593bc4882684fc58042d19db5e13a810e44e02f8d4c32afd1eb30464818",
  {
    input: {
      image: "https://replicate.delivery/pbxt/K3HorhanHXhZ8WeWpH1udCnnXe3UX1Olmp619RN3nHxNBBmU/WechatIMG17527_crop43.jpg",
      max_iter: 5,
      num_infer: 10,
      resize_input: true,
      denoise_steps: 10,
      reduction_method: "median",
      regularizer_strength: 0.02
    }
  }
);

// 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 adirik/marigold using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "adirik/marigold:1a363593bc4882684fc58042d19db5e13a810e44e02f8d4c32afd1eb30464818",
    input={
        "image": "https://replicate.delivery/pbxt/K3HorhanHXhZ8WeWpH1udCnnXe3UX1Olmp619RN3nHxNBBmU/WechatIMG17527_crop43.jpg",
        "max_iter": 5,
        "num_infer": 10,
        "resize_input": True,
        "denoise_steps": 10,
        "reduction_method": "median",
        "regularizer_strength": 0.02
    }
)
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 adirik/marigold 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": "adirik/marigold:1a363593bc4882684fc58042d19db5e13a810e44e02f8d4c32afd1eb30464818",
    "input": {
      "image": "https://replicate.delivery/pbxt/K3HorhanHXhZ8WeWpH1udCnnXe3UX1Olmp619RN3nHxNBBmU/WechatIMG17527_crop43.jpg",
      "max_iter": 5,
      "num_infer": 10,
      "resize_input": true,
      "denoise_steps": 10,
      "reduction_method": "median",
      "regularizer_strength": 0.02
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-12-15T08:28:13.995762Z",
  "created_at": "2023-12-15T08:27:59.350010Z",
  "data_removed": false,
  "error": null,
  "id": "zxctnwtbp2ke2qy53cxkl2ekv4",
  "input": {
    "image": "https://replicate.delivery/pbxt/K3HorhanHXhZ8WeWpH1udCnnXe3UX1Olmp619RN3nHxNBBmU/WechatIMG17527_crop43.jpg",
    "max_iter": 5,
    "num_infer": 10,
    "resize_input": true,
    "denoise_steps": 10,
    "reduction_method": "median",
    "regularizer_strength": 0.02
  },
  "logs": "multiple inference:   0%|          | 0/1 [00:00<?, ?it/s]\ndenoising:   0%|          | 0/10 [00:00<?, ?it/s]\u001b[A\ndenoising:  10%|█         | 1/10 [00:01<00:14,  1.57s/it]\u001b[A\ndenoising:  20%|██        | 2/10 [00:02<00:09,  1.16s/it]\u001b[A\ndenoising:  30%|███       | 3/10 [00:03<00:07,  1.02s/it]\u001b[A\ndenoising:  40%|████      | 4/10 [00:04<00:05,  1.04it/s]\u001b[A\ndenoising:  50%|█████     | 5/10 [00:05<00:04,  1.08it/s]\u001b[A\ndenoising:  60%|██████    | 6/10 [00:05<00:03,  1.10it/s]\u001b[A\ndenoising:  70%|███████   | 7/10 [00:06<00:02,  1.12it/s]\u001b[A\ndenoising:  80%|████████  | 8/10 [00:07<00:01,  1.13it/s]\u001b[A\ndenoising:  90%|█████████ | 9/10 [00:08<00:00,  1.13it/s]\u001b[A\ndenoising: 100%|██████████| 10/10 [00:09<00:00,  1.14it/s]\u001b[A\n                                                          \u001b[A\nmultiple inference: 100%|██████████| 1/1 [00:09<00:00,  9.45s/it]",
  "metrics": {
    "predict_time": 14.571437,
    "total_time": 14.645752
  },
  "output": [
    "https://replicate.delivery/pbxt/fS7CT14IFJXyHiAIfcKospCWztxuheAEyR8zffRKhR1lDgTQC/depth_bw.png",
    "https://replicate.delivery/pbxt/TadKPFoM0Nr3Ktl6gyAcdEUp5mUTWN8rOokJlNJD0zTHAngE/depth_colored.png"
  ],
  "started_at": "2023-12-15T08:27:59.424325Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/zxctnwtbp2ke2qy53cxkl2ekv4",
    "cancel": "https://api.replicate.com/v1/predictions/zxctnwtbp2ke2qy53cxkl2ekv4/cancel"
  },
  "version": "1a363593bc4882684fc58042d19db5e13a810e44e02f8d4c32afd1eb30464818"
}

Generated in

14.6 seconds

Tweak itReport