Introduction

Hi, developers, welcome to use Dewatermark's API. The following are some basic introductions to your access service. Hope you can find the AI technology capabilities that are suitable for your business here. Thank you for using!

Authentication

To authorize, use this code:

import requests

API_KEY = "YOUR_API_KEY"
headers = {
    "X-API-KEY": API_KEY
}

# Make API request
response = requests.get(
    "https://platform.dewatermark.ai/api/object_removal/v1/erase_watermark",
    headers=headers
)

# With shell, you can just pass the correct header with each request
curl "https://platform.dewatermark.ai/api/object_removal/v1/erase_watermark" \
  -H "X-API-KEY: <API-KEY>"

Make sure to replace <API-KEY> with your API key.

Dewatermark uses API keys to allow access to the API. You can receive your unique API key by signing up and opening API managent page).

The API key must be included in all API requests to the server in a header that looks like the following:

X-API-KEY: API_KEY

You must replace API_KEY with your personal API key. Your personal API key can be obtained from the API management interface.

Image Processing API

Remove Watermark

import requests
import base64
import uuid
import os
from io import BytesIO


def erase_watermark(original_preview_image=None, mask_brush=None, session_id=None, remove_text="true"):
    API_KEY = "YOUR_API_KEY"
    erase_url = "https://platform.dewatermark.ai/api/object_removal/v1/erase_watermark"
    headers = {
        "X-API-KEY": API_KEY
    }
    erase_files = {}

    if original_preview_image is not None:
        if isinstance(original_preview_image, str) and os.path.isfile(original_preview_image):
            image_file = open(original_preview_image, "rb")
            file_original_preview_image = ("original_preview_image.jpeg", image_file)
        else:
            image_bytes = base64.b64decode(original_preview_image)
            image_file = BytesIO(image_bytes)
            file_original_preview_image = ("original_preview_image.jpeg", image_file)
        erase_files["original_preview_image"] = file_original_preview_image

    if mask_brush is not None:
        image_file = open(mask_brush, "rb")
        file_mask_brush = ("mask_brush.png", image_file)


    if original_preview_image is not None:
        erase_files["original_preview_image"] = file_original_preview_image

    if mask_brush is not None:
        erase_files["mask_brush"] = file_mask_brush

    erase_files["remove_text"] = (None, remove_text)

    erase_response = requests.post(erase_url, headers=headers, files=erase_files)

    response_data = erase_response.json()
    return {
        "session_id": response_data["session_id"],
        "image_base64": response_data["edited_image"]["image"],
        "mask_base": response_data["edited_image"]["mask"]
    }

# Initial call: Automatically detect and remove visible watermarks using AI
auto_result = erase_watermark("input.jpeg")

# Optional: Uncomment this line to preview the auto-processed result (Base64-encoded image)
# print(auto_result["image_base64"])

# Manual refinement: If some watermarks remain, manually specify areas to remove using a brush mask
manual_result_step_1 = erase_watermark(
    original_preview_image=auto_result["image_base64"],
    mask_base=auto_result["mask_base"],
    mask_brush="mask_brush_manual_step_1.png"
)

curl -X POST "https://platform.dewatermark.ai/api/object_removal/v1/erase_watermark" \
  -H "X-API-KEY: API_KEY" \
  --form 'session_id="SESSION_ID"' \
  --form 'original_preview_image=@"IMAGE_FILE"' \
  --form 'mask_base=@"MASK_BASE_FILE"'\
  --form 'mask_brush=@"MASK_BRUSH_FILE"' \
  --form 'remove_text="true"'

This API allows you to remove watermark from an image and seamlessly inpaint the erased area to blend it naturally with the surrounding background. Each remove watermark image API call is counted as 1 credits.

The above command returns JSON structured like this:

{
  "edited_image": {
    "image": "BASE_64_IMAGE",
    "image_id": "image_id",
    "mask": "BASE64_MASK",
    "watermark_mask":"BASE64_MASK"
  },
  "event_id": "event_id",
  "session_id": "session_id"
}

HTTP Request

POST https://platform.dewatermark.ai/api/object_removal/v1/erase_watermark

Request body

Form	Required	Type	Description
original_preview_image	Optional	binary	The input image, it should be a JPEG image and the largest dimension is not greater than 6000 px.
session_id	Optional	text	The session id, it represents the current image.
mask_brush	Optional	binary	The mask image for the Remove Object API should include a binary representation of the unwanted object's outline, delineating the area to be removed and inpainted.
remove_text	Optional	text	If set to 'true', enables the text removal feature for improved results when removing purely textual watermarks. Note that this may remove all text from your image.
predict_mode	Optional	text	You can choose between "old" (2.0) or "3.0", 2.0 works best for emoji while 3.0 work for most cases.

The inital request doesn't require mask_brush.

Response

Property	Description
edited_image.image	The result after removing object, it it's a base64 encoded image.
edited_image.mask	This is the masked image of all previously erased parts.

Here's a complete example that demonstrates the watermark removal process with automatic detection and manual refinement:

The process works as follows:

Initial Input Image
Automatic Watermark Detection and Removal
Manual Correction

This example demonstrates the complete workflow for removing watermarks: 1. Start with automatic watermark detection and removal 2. If needed, perform manual corrections using brush masks

The images show the progression from the original image through each step of the watermark removal process, including the manual masks used for refinement.

Even after the initial API call, you can achieve even more precise results by manually specifying the remaining watermark area you want to erase. Here's the process:

Manual Selection: Define a mask that isolates the specific part of the image containing the remaining watermark or unwanted element. This mask acts as a guide for the API.

original_preview_image: The image you want to erase the watermark**

mask_brush: This parameter allows you to providea mask that focuses on the watermark area you want to erase.

remove_text: If you want to enable the text removal feature, set remove_text to 'true' in the request body to remove text from the image. If the watermark is purely text, enable the text remover for improved results. Note that this may remove all text from your image.

predict_mode: To select the model version, You can choose between "old" (2.0) or "3.0", 2.0 works best for emoji while 3.0 work for most cases.

By following these steps, you can iteratively remove watermarks and achieve a highly refined final image.

import requests
import base64
import uuid
import os
from io import BytesIO


def erase_watermark(original_preview_image=None, remove_text="true"):
    API_KEY = "YOUR_API_KEY"
    erase_url = "https://platform.dewatermark.ai/api/object_removal/v1/erase_watermark"
    headers = {
        "X-API-KEY": API_KEY
    }
    erase_files = {}

    if original_preview_image is not None:
        if isinstance(original_preview_image, str) and os.path.isfile(original_preview_image):
            image_file = open(original_preview_image, "rb")
            file_original_preview_image = ("original_preview_image.jpeg", image_file)
        else:
            image_bytes = base64.b64decode(original_preview_image)
            image_file = BytesIO(image_bytes)
            file_original_preview_image = ("original_preview_image.jpeg", image_file)
        erase_files["original_preview_image"] = file_original_preview_image


    erase_files["remove_text"] = (None, remove_text)

    erase_response = requests.post(erase_url, headers=headers, files=erase_files)

    response_data = erase_response.json()
    return {
        "session_id": response_data["session_id"],
        "preview_image_to_save": response_data["edited_image"]["image"],
        "preview_mask_to_save": response_data["edited_image"]["watermark_mask"]
    }

Errors

This error section is stored in a separate file in includes/_errors.md. Slate allows you to optionally separate out your docs into many files...just save them to the includes folder and add them to the top of your index.md's frontmatter. Files are included in the order listed.

The Kittn API uses the following error codes:

Error Code	Meaning
400	Bad Request -- Your request is invalid.
401	Unauthorized -- Your API key is wrong.
403	Forbidden -- The kitten requested is hidden for administrators only.
404	Not Found -- The specified kitten could not be found.
405	Method Not Allowed -- You tried to access a kitten with an invalid method.
406	Not Acceptable -- You requested a format that isn't json.
410	Gone -- The kitten requested has been removed from our servers.
418	I'm a teapot.
429	Too Many Requests -- You're requesting too many kittens! Slow down!
500	Internal Server Error -- We had a problem with our server. Try again later.
503	Service Unavailable -- We're temporarily offline for maintenance. Please try again later.

Introduction

Authentication

Image Processing API

Remove Watermark

Remove Watermark

HTTP Request

Request body

Response

Continuing Watermark Removal with Manual Refinement

Errors