doubao-watermark-remover

Remove the visible Doubao (豆包) AI watermark from images. Use when asked to remove Doubao watermarks, clean Doubao-generated images, or process images with the "豆包AI生成" watermark.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "doubao-watermark-remover" with this command: npx skills add zhengsuanfa/doubao-watermark-remover/zhengsuanfa-doubao-watermark-remover-doubao-watermark-remover

Doubao Watermark Remover

Dependencies

  • Python 3.9+
  • Pillow (install with pip install -r requirements.txt)

Quick start

  1. Install dependencies in the scripts folder:

    • cd doubao-watermark-remover/scripts && pip install -r requirements.txt
  2. Run the CLI:

    • python remove_watermark.py <input-image> <output-image>

CLI usage

  • Parameters:
    • input-image: path to the Doubao watermarked image
    • output-image: path for the cleaned image (format inferred from extension)

Example:

python remove_watermark.py ./in.png ./out.png

What this skill provides

  • scripts/remove_watermark.py: CLI entry point and core algorithm.
  • scripts/capture_alpha_map.py: Tool to capture Doubao watermark alpha map.
  • references/algorithm.md: Math, detection rules, and usage guide.

Workflow

  1. First time: Generate alpha map using capture_alpha_map.py
  2. Use remove_watermark.py for batch processing.

Capturing Alpha Map (First Time Required)

Since Doubao watermark pattern may vary, you need to capture the alpha map first:

  1. Generate a pure black image (0,0,0) and have Doubao add watermark to it

  2. Run the capture tool:

    python capture_alpha_map.py <black-with-watermark.png> <width> <height>
    

    Size options: 140x35 (small images) or 180x40 (large images)

  3. The tool will save the alpha map to assets/ folder

Notes

  • Doubao watermark "豆包AI生成" appears in the bottom-right corner
  • Script uses Pillow for image IO and per-pixel edits
  • Output format is inferred from the output file extension

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

ll-feishu-audio

飞书语音交互技能。支持语音消息自动识别、AI 处理、语音回复全流程。需要配置 FEISHU_APP_ID 和 FEISHU_APP_SECRET 环境变量。使用 faster-whisper 进行语音识别,Edge TTS 进行语音合成,自动转换 OPUS 格式并通过飞书发送。适用于飞书平台的语音对话场景。

Archived SourceRecently Updated
General

test_skill

import json import tkinter as tk from tkinter import messagebox, simpledialog

Archived SourceRecently Updated
General

51mee-resume-profile

简历画像。触发场景:用户要求生成候选人画像;用户想了解候选人的多维度标签和能力评估。

Archived SourceRecently Updated
General

51mee-resume-parse

简历解析。触发场景:用户上传简历文件要求解析、提取结构化信息。

Archived SourceRecently Updated