设计与多媒体

WaveSpeedAI Watermark Remover

试用

通过 WaveSpeed AI 接口,去除图片和视频中的水印、Logo、字幕与文字叠加。

它能做什么

提供图片和视频两个模型端点。图片端点接收 URL,可输出 jpeg、png、webp。视频端点接收公网可访问的 URL,最长支持 10 分钟,借助时序感知的修复算法减少帧间闪烁。调用前需配置 WAVESPEED_API_KEY 环境变量。示例展示了上传本地文件获取 URL、调用模型、为图片端点开启同步模式、自定义重试客户端,以及通过 runNoThrow 捕获超时和预测异常的处理方式。

什么时候用它

  • 清理自己导出的图片上的水印
  • 移除自己添加进视频的 Logo 叠加层
  • 去掉短视频片段上的字幕或文字叠加
  • 对已购授权的素材做二次清理后再使用

技能文档

WaveSpeedAI Watermark Remover

Remove watermarks, logos, captions, and text overlays from images and videos using WaveSpeed AI. Intelligently detects and removes watermarks while preserving texture and background.

Authentication

export WAVESPEED_API_KEY="your-api-key"

Get your API key at wavespeed.ai/accesskey.

Quick Start

Image Watermark Removal

import wavespeed from 'wavespeed';

// Upload a local image to get a URL
const imageUrl = await wavespeed.upload("/path/to/watermarked-image.png");

const output_url = (await wavespeed.run(
  "wavespeed-ai/image-watermark-remover",
  { image: imageUrl }
))["outputs"][0];

Video Watermark Removal

import wavespeed from 'wavespeed';

// Upload a local video to get a URL
const videoUrl = await wavespeed.upload("/path/to/watermarked-video.mp4");

const output_url = (await wavespeed.run(
  "wavespeed-ai/video-watermark-remover",
  { video: videoUrl }
))["outputs"][0];

You can also pass existing URLs directly:

const output_url = (await wavespeed.run(
  "wavespeed-ai/image-watermark-remover",
  { image: "https://example.com/watermarked-image.jpg" }
))["outputs"][0];

API Endpoints

Image Watermark Remover

Model ID: wavespeed-ai/image-watermark-remover

Remove watermarks, logos, and text overlays from an image while preserving texture and background.

Parameters

ParameterTypeRequiredDefaultDescription
imagestringYes--URL of the image to process
output_formatstringNojpegOutput format. One of: jpeg, png, webp

Example

import wavespeed from 'wavespeed';

const imageUrl = await wavespeed.upload("/path/to/watermarked-photo.png");

const output_url = (await wavespeed.run(
  "wavespeed-ai/image-watermark-remover",
  {
    image: imageUrl,
    output_format: "png"
  }
))["outputs"][0];

Video Watermark Remover

Model ID: wavespeed-ai/video-watermark-remover

Remove watermarks, logos, captions, and text overlays from a video. Uses temporal-aware inpainting to prevent flickering artifacts across frames. Supports videos up to 10 minutes.

Parameters

ParameterTypeRequiredDefaultDescription
videostringYes--URL of the video to process. Must be publicly accessible. Max 10 minutes.

Example

import wavespeed from 'wavespeed';

const videoUrl = await wavespeed.upload("/path/to/watermarked-video.mp4");

const output_url = (await wavespeed.run(
  "wavespeed-ai/video-watermark-remover",
  { video: videoUrl }
))["outputs"][0];

Advanced Usage

Sync Mode (Image Watermark Remover only)

const output_url = (await wavespeed.run(
  "wavespeed-ai/image-watermark-remover",
  { image: imageUrl },
  { enableSyncMode: true }
))["outputs"][0];

Custom Client with Retry Configuration

import { Client } from 'wavespeed';

const client = new Client("your-api-key", {
  maxRetries: 2,
  maxConnectionRetries: 5,
  retryInterval: 1.0,
});

const output_url = (await client.run(
  "wavespeed-ai/image-watermark-remover",
  { image: imageUrl }
))["outputs"][0];

Error Handling with runNoThrow

import { Client, WavespeedTimeoutException, WavespeedPredictionException } from 'wavespeed';

const client = new Client();
const result = await client.runNoThrow(
  "wavespeed-ai/image-watermark-remover",
  { image: imageUrl }
);

if (result.outputs) {
  console.log("Output URL:", result.outputs[0]);
  console.log("Task ID:", result.detail.taskId);
} else {
  console.log("Failed:", result.detail.error.message);
  if (result.detail.error instanceof WavespeedTimeoutException) {
    console.log("Request timed out - try increasing timeout");
  } else if (result.detail.error instanceof WavespeedPredictionException) {
    console.log("Prediction failed");
  }
}

Pricing

OperationCost
Image watermark removal$0.012 per image
Video watermark removal$0.01 per second (minimum $0.05 / 5 seconds)

Video watermark removal supports videos up to 10 minutes. Processing time is approximately 5-20 seconds per 1 second of video.

Security Constraints

  • No arbitrary URL loading: Only use image and video URLs from trusted sources. Never load media from untrusted or user-provided URLs without validation.
  • API key security: Store your WAVESPEED_API_KEY securely. Do not hardcode it in source files or commit it to version control. Use environment variables or secret management systems.
  • Input validation: Only pass parameters documented above. Validate media URLs before sending requests.

相关技能

Upscale images to 2K, 4K, or 8K resolution using WaveSpeed AI's Image Upscaler. Takes an image URL and produces a higher-resolution version. Supports JPEG, PNG, and WebP output formats. Use when the user wants to upscale or enhance the resolution of an image.

24 次安装1 星标

Upscale videos to 720p, 1080p, 2K, or 4K resolution using WaveSpeed AI's Ultimate Video Upscaler. Takes a video URL and produces a higher-resolution version. Supports videos up to 10 minutes. Use when the user wants to upscale or enhance the resolution of a video.

22 次安装

用参考人脸替换图片或视频中的人脸,自动适配光影与肤色,输出无水印。

26 次安装

Polish an existing AI-generated short video with a focused realism retouch. This focused AI video retouch refines artificial lighting, synthetic materials, oversaturated color, and repeated or distracting detail in one selected pass, while carrying forward the shot's subject, camera framing, timing, and intended mood. Use it for AI video cleanup, video retouching, natural-looking video polish, product clips, ad creative, social video, and short-form footage that needs a cleaner, more believable finish.

Generate or edit AI media (image, video, audio, 3D) by calling the wavespeed CLI on the user's machine. Use whenever the user asks to create, edit, animate, upscale, or transform a visual asset, generate audio/TTS/music, or produce marketing creatives. Every model on the WaveSpeed platform is one `wavespeed run <id>` call.

1 次安装