← 返回 Skills 市场
okaris

Background Removal

作者 Ömer Karışman · GitHub ↗ · v0.1.5
cross-platform ⚠ suspicious
1711
总下载
0
收藏
7
当前安装
2
版本数
在 OpenClaw 中安装
/install background-removal
功能描述
Remove backgrounds from images with BiRefNet via inference.sh CLI. Model: BiRefNet (high accuracy background removal). Use for: product photos, portraits, e-...
使用说明 (SKILL.md)

Background Removal

Remove backgrounds from images via inference.sh CLI.

Background Removal

Quick Start

curl -fsSL https://cli.inference.sh | sh && infsh login

infsh app run infsh/birefnet --input '{"image_url": "https://your-photo.jpg"}'

Install note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available.

How To

Use Reve for image editing including background changes:

infsh app run falai/reve --input '{
  "prompt": "remove the background, make it transparent",
  "image_url": "https://portrait.jpg"
}'

Or change background directly:

infsh app run falai/reve --input '{
  "prompt": "change the background to a beach",
  "image_url": "https://product-photo.jpg"
}'

Workflow: Generate and Edit

# 1. Generate an image
infsh app run falai/flux-dev-lora --input '{"prompt": "a cute robot mascot"}' > robot.json

# 2. Edit with Reve
infsh app run falai/reve --input '{
  "prompt": "remove background, transparent",
  "image_url": "\x3Curl-from-step-1>"
}'

Use Cases

  • E-commerce: Clean product photos
  • Portraits: Professional headshots
  • Marketing: Assets for design
  • Social Media: Profile pictures
  • Design: Elements for compositions

Output

Returns a PNG with transparent background.

Related Skills

# Full platform skill (all 150+ apps)
npx skills add inference-sh/skills@inference-sh

# Image generation
npx skills add inference-sh/skills@ai-image-generation

# FLUX models (including inpainting)
npx skills add inference-sh/skills@flux-image

# Upscaling
npx skills add inference-sh/skills@image-upscaling

Browse all image apps: infsh app list --category image

Documentation

安全使用建议
This skill appears to do what it says: it uses inference.sh to remove image backgrounds. Before installing, review the remote installer script (https://cli.inference.sh) yourself and verify checksums from the publisher's checksums.txt rather than piping blindly to sh. Be aware that images you send will be processed by the inference.sh service (privacy/PII risk) and that 'infsh login' will create or store credentials/tokens. If you prefer reduced risk, run the installer in an isolated environment (VM/container) or use a vetted local/background-removal tool instead. If you plan to run the suggested 'npx skills add' commands, remember those will pull additional packages from the npm registry — inspect them if you have security concerns.
功能分析
Type: OpenClaw Skill Name: background-removal Version: 0.1.5 The skill is classified as suspicious due to the inclusion of `curl -fsSL https://cli.inference.sh | sh` in the `SKILL.md` file. This command downloads and executes a remote shell script, which is a significant supply chain risk and a direct remote code execution vulnerability. While the stated purpose is to install a legitimate CLI, this method lacks auditability and could lead to arbitrary code execution if the remote script is compromised or malicious. This constitutes a risky capability without clear malicious intent within the provided files.
能力评估
Purpose & Capability
The name/description (background removal using BiRefNet) matches the runtime instructions which call the inference.sh CLI and specific image apps; nothing requested in the SKILL.md is unrelated to image background removal.
Instruction Scope
Instructions stay on-task (invoke infsh to run models and edit images). They do require running a remote installer (curl | sh https://cli.inference.sh) and performing 'infsh login' which will communicate with the inference.sh service and may store credentials/tokens; the skill does not instruct reading unrelated files or env vars.
Install Mechanism
There is no formal install spec in the registry; the SKILL.md recommends piping a remote install script (cli.inference.sh) into sh and later uses npx to add other skill packages. Downloading and executing an installer from a third‑party domain is higher risk — although the page claims checksum verification, execution of remote scripts and npm package pulls should be validated before running.
Credentials
The skill declares no required env vars, which is consistent with the metadata. However, it calls 'infsh login' (interactive authentication) without declaring credentials; installing/using the CLI will likely create or require account credentials or tokens managed outside the skill metadata.
Persistence & Privilege
The skill does not request always:true or system-wide config changes. It relies on an external CLI that you (or the agent) would install; the skill itself does not request elevated privileges or permanent platform presence.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install background-removal
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /background-removal 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v0.1.5
- Added detailed instructions and examples for using BiRefNet model via inference.sh CLI for background removal. - Included workflow examples for image generation and editing, and use cases across e-commerce, portraits, marketing, and design. - Expanded documentation links and related skills for broader image editing capabilities. - Clarified output format as PNG with transparent background.
v0.1.0
Initial release of the background-removal skill. - Remove backgrounds from images using BiRefNet via the inference.sh CLI. - Supports high-accuracy cutouts for product photos, portraits, e-commerce, and photo editing. - Includes step-by-step guides for quick start, transparent background, and background replacement workflows. - Lists relevant use cases and related skills for image editing, upscaling, and generation. - Returns a PNG with a transparent background as output.
元数据
Slug background-removal
版本 0.1.5
许可证
累计安装 7
当前安装数 7
历史版本数 2
常见问题

Background Removal 是什么?

Remove backgrounds from images with BiRefNet via inference.sh CLI. Model: BiRefNet (high accuracy background removal). Use for: product photos, portraits, e-... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1711 次。

如何安装 Background Removal?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install background-removal」即可一键安装,无需额外配置。

Background Removal 是免费的吗?

是的,Background Removal 完全免费(开源免费),可自由下载、安装和使用。

Background Removal 支持哪些平台?

Background Removal 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Background Removal?

由 Ömer Karışman(@okaris)开发并维护,当前版本 v0.1.5。

💬 留言讨论