菜单
Remove backgrounds from images using rembg (IS-Net / U2Net). Outputs transparent PNGs or composites onto a solid colour or custom backdrop image. Works on portraits, products, and general subjects.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Schedule, create, and manage social media posts on Instagram and LinkedIn using the Buffer GraphQL API. Use when the user wants to publish content, schedule posts, check scheduled posts, list connected channels, or create content ideas on Buffer.
Research SEO opportunities through audits, keyword discovery, traffic validation, and site architecture analysis.
Maintains and applies brand identity across all content operations. Ensures every output aligns with the personal brand's voice, values, and visual identity.
MCP skill for canva. Provides 23 tools: upload-asset-from-url, upload-asset-from-file, resolve-shortlink, search-designs, get-design, get-design-pages, get-design-content, get-presenter-notes, import-design-from-url, merge-designs, export-design, get-export-formats, create-folder, move-item-to-folder, list-folder-items, search-folders, comment-on-design, list-comments, list-replies, reply-to-comment, generate-design, create-design-from-candidate, list-brand-kits
Plan ads, generate ad creative, and configure paid acquisition measurement. Use for paid campaign setup and tracking.
Generate growth ideas and low-cost marketing approaches. Use for campaign ideation, growth planning, and free-tool strategy exploration.
| name | background-remover |
| description | Remove backgrounds from images using rembg (IS-Net / U2Net). Outputs transparent PNGs or composites onto a solid colour or custom backdrop image. Works on portraits, products, and general subjects. |
| metadata | {"openclaw":{"emoji":"✂️","requires":{"bins":["uv"]}}} |
Removes image backgrounds using rembg (IS-Net by default). The foreground can be kept as a transparent PNG or composited onto a custom background.
The skill directory (where this SKILL.md lives) is referred to as $SKILL_DIR below.
Use this skill when the user wants to:
cd "$SKILL_DIR" && uv sync
Model weights are downloaded automatically on first use (~180 MB for IS-Net).
Before I process the images, I need to know:
✂️ Background
- none — keep as transparent PNG
- #rrggbb — solid colour (e.g. "#ffffff" or "#1a1a2e")
- /path/to/img — composite onto a background image
🧠 Model (optional, default: isnet-general-use)
- isnet-general-use — best for most subjects
- u2net_human_seg — optimised for people
- isnet-anime — optimised for illustrated/anime characters
⚙️ Device
- auto — GPU if available, else CPU (default)
- cpu — force CPU (~3s/image via ONNX CPU provider)
📁 Input / output directories (default: ./input and ./output)
cd "$SKILL_DIR" && uv run python scripts/rembg_batch.py --config config.json
| Key | Values | Default | Description |
|---|---|---|---|
input_dir | path | ./input | Source image folder |
output_dir | path | ./output | Destination folder |
model | see models below | isnet-general-use | Segmentation model |
bg | null / hex / path | null | Background (null = transparent) |
output_format | png, webp | png | Output format |
device | auto, cpu, cuda | auto | Inference device |
Available models: isnet-general-use, isnet-anime, u2net, u2net_human_seg, u2netp, birefnet-general
# Transparent PNG
cd "$SKILL_DIR" && uv run python scripts/rembg_batch.py
# White background
cd "$SKILL_DIR" && uv run python scripts/rembg_batch.py --bg "#ffffff"
# Dark brand background
cd "$SKILL_DIR" && uv run python scripts/rembg_batch.py --bg "#0d1117"
# Custom backdrop image
cd "$SKILL_DIR" && uv run python scripts/rembg_batch.py --bg ./brand-backdrop.jpg
# Force CPU
cd "$SKILL_DIR" && uv run python scripts/rembg_batch.py --device cpu
# Portrait-optimised model
cd "$SKILL_DIR" && uv run python scripts/rembg_batch.py --model u2net_human_seg
Processed images written to output_dir as PNG (or WebP), same stem as input.