Background Removal — model skill for images & thumbnails

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

Cut subjects out of photos into clean transparent PNGs with BiRefNet.

• Type: Model · Images & thumbnails
• Slug: inference-sh-background-removal
• Status: live
• Publisher: inference.sh (vendor, verified)
• License: MIT
• Source: https://github.com/inference-sh/skills/tree/main/tools/image/background-removal
• Works in: Claude Code, Codex, Cursor, Gemini CLI
• Requires: inference.sh account, belt CLI (belt login)
• Cost: Billed by inference.sh
• Adoption: 7 installs, 781 GitHub stars (skills.sh, 2026-10-26)

What it does

Removes image backgrounds with BiRefNet through the inference.sh CLI, producing transparent PNGs ready for compositing. It targets product photos, portraits and e-commerce images.

Use when

• Removing a photo background
• Transparent product cutouts
• Preparing a subject for compositing

Install

• Claude Code: npx skills add inference-sh/skills --skill background-removal -a claude-code
• Codex: npx skills add inference-sh/skills --skill background-removal -a codex
• Cursor: npx skills add inference-sh/skills --skill background-removal -a cursor
• Gemini CLI: npx skills add inference-sh/skills --skill background-removal -a gemini-cli

Models it drives: birefnet

Example output

https://skills.varg.ai/previews/inference-sh-background-removal.webp — BiRefNet output from fal's BiRefNet model page (inference.sh self-hosts the same open model as infsh/birefnet): a tree frog cut out of its mossy background as a transparent PNG (credit: fal (BiRefNet example), https://fal.ai/models/fal-ai/birefnet)

More images & thumbnails skills

• Higgsfield YouTube Thumbnail: Design truthful, high-CTR YouTube thumbnails and vertical covers with up to three consistent faces.
• Slack GIF Creator: Make animated GIFs that pass Slack's limits: 128×128 emoji or 480×480 message GIFs, validated on export.
• PixiJS GIFs: Load, play and control animated GIFs inside a PixiJS v8 scene.
• AI Image Generation: Generate images with 50+ models from one CLI: GPT Image 2.5, FLUX, Gemini, Grok, Seedream, Reve and more.
• FLUX Image: Generate and restyle images with FLUX Dev LoRA and FLUX.2 Klein, including custom LoRA styles.
• GPT Image: Generate and edit images with OpenAI GPT Image 2.5 and GPT Image 2 from the command line.

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.

• Claude Code: claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg (skill + hosted MCP)
• Codex, Cursor, Gemini CLI, OpenClaw: npx skills add vargHQ/skills --skill varg-ai -a <agent> -y
• Claude.ai, ChatGPT, any MCP client: connect https://mcp.varg.ai/mcp
• API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt