---
name: sticker-rip
description: One-shot background remover. Turn any image (or folder of images) into transparent PNG stickers using rembg's U2Net model. Outputs clean alpha cutouts ready to be layered as VFX assets in cinema-x-gif, kromvision-gif-flips, or any compositing workflow. Use when the user asks for "rip the background", "make this transparent", "cutout the subject", "sticker pack", "alpha channel cutout", or wants to extract subjects from photos for sample-flip / VFX overlays.
---


# sticker-rip

Drop-in subject cutout. Image (or folder) in, transparent PNG sticker(s) out.

Built on [`rembg`](https://github.com/danielgatis/rembg) using U2Net by default. Output PNGs have a real alpha channel — composite straight onto video in ffmpeg or any NLE.

## Single image

```bash
python3 ~/.claude/skills/sticker-rip/scripts/rip.py --input /path/to/photo.jpg
# → /path/to/photo_ripped/photo.png
```

## Folder of images

```bash
python3 ~/.claude/skills/sticker-rip/scripts/rip.py --input /path/to/folder --output /path/to/stickers
# processes every .jpg/.jpeg/.png/.webp in the folder
```

## Pick a different model

```bash
python3 ~/.claude/skills/sticker-rip/scripts/rip.py --input pic.jpg --model isnet-general-use
```

Available models:
- `u2net` *(default)* — best general-purpose
- `u2netp` — lighter/faster
- `u2net_human_seg` — humans only, sharpest on people
- `isnet-general-use` — high-quality alternative
- `birefnet-portrait` — best portraits, larger model

## Parallel batch

```bash
python3 ~/.claude/skills/sticker-rip/scripts/rip.py --input folder/ --batch-size 8
```

## First-run install

The script auto-installs `rembg` + `onnxruntime` on first run. Models download lazily on first use of each model — about 170MB for `u2net`.

## Pairs well with

- `cinema-x-gif` — drop these stickers onto footage as transparent VFX flips
- `kromvision-gif-flips` — same, with the Kromvision aesthetic
- `canvas-gen` — cut a subject and turn it into a Spotify Canvas loop