Apply deterministic image post-processing with background removal, matting, and wordmark addition.
npx skills add https://github.com/neozenith/agentic-dotfiles --skill art-edit
Please help me install this Agent Skill. Skill: art-edit Source: https://github.com/neozenith/agentic-dotfiles/tree/main/skills/art-edit Command: npx skills add https://github.com/neozenith/agentic-dotfiles --skill art-edit
The art-edit Skill streamlines the process of applying deterministic image post-processing operations, such as background removal, matting, and wordmark composition, to images. It operates entirely offline, eliminating the need for API keys or network connections, and provides reproducibility through JSON sidecars.
Run the art-edit skill with the 'remove-bg' command to make the background of an image transparent. For example:
uv run .claude/skills/art-edit/scripts/art_edit.py remove-bg in.png -o logo.png
High-intent search queries and answers about installing and using this skill.
You can remove image backgrounds offline by running the art-edit script with the 'remove-bg' command, which uses U2-Net or threshold methods via rembg and onnxruntime. It requires pre-downloaded models but needs no network connection or API keys.
Yes, reproducible image matting and background removal is possible because the tool generates JSON sidecars for every operation. These sidecars store the exact parameters used, allowing you to precisely reproduce deterministic image post-processing edits later.
The best way to add a wordmark locally is using the wordmark composition feature, which applies a two-tone text wordmark to your image. This operation runs entirely offline using Pillow and NumPy and outputs a reproducible JSON sidecar.
Background removal with rembg works offline using onnxruntime, provided you have pre-downloaded the necessary U2-Net models. Once models are cached locally, no internet connection is required to process images.
Yes, Pillow and NumPy are required dependencies for offline image post-processing. They handle the core image manipulation tasks for background removal, matting, and wordmark addition alongside rembg and onnxruntime.
You should use a simple threshold method instead of U2-Net for background removal when you need a lightweight, deterministic approach without relying on pre-downloaded machine learning models. U2-Net offers higher quality matting but requires model dependencies.
artosetrovRemove image backgrounds from photos using rembg and U²-Net models.
kjayleeAutomate 3D asset pipelines using Blender's Python API for conversion, generation, and rendering.
skaile-aiAnalyze sidecar manifests to propose cross-asset requires edges as JSON.
AngelP17Generate and edit images from prompts using AI models via OpenRouter API.