# AI use cases for Unbagrnd (zidniryi/unbagrnd) Repo: [zidniryi/unbagrnd](https://github.com/zidniryi/unbagrnd) | Use cases: 4 | Page: https://dedupedai.com/use-cases/zidniryi-unbagrnd/ unbagrnd is a free, open-source desktop app, with a self-hostable REST API, that removes image backgrounds using an AI model that runs on your own device. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Remove backgrounds from a whole folder of photos offline: https://dedupedai.com/use-cases/zidniryi-unbagrnd/batch-remove-backgrounds-from-a-folder/ - Clean up hair edges and export a mask for design tools: https://dedupedai.com/use-cases/zidniryi-unbagrnd/refine-cutout-edges-and-export-a-layer-mask/ - Run the desktop app from source for development: https://dedupedai.com/use-cases/zidniryi-unbagrnd/build-and-run-the-desktop-app-from-source/ - Host a private background removal API with Docker: https://dedupedai.com/use-cases/zidniryi-unbagrnd/self-host-a-background-removal-api/ ## How to remove backgrounds from a whole folder of photos offline with Unbagrnd Repo: [zidniryi/unbagrnd](https://github.com/zidniryi/unbagrnd) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Install the desktop app and cut out the background from many images in one batch, with no uploads. **Who it is for:** A seller, designer, or photographer with a folder of product or portrait photos who needs clean cutouts without sending files to a cloud service. **The problem:** Cutting out backgrounds by hand or uploading photos to a paid cloud tool is slow, costly, or a privacy concern. **The outcome:** A folder of images with transparent or colored backgrounds, exported as PNG, WebP, or SVG, or as a ZIP. ### Steps 1. Download the installer for your platform from the Releases page and install it. 2. Open Unbagrnd, choose the batch option, and select your folder of images. 3. In Settings, pick the output format (PNG, WebP, or SVG) and choose a model that fits your speed and accuracy needs. 4. Optionally set one background color and a drop shadow for the whole batch, and set an output name template such as {name}. 5. Run the batch, retry only the files that failed if any, and export the results as a ZIP. ### Prompt to paste into your agent ```text Using the unbagrnd app from github.com/zidniryi/unbagrnd, process every image in in batch mode and export the results as a ZIP. Expected output: one ZIP file containing one cutout per source image. Verify that the number of images in the ZIP matches the number of source images. ``` ### Caveat The first background removal downloads the model (about 170 MB), and the macOS build runs on Apple Silicon only. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/zidniryi-unbagrnd/batch-remove-backgrounds-from-a-folder/ ## How to clean up hair edges and export a mask for design tools with Unbagrnd Repo: [zidniryi/unbagrnd](https://github.com/zidniryi/unbagrnd) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Refine a cutout's outline and hand edits, then save the alpha channel as a black-and-white matte. **Who it is for:** A graphic designer who needs a precise cutout of a person or animal with fine hair or fur, and a layer mask for Photoshop-style design tools. **The problem:** The AI cutout is close but leaves rough hair edges or small errors, and design tools need the mask as a separate file. **The outcome:** A refined cutout plus a black-and-white matte file that can be used as a layer mask. ### Steps 1. Open the image in Unbagrnd and let the model produce the first cutout. 2. Use the brush to erase or restore small areas, and use undo or redo as needed. 3. Shift, smooth, or feather the outline with the live preview until hair or fur edges look right. 4. Export the mask to save the cutout's alpha channel as a black-and-white matte. 5. Import the matte into your design tool as a layer mask. ### Prompt to paste into your agent ```text Using the unbagrnd app from github.com/zidniryi/unbagrnd, refine the cutout of and export its alpha channel as a black-and-white matte. Expected output: a grayscale image where the subject is white and the background is black. Verify that the matte contains only black and white pixels. ``` ### Caveat Refinement tools work on the output of the on-device model, so very difficult images may still need manual brushwork. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/zidniryi-unbagrnd/refine-cutout-edges-and-export-a-layer-mask/ ## How to run the desktop app from source for development with Unbagrnd Repo: [zidniryi/unbagrnd](https://github.com/zidniryi/unbagrnd) | Difficulty: Intermediate | Time: 60 minutes | Basis: From the README Install Node.js and Rust, then start Unbagrnd in dev mode with hot reload. **Who it is for:** A developer who wants to change the Unbagrnd desktop app or test it on their own machine. **The problem:** Pre-built installers do not help when you need to modify the Tauri app or its Rust backend. **The outcome:** The Unbagrnd desktop app running in dev mode with hot reload, and a native installer built for your OS. ### Steps 1. Install Node.js 20+ and a recent stable Rust (1.88+) through rustup, plus the Tauri prerequisites for your OS. 2. Clone the repository from github.com/zidniryi/unbagrnd and change into the project folder. 3. `npm install` 4. `npm run tauri dev` 5. `npm run tauri build` to produce an installer in src-tauri/target/release/bundle/. ### Prompt to paste into your agent ```text Clone github.com/zidniryi/unbagrnd, install dependencies with npm, and start the app with npm run tauri dev. Expected output: the unbagrnd window opens. Verify that the app starts without build errors and that the frontend loads. ``` ### Caveat Build times and setup depend on the Tauri prerequisites for your OS, and the Rust toolchain must be installed through rustup rather than your OS package manager. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/zidniryi-unbagrnd/build-and-run-the-desktop-app-from-source/ ## How to host a private background removal API with Docker with Unbagrnd Repo: [zidniryi/unbagrnd](https://github.com/zidniryi/unbagrnd) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Run the Axum REST API on your own server, then create API keys for your apps. **Who it is for:** A developer or small team that wants background removal inside its own product, with images staying on its own server. **The problem:** Calling a third-party cloud service sends customer images off your infrastructure and adds per-use cost. **The outcome:** A running background removal API on your server, with a health check that returns ok and a working API key for callers. ### Steps 1. Clone the repository and copy the example environment file. 2. `cp .env.example .env` 3. Edit .env and set UNBAGRND_ADMIN_KEY, for example with `openssl rand -hex 32`. 4. `docker compose up --build` 5. `curl http://localhost:8080/health` should return {"status":"ok"}, then create a key with POST /v1/keys using your X-Admin-Key header. ### Prompt to paste into your agent ```text Clone github.com/zidniryi/unbagrnd, set UNBAGRND_ADMIN_KEY in .env, and start the stack with docker compose up --build. Expected output: a health response of {"status":"ok"} from http://localhost:8080/health. Verify the response and then use a generated key to call POST /v1/remove-background with an image from . ``` ### Caveat The API routes beyond /health and key management are not fully documented in the README excerpt, so check the Swagger UI at /docs for exact request formats. Risk, credentials: The UNBAGRND_ADMIN_KEY controls API key creation and revocation, so store it securely and never commit it to version control. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/zidniryi-unbagrnd/self-host-a-background-removal-api/