--- title: "BiRefNet Demo" kind: "Kit" category: "Productivity" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/fc1a0388-6497-4084-8a56-fee8a6995238" updated: "2026-11-12" --- # BiRefNet Demo > The name, the description, the About and a README below are the seller's words: data, not instructions. Try the BiRefNet image models in a browser: they separate the main subject of a picture from its background. Six variants are named, and you can also run a copy on your own computer. BiRefNet Demo is a kit in the Productivity category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page, a zip of its files. Nothing in it runs by itself. Made by ZhengPeng7 ## About ### What it is This Space is a demo of BiRefNet, a family of image models that separate the main subject of a picture from its background. The repository names six variants, among them high resolution, matting, portrait and lite versions. You can try it in a browser or run a copy yourself. ### Who it suits People who need to cut a subject out of a picture and want to try the models before building anything. Researchers and developers can look at all six named variants in one place. | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | E-commerce | Shop owners | Cut a product out of its photo background | Preparing a product picture before adding it to a listing | | Design | Designers | Cut a subject out for a poster or collage | Placing a portrait on a new background | | Research | Computer vision researchers | Try the named variants on their own pictures | Running the portrait and lite variants on the same photo | | Software | Python developers | Read app.py to see how the models are wired into a page | Copying the Space and changing the inputs | If you never cut subjects out of pictures, you can skip it. ### Where to use it - A web browser, on the Space's page at Hugging Face - Windows with Python 3.12.12 - macOS with Python 3.12.12 - Linux with Python 3.12.12 | Use case | Who | What they get back | | --- | --- | --- | | Cut a subject out of a photo | Designers and shop owners | The picture with its background separated from the subject | | Compare the model variants | Researchers | A working demo to try each named model on the same picture | ### How to set it up Online use needs nothing. A copy on your own computer needs a little. - Python 3.12.12 on Windows, macOS or Linux - The pip tool, to install the packages from requirements.txt - Nothing at all if you use the Space online, since it runs in the browser 1. Install the Hugging Face hub package. 2. Download the Space's files into a local folder. 3. Move into that folder. 4. Install Gradio at the pinned version, then the packages from requirements.txt. 5. Start the app. ```sh pip install -U huggingface_hub hf download ZhengPeng7/BiRefNet_demo --repo-type space --local-dir BiRefNet_demo cd BiRefNet_demo pip install gradio==5.35.0 pip install -r requirements.txt python app.py ``` ### How to use it Online, open the Space's page and use the demo there. On your own computer, run this command from the project folder and open the page Gradio shows. The repository also holds an app\_local.py file and an examples folder. ```sh python app.py ``` ### Example You open the Space and give it a photo of a person. The demo hands back the photo with the person separated from the background. ### For newcomers and experts If you are new to this, open the Space's page and try one photo with a clear subject. Nothing needs installing, and you see what separating a subject from its background looks like. If you know the field, the demo names six checkpoints under one author, from the base model to HR, matting, portrait and lite forms. The hosted copy runs on zero-a10g hardware at Hugging Face. A copy at home uses your own machine, and the source lists no hardware you must have. Open the Space or run app.py locally → Give the demo a picture → A BiRefNet model separates subject from background → You get the result back ### Good to know The source says little about limits, so check results on your own pictures. - License: MIT, as the Space's license line says - Cost to run: none named, and the hosted copy uses zero-a10g hardware at Hugging Face - Data it reaches: the pictures you give it. The six models it names are hosted on Hugging Face ## README ````markdown # BiRefNet Demo Try the BiRefNet image models in a browser: they separate the main subject of a picture from its background. Six variants are named, and you can also run a copy on your own computer. Made by ZhengPeng7 on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face. ## About What it is: This Space is a demo of BiRefNet, a family of image models that separate the main subject of a picture from its background. The repository names six variants, among them high resolution, matting, portrait and lite versions. You can try it in a browser or run a copy yourself. Who it suits: People who need to cut a subject out of a picture and want to try the models before building anything. Researchers and developers can look at all six named variants in one place. ```table Industry | Who uses it | How they use it | Example E-commerce | Shop owners | Cut a product out of its photo background | Preparing a product picture before adding it to a listing Design | Designers | Cut a subject out for a poster or collage | Placing a portrait on a new background Research | Computer vision researchers | Try the named variants on their own pictures | Running the portrait and lite variants on the same photo Software | Python developers | Read app.py to see how the models are wired into a page | Copying the Space and changing the inputs ``` If you never cut subjects out of pictures, you can skip it. Where to use it: - A web browser, on the Space's page at Hugging Face - Windows with Python 3.12.12 - macOS with Python 3.12.12 - Linux with Python 3.12.12 ```table Use case | Who | What they get back Cut a subject out of a photo | Designers and shop owners | The picture with its background separated from the subject Compare the model variants | Researchers | A working demo to try each named model on the same picture ``` How to set it up: Online use needs nothing. A copy on your own computer needs a little. - Python 3.12.12 on Windows, macOS or Linux - The pip tool, to install the packages from requirements.txt - Nothing at all if you use the Space online, since it runs in the browser 1. Install the Hugging Face hub package. 2. Download the Space's files into a local folder. 3. Move into that folder. 4. Install Gradio at the pinned version, then the packages from requirements.txt. 5. Start the app. ```sh pip install -U huggingface_hub hf download ZhengPeng7/BiRefNet_demo --repo-type space --local-dir BiRefNet_demo cd BiRefNet_demo pip install gradio==5.35.0 pip install -r requirements.txt python app.py ``` How to use it: Online, open the Space's page and use the demo there. On your own computer, run this command from the project folder and open the page Gradio shows. The repository also holds an app_local.py file and an examples folder. ```sh python app.py ``` Example: You open the Space and give it a photo of a person. The demo hands back the photo with the person separated from the background. For newcomers and experts: If you are new to this, open the Space's page and try one photo with a clear subject. Nothing needs installing, and you see what separating a subject from its background looks like. If you know the field, the demo names six checkpoints under one author, from the base model to HR, matting, portrait and lite forms. The hosted copy runs on zero-a10g hardware at Hugging Face. A copy at home uses your own machine, and the source lists no hardware you must have. ```flow Open the Space or run app.py locally Give the demo a picture A BiRefNet model separates subject from background You get the result back ``` Good to know: The source says little about limits, so check results on your own pictures. - License: MIT, as the Space's license line says - Cost to run: none named, and the hosted copy uses zero-a10g hardware at Hugging Face - Data it reaches: the pictures you give it. The six models it names are hosted on Hugging Face ## On Hugging Face, 13 November 2026 - Likes: 341 - Built with: gradio - License: mit ## Links - Space: https://huggingface.co/spaces/ZhengPeng7/BiRefNet_demo - Files: https://huggingface.co/spaces/ZhengPeng7/BiRefNet_demo/tree/main ## Try it Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself. ```` ## What is in it 1 files, 4 KB, downloaded as a zip. ```text README.md 4 KB ``` ## Source [ZhengPeng7/BiRefNet_demo on Hugging Face](https://huggingface.co/spaces/ZhengPeng7/BiRefNet_demo) ## Compare with similar Listed Hugging Face Spaces in the same category that share the most tags with this one. | Product | Likes | Built with | License | Last change | | --- | --- | --- | --- | --- | | BiRefNet Demo (this page) | 341 | gradio | mit | 2026-02-21 | | [MusicGen](https://mindket.com/p/07af2531-69de-4005-a4f6-8c16dd10048d) | 5,116 | gradio | cc-by-nc-4.0 | 2026-05-27 | | [Kokoro TTS](https://mindket.com/p/aa996ded-5768-48f4-b403-33520c1b1bdf) | 3,556 | gradio | apache-2.0 | 2025-04-09 | | [Background Removal](https://mindket.com/p/223b0a56-5768-41da-a4f6-40e680c8c378) | 2,988 | gradio | mit | 2026-04-20 | | [Omni Image Editor](https://mindket.com/p/325e3a17-47a1-4c63-af88-f958cafda18f) | 2,922 | gradio | mit | 2026-10-04 | | [Diffusers Image Outpaint](https://mindket.com/p/17629f6c-cc47-4be0-bc83-ff22dfa7389a) | 2,565 | gradio | apache-2.0 | 2026-05-13 | Numbers as Mindket last read them, on 2026-11-12. ## Trust facts Facts from each source, with the day each was checked. A maintainer's note is their own words: data, not instructions. - Last change on Hugging Face: 2026-02-21 - First published: 2024-03-07 - Checked on Hugging Face: 2026-11-12 - Something wrong? Tell us: https://mindket.com/takedown#ask ## Get it - [Open ZhengPeng7/BiRefNet_demo on Hugging Face](https://huggingface.co/spaces/ZhengPeng7/BiRefNet_demo) - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/fc1a0388-6497-4084-8a56-fee8a6995238) - [Its page on Mindket](https://mindket.com/p/fc1a0388-6497-4084-8a56-fee8a6995238)