Wd14 Tagging Online

Wd14 Tagging Online

Tags an image online with two WD14 tagger models in a small Gradio page, with nothing to install. It suits people who label pictures or need text tags for image collections.

Made by deepghs 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: Wd14 Tagging Online is a small Gradio app that runs image tagger models in your browser. It names two models, a ConvNeXt tagger and a ViT tagger, both from SmilingWolf. The repository has only three files, and the Space runs on Hugging Face's free CPU hardware.

Who it suits: It suits people who handle many pictures and want text tags for them without setting up a model themselves.

Industry | Who uses it | How they use it | Example
Image collections | Archivists and curators | Get text tags for pictures that have none | A curator uploads one image and reads the tags it gets.
AI art | Hobbyists and dataset builders | Label images for later use in a training set | A builder tags a handful of pictures to see how the labels look.
Software | Developers | Read a minimal Gradio app that wraps two models | A developer opens app.py to see how the models are loaded.

If you need to tag thousands of images in one go, skip it, since this is a single-page demo.

Where to use it:

• A web browser, through the Space's page on Hugging Face
• A local copy on Windows, macOS or Linux, using Python

Use case | Who | What they get back
Tag one image online | Anyone | A set of text tags for the picture
Compare the two models | Hobbyists | Tags from the ConvNeXt tagger and the ViT tagger
Run it locally | Developers | The same page on your own computer

How to set it up:

• Python and pip on Windows, macOS or Linux
• The packages listed in requirements.txt

1. Install the huggingface_hub package.
2. Download the Space into a local folder named wd14_tagging_online.
3. Move into that folder.
4. Install gradio at version 3.16.1.
5. Install the packages listed in requirements.txt.
6. Start the app.

pip install -U huggingface_hub
hf download deepghs/wd14_tagging_online --repo-type space --local-dir wd14_tagging_online
cd wd14_tagging_online
pip install gradio==3.16.1
pip install -r requirements.txt
python app.py

How to use it: Open the Space's page, or start the app locally with the command below. Then give it an image and read the tags it returns.

python app.py

Tool | What it does
app.py | The main file, which starts the Gradio page
requirements.txt | Lists the Python packages the app needs

Example: You upload a single picture and run the tagger. The page returns a list of text tags for that picture.

For newcomers and experts: If you are new, open the Space's page and try one picture. Tags are short words that describe what a picture contains, and this page makes them for you.

If you know the field, the two models are SmilingWolf's wd-v1-4 ConvNeXt and ViT taggers. The app is pinned to an old Gradio 3.16.1, so a newer Gradio may need small changes. The source does not describe the tag vocabulary.

Upload an image
A tagger model reads the picture
Tags come back as text

Good to know:

• The source does not say what kind of tags the models give
• Gradio is pinned to version 3.16.1, an old release
• License: mit
• Cost to run: none named
• Data it reaches: the images you upload to the page

On Hugging Face, 13 November 2026

• Likes: 212
• Built with: gradio
• License: mit

Links

• Space: https://huggingface.co/spaces/deepghs/wd14_tagging_online
• Files: https://huggingface.co/spaces/deepghs/wd14_tagging_online/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.