Anime Face Detector

Anime Face Detector

Finds anime faces in an image and estimates 28 landmark points on each, in plain PyTorch behind a Gradio page. For artists, dataset builders and machine learning developers.

Made by hysts 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 Gradio app is a demo of an anime face detector. It finds faces in anime-style images and estimates 28 landmark points on each one, using plain PyTorch. The record names a set of sample images from the TADNE collection as its data.

Who it suits: It suits artists, dataset builders and machine learning developers who work with anime-style images and want faces located or marked. It also suits learners who want a small, readable Gradio demo.

Industry | Who uses it | How they use it | Example
Illustration | Digital artists | Check where a model places face landmarks on a drawing | Upload a character picture and view the marks
Data work | Dataset builders | Locate faces before cropping or labeling | Run a sample image and note the face boxes
Software | Python developers | Read a small PyTorch demo wrapped in Gradio | Open app.py and requirements.txt

You can skip it if your images are photos of real people, since the model is built for anime-style faces.

Where to use it:

• A web browser, on the Space's page on Hugging Face
• Python 3.12 on Windows, macOS or Linux, from a downloaded copy

Use case | Who | What they get back
Detect faces in anime art | Artists and builders | Detected faces on the image
Mark facial landmarks | Developers | 28 landmark points per face
Reuse as a base | Learners | A small Gradio app to adapt

How to set it up:

• Nothing at all if you use the online Space
• Python 3.12 on your computer, only if you run a copy
• The packages listed in requirements.txt

1. Open the Space's page in a browser to use it with nothing to install.
2. To run a copy, install the Hugging Face Hub package and download the Space.
3. Move into the new folder, then install the pinned Gradio version and the listed requirements.
4. Start the app with Python.

pip install -U huggingface_hub
hf download hysts/anime-face-detector --repo-type space --local-dir anime-face-detector
cd anime-face-detector
pip install gradio==6.19.0
pip install -r requirements.txt
python app.py

How to use it: Online, open the Space and use the controls on its page. On your own machine, run the main file from the Space folder, then use the page it serves. The record does not list the controls, so look at the page.

python app.py

Example: You open the Space and give it an anime-style picture. The app finds the faces in it and marks the 28 landmark points on each. The record shows no sample output, so the exact display depends on the page.

For newcomers and experts: Face detection means a program finds where faces are in a picture, and landmarks are small marked points such as eyes and mouth. Start by opening the Space and trying one anime picture.

If you know the field, the demo uses plain PyTorch for both detection and landmark estimation, and it pins a specific Gradio version. The record gives no accuracy figures, so check results on your own images.

You give the page an image
The Gradio page sends it to app.py
The model finds the faces
It estimates 28 landmarks per face
The page shows the marked image

Good to know:

• License: MIT, as listed on the Space
• Cost to run: none named
• Data it reaches: the images you give it and the sample images it names
• Not for: the record names no exclusions, and the model targets anime-style faces

On Hugging Face, 13 November 2026

• Likes: 17
• Built with: gradio
• License: mit

Links

• Space: https://huggingface.co/spaces/hysts/anime-face-detector
• Files: https://huggingface.co/spaces/hysts/anime-face-detector/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.