InstantID

InstantID

A Gradio demo built around the InstantX/InstantID model, with a Stable Diffusion XL pipeline, ControlNet depth and canny models and style templates, online or on your computer.

Made by InstantX 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: InstantID is a Gradio demo that InstantX published as a Hugging Face Space. It names the InstantX/InstantID model along with ControlNet depth and canny models, an LCM LoRA for SDXL and a Depth Anything model. The repository holds an SDXL pipeline file, a style template file and folders for examples, models and an IP adapter.

Who it suits: People who want to try the InstantID model in a browser, and developers who want a larger image generation demo to read or run themselves.

Industry | Who uses it | How they use it | Example
Creative work | Image makers | Open the Space to try the model it names | Looking at what the demo offers before running anything locally
Machine learning | Researchers | Download the files and read the pipeline code | Studying how the model, ControlNet and the IP adapter are put together
Software development | Gradio developers | Read app.py and the style template file | Seeing how a larger image demo is laid out in Gradio

Skip it if you want a hosted service with an API, since this is an app you open or run yourself.

Where to use it: InstantID runs in these places.

• A web browser: open the Space's page on Hugging Face
• Python on Windows, macOS or Linux: run a copy of the Space

Use case | Who | What they get back
Try it online | Anyone with a browser | The Gradio demo running from the Space
Run it locally | Developers with Python | A copy of the app started from app.py
Read the code | Learners | The pipeline file, style templates, examples and the IP adapter folder

How to set it up: Online use needs only a browser. A local copy needs a few things first.

• A web browser for the online Space
• Python on Windows, macOS or Linux for a local copy
• The Python packages listed in requirements.txt

1. Install the Hugging Face hub library with pip.
2. Download the Space's files into a folder called InstantID.
3. Move into that folder.
4. Install Gradio at the version the Space uses.
5. Install the packages listed in requirements.txt.
6. Start the app with Python.

pip install -U huggingface_hub
hf download InstantX/InstantID --repo-type space --local-dir InstantID
cd InstantID
pip install gradio==4.40.0
pip install -r requirements.txt
python app.py

How to use it: Online, open the Space's page and use the demo in your tab. On your own computer, start it from the folder with the command below.

python app.py

Tool | What it does
python app.py | Starts the Gradio app from the main file
pip install -r requirements.txt | Installs the packages the app needs
hf download | Fetches the Space's files into a local folder

Example: You download the Space with the hf command, install Gradio 4.40.0 and the listed packages, then run python app.py. The demo starts from your local copy of the files.

For newcomers and experts: If you are new, open the Space's page and look at what the demo offers. Running it online needs no setup, so start there before you try a local copy.

If you know the field, the repository bundles an SDXL pipeline file for InstantID, an IP adapter folder and a torchhub folder, and it names depth and canny ControlNet checkpoints. A local copy pins Gradio 4.40.0. The Space itself uses zero-a10g hardware at Hugging Face, so a local run depends on your own machine.

Open the Space or run app.py
Gradio serves the demo
You use it in your browser

Good to know: It is a single Gradio demo, so what you can do is limited to what its page offers.

• Version: Gradio 4.40.0
• Models named: six repositories, covering InstantID, two ControlNet checkpoints, an LCM LoRA, Depth Anything and the original ControlNet
• Size: 107 files in the repository
• License: apache-2
• Cost to run: none named
• Data it reaches: the models it names, none else named
• Not for: no forbidden uses are named

On Hugging Face, 13 November 2026

• Likes: 3,659
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/InstantX/InstantID
• Files: https://huggingface.co/spaces/InstantX/InstantID/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.