PhotoMaker

PhotoMaker

A Gradio demo from TencentARC built on its PhotoMaker models and the RealVisXL image model, with style templates and example inputs. It suits designers and researchers who want to try AI photo making in a browser.

Made by TencentARC 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: PhotoMaker is TencentARC's Gradio demo for its PhotoMaker models. The Space names the PhotoMaker and PhotoMaker-V2 weights, the RealVisXL V3.0 image model and google/ddpm-celebahq-256. The repository holds a pipeline, a model file, a style template file and example inputs.

Who it suits: Designers, content creators and researchers who want to try TencentARC's photo-making models in a browser without a setup. It also suits developers who want to read how the demo is wired together.

Title: Who tries the PhotoMaker demo
Industry | Who uses it | How they use it | Example
Design | Designers | Try an AI photo-making demo with ready styles | Test one of the style templates
Content | Creators | Explore what the models can produce | Run an example input and look at the result
Research | Image generation researchers | Try the PhotoMaker models on their own inputs | Compare the V2 weights with the first release
Software | Developers | Read the pipeline code behind the demo | Open pipeline.py to see how the models connect

If you need detailed documentation of the model's features, you can skip it, since the Space page gives only a configuration note.

Where to use it:

• A web browser: the Space runs on Hugging Face with nothing to install
• Windows, macOS or Linux with Python, from a local copy

Use case | Who | What they get back
Try the models quickly | Anyone | A working demo in a browser tab
Test a style template | Designers | An image made in one of the styles the demo lists
Study the demo code | Developers | A small repository with a pipeline and a model file

How to set it up: Using the Space online needs nothing. A local copy needs Python and the packages the repository lists. The Space runs on ZeroGPU at Hugging Face, so a local copy may need a capable GPU.

• Python with pip
• The Python packages in requirements.txt

1. Install the Hugging Face hub package and download the Space into a folder.
2. Move into that folder.
3. Install Gradio 4.37.2, then the packages from requirements.txt.
4. Start the app with Python.

pip install -U huggingface_hub
hf download TencentARC/PhotoMaker --repo-type space --local-dir PhotoMaker
cd PhotoMaker
pip install gradio==4.37.2
pip install -r requirements.txt
python app.py

How to use it: Open the Space in your browser, or start the local copy with the command below and open the page Gradio serves. The source lists no further steps, so use the controls the page shows.

python app.py

Example: You open the Space and try one of the example inputs that the repository ships in its examples folder. The app runs the PhotoMaker pipeline on it and shows you the result.

For newcomers and experts: If you are new to this, open the Space and start with an example input before using your own. Change one setting at a time to see its effect.

If you know the field, the code is small. A model file and a pipeline file hold the PhotoMaker logic, and a style template file holds the preset styles. The Space names RealVisXL V3.0 and a CelebA-HQ diffusion model next to the PhotoMaker weights. Beyond those names, the source does not describe how they combine.

You open the Space
You pick an example or your own input
The PhotoMaker pipeline runs
The result appears in the page

Good to know:

• Hardware: the Space runs on zero-a10g at Hugging Face
• Newer version: a separate Space exists for PhotoMaker V2
• License: apache-2
• Cost to run: none named

On Hugging Face, 13 November 2026

• Likes: 1,960
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/TencentARC/PhotoMaker
• Files: https://huggingface.co/spaces/TencentARC/PhotoMaker/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.