PuLID-FLUX

PuLID-FLUX

A Gradio app that works with the FLUX.1 image models on ZeroGPU hardware, with several supporting models named in its record. For people exploring FLUX image generation, though the README gives no instructions.

Made by yanze 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: PuLID-FLUX is a Gradio app that works with the FLUX.1 family of image models. It names FLUX.1-dev, FLUX.1-Krea-dev and FLUX.1-schnell, plus SDXL-Lightning, an antelopev2 model and an image content-check model from Falconsai. The README holds only a configuration pointer, so it does not say more about what the app does.

Who it suits: People who want to try an image generation app built on FLUX.1, and developers who want to read how such an app is put together.

Industry | Who uses it | How they use it | Example
Design | Designers | Try FLUX based image generation | Open the Space and use the example inputs
AI development | Developers | Study a FLUX pipeline in Python | Read the folders named flux and pulid
Research | Researchers | See how several image models are combined | Look at the models the Space names

People who need documented settings or a user guide can skip it, because the README gives none.

Where to use it:

• A browser: the Space runs on Hugging Face with nothing to install
• Windows, macOS or Linux: run a copy of the Space with Python 3.10

Use case | Who | What they get back
Try the app | Designers | Generated images from the Space's page
Study the code | Developers | The flux, pulid, eva_clip and models folders
Try ready inputs | Newcomers | The sample files in example_inputs

How to set it up:

• Python 3.10 with pip on Windows, macOS or Linux
• The Python packages listed in requirements.txt
• Nothing at all if you only use the Space in a browser

1. Install the Hugging Face hub package.
2. Download the Space's files into a folder.
3. Move into that folder.
4. Install Gradio 5.39.0 and the packages from requirements.txt.
5. Start the app.

pip install -U huggingface_hub
hf download yanze/PuLID-FLUX --repo-type space --local-dir PuLID-FLUX
cd PuLID-FLUX
pip install gradio==5.39.0
pip install -r requirements.txt
python app.py

How to use it: Open the Space page in a browser, or start your own copy with the command below. The README gives no steps, so the controls on the Gradio page are your guide.

python app.py

Example: You open the Space and try one of the sample files from its example_inputs folder. Going by the models it names, the app returns a generated image.

For newcomers and experts: If you are new, open the Space in a browser and try a sample input. Nothing needs installing, and the page itself shows what the app can do.

For experts, the repository holds app.py with folders named eva_clip, flux, models and pulid. The Space names several FLUX.1 variants, SDXL-Lightning, DIAMONIK7777/antelopev2 and a Falconsai content-check model, and runs on zero-a10g hardware.

You open the Space
You give the app an input
The FLUX based pipeline runs
You get the generated image

Good to know:

• License: apache-2
• Cost to run: none named
• Data it reaches: the inputs you give it, and the models it names
• Not for: none stated in the README

On Hugging Face, 13 November 2026

• Likes: 2,122
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/yanze/PuLID-FLUX
• Files: https://huggingface.co/spaces/yanze/PuLID-FLUX/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.