Prompt Squirrel

Prompt Squirrel

Cleans up and groups image prompts that are written as lists of tags, in a Gradio page with sample prompts to try. For people who write tag-style prompts for image models.

Made by FoodDesert 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: Prompt Squirrel is a Gradio app that cleans up and groups image prompts written as lists of tags. The repository holds the data it works from, including tag lists in CSV files, a FastText model file and a TF-IDF file. It also carries sample prompts, sample images and two notebooks.

Who it suits: People who write tag-style prompts for image models and want them tidy and consistent. It also suits developers who want to see how a tag cleaning app is built from data files.

Industry | Who uses it | How they use it | Example
Digital art | Prompt writers | Tidy a long tag list before using it | Try one of the sample prompts
Research | Dataset curators | Look at how tags are organised | Open the CSV data files in a local copy
Software | Developers | Study an app built on tag data and a FastText model | Read app.py and the two notebooks

If you write prompts in plain sentences instead of tags, you can skip it.

Where to use it: The app runs in these places:

• A web browser: open the Space page on Hugging Face and use it there.
• Windows, macOS or Linux: run a copy on your own computer with Python 3.10.12.

Use case | Who | What they get back
Tidy a tag prompt | Prompt writers | A cleaner, organised version of the tags
Try a sample | Newcomers | A ready example prompt to run through the app
Study the data | Developers | CSV files, a FastText model and notebooks to read

How to set it up: You need a few things first:

• Python 3.10.12
• The huggingface_hub package, which the first command installs
• The packages listed in requirements.txt

The repository holds 8596 files, including data files and images, so the download takes a while. The steps download the Space, install Gradio at the version the Space uses, add the other packages and start the app.

1. Install the Hugging Face package.
2. Download the Space into a folder called Prompt_Squirrel.
3. Move into that folder.
4. Install Gradio 5.43.1.
5. Install the packages from requirements.txt.
6. Start the app.

pip install -U huggingface_hub
hf download FoodDesert/Prompt_Squirrel --repo-type space --local-dir Prompt_Squirrel
cd Prompt_Squirrel
pip install gradio==5.43.1
pip install -r requirements.txt
python app.py

How to use it: Open the Space page on Hugging Face, or start the local copy with the last command above. Gradio serves a web page where you work with a tag-based prompt. The card does not list the controls, and SamplePrompts.csv gives you examples to start from.

python app.py

Tool | What it does
hf download | Copies the Space's files into a folder on your computer
python app.py | Starts the app on your own computer

Example: You open the Space, take one of the sample prompts and run it through the app. You then read the tidied version it gives back and compare it with what you started from.

For newcomers and experts: If you are new to this, open the Space page and try a sample prompt. You do not need to install anything for that. A local copy is only worth the setup when you want to read the data and code.

If you know the field, the data files carry the names e621 and fluffyrock_3m, which hints at the tag style the app expects. The word_rating_probabilities.csv file and the TF-IDF file sit beside the FastText model. The notebooks show how images and tags were prepared.

You paste a tag-based prompt
The app compares it with its tag data
Tags are cleaned up and grouped
The organised prompt shows on the page

Good to know: The card is one line, so check the page for what the controls do.

• License: apache-2, as the Space lists it.
• Cost to run: none named. The hosted Space runs on the cpu-basic hardware at Hugging Face.
• Data it reaches: the prompts you enter and the data files in the repository. A local copy downloads all of them from Hugging Face.
• Not for: none stated in the card.

On Hugging Face, 13 November 2026

• Likes: 20
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/FoodDesert/Prompt_Squirrel
• Files: https://huggingface.co/spaces/FoodDesert/Prompt_Squirrel/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.