Storytelling

Storytelling

Generates stories with GPT-2 in a Streamlit page and uses an emotion classifier model alongside it. For writers, students and developers exploring emotion-aware text generation.

Made by jitesh 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: Storytelling is a Streamlit app that, by its name, generates stories. The record names two models, GPT-2 for text generation and an English emotion classifier built on DistilRoBERTa. The repository has source and data folders, a setup file and a run script.

Who it suits: It suits writers who want machine-made story drafts, students of text generation, and developers who want a small project with source folders to read. The record does not say how the emotion model is used, so open the page to see.

Industry | Who uses it | How they use it | Example
Writing | Hobby writers | Get a story draft to edit | Start a story and read how it continues
Education | NLP students | See a text generator paired with an emotion model | Read the src folder to see how they connect
Software | Python developers | Study a Streamlit project with data and source folders | Open app.py, setup.py and run.sh

You can skip it if you need finished prose with no editing.

Where to use it:

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

Use case | Who | What they get back
Draft a short story | Writers | Text from the GPT-2 model
Study emotion and generation | Students | A project that combines two models
Reuse as a base | Developers | A Streamlit project with data and source folders

How to set it up:

• Nothing at all if you use the online Space
• Python 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 Streamlit and the listed requirements.
4. Start the app with Streamlit.

pip install -U huggingface_hub
hf download jitesh/storytelling --repo-type space --local-dir storytelling
cd storytelling
pip install streamlit
pip install -r requirements.txt
streamlit run 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 with Streamlit from the Space folder, then use the page it serves. The record does not list the controls, so look at the page.

streamlit run app.py

Example: You open the Space and give it the start of a story. The app continues it with GPT-2 and may use the emotion model in the process. The record shows no sample, so check the page for the exact inputs.

For newcomers and experts: A text generator continues what you give it, one word piece at a time. Start by opening the Space, typing a short story opening and reading what comes back.

If you know the field, GPT-2 is a small older language model, so output can drift and repeat. The emotion model labels text by feeling, which hints at a way to steer or check the mood. The record gives no details on how, so read the src folder.

You enter a story opening
GPT-2 continues the text
The emotion model labels the feeling of the text
The page shows the story

Good to know:

• License: MIT, as listed on the Space
• Cost to run: none named
• Data it reaches: the text you enter, the two models it names and the files in its data folder
• Not for: the record names no exclusions, so read generated text before you share it

On Hugging Face, 13 November 2026

• Likes: 1
• Built with: streamlit
• License: mit

Links

• Space: https://huggingface.co/spaces/jitesh/storytelling
• Files: https://huggingface.co/spaces/jitesh/storytelling/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.