Omni Video Factory

Omni Video Factory

Makes video from text, makes video from an image, and extends an existing clip, on a Gradio page that runs in the browser. For creators who want quick AI video tests with nothing to install.

Made by vamo455 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: Omni Video Factory is a Gradio page for AI video, published by vamo455. It handles three jobs: making a video from text, making a video from an image, and extending a video. The repository name mentions an automatic prompt and high quality. You can open the page in the browser with nothing to install.

Who it suits: It suits people who want to try AI video generation without setting up a machine, and developers who want to read how such a page is organised.

Industry | Who uses it | How they use it | Example
Marketing | Content creators | Test short video ideas before a real shoot | Turn a written idea into a clip
Design | Designers | Animate a still picture | Start from one image and ask for a video
Media | Editors | Lengthen an existing clip | Use the extend job on a short video
Software | Python developers | Read how a video page is built on Gradio | Look through app.py and the src folder

Skip it if you need fixed clip lengths or fine control, since the source describes only the three jobs.

Where to use it:

• A web browser, on the Space's page at Hugging Face, which runs on ZeroGPU
• Your own Windows, macOS or Linux computer with Python 3.12

Use case | Who | What they get back
Video from a written idea | Creators | A generated clip
Video from a picture | Designers | A clip that starts from your image
Longer video | Editors | A lengthened version of a clip you supply

How to set it up: The online page needs nothing. A local copy needs Python and two lists of packages.

• Python 3.12 and pip
• Python packages from requirements.txt
• System packages from packages.txt, which the Space installs with apt-get
• Windows, macOS or Linux

1. Install the Hugging Face hub library.
2. Download the Space's files into a folder named Omni-videos-custom-auto_prompt_high-quality.
3. Move into that folder.
4. Install Gradio 5.44.1, then the packages from requirements.txt.
5. Start app.py.

pip install -U huggingface_hub
hf download vamo455/Omni-videos-custom-auto_prompt_high-quality --repo-type space --local-dir Omni-videos-custom-auto_prompt_high-quality
cd Omni-videos-custom-auto_prompt_high-quality
pip install gradio==5.44.1
pip install -r requirements.txt
python app.py

How to use it: Open the Space's page and pick one of the three jobs. For a local copy, run the last command above and open the address it prints in your browser.

python app.py

Example: You open the page, give it a written idea and ask for a video. The page works on it and returns a clip you can watch in the browser.

For newcomers and experts: Open the online page and try the text job with one short sentence. Watch the result before you move on to the image job.

The app is built with Gradio 5.44.1 on Python 3.12, and its main file is app.py. The Hugging Face copy runs on ZeroGPU hardware. The repository also holds AGENTS.md, DEPLOY.md, an index.html and a src folder. The record names no model and no settings, so the automatic prompt and quality choices are for you to read in the code.

Open the page
Choose text, image or extend
Give it your text, image or clip
Watch the video it returns

Good to know:

• Hardware: The Hugging Face copy runs on ZeroGPU hardware.
• Gaps: The record names no model, so limits and settings are not described here.
• License: mit.
• Cost to run: none named.
• Data it reaches: Text, images and video clips you give it.

On Hugging Face, 13 November 2026

• Likes: 426
• Built with: gradio
• License: mit

Links

• Space: https://huggingface.co/spaces/vamo455/Omni-videos-custom-auto_prompt_high-quality
• Files: https://huggingface.co/spaces/vamo455/Omni-videos-custom-auto_prompt_high-quality/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.