Welcome to the AI Stories Factory, your friendly neighborhood AI video app!
If you haven’t tried it yet, go here to try the app 👉 AI Stories Factory on Hugging Face
The AI Stories Factory presents a new approach to AI content generation, by letting anyone generate a multi-scenes music video from a single prompt.
This is a new form of prompt engineering, and this guide (which is still a work in progress) will tell you how to do it!
<aside> ⚠️ Please exercise caution when using the AI Stories Factory. AI models for text, music, video and sound may be subject to cultural biases or factual errors, and often generate hallucinations which some viewers might find disturbing so user’s discretion is advised. Generated content is for non-commercial use only.
</aside>
It all begins with a prompt, which can be as simple as a single keyword:
Then select your favorite video orientation by clicking on this toggle:
Then click on “Generate”:
Prompt: “Jellyfishes”
<aside> 🤗 This free and open-source model is not on the same quality level as Sora or Veo. Please don’t be too disappointed if you see visual artifacts or glitches, eg. “fade out” effects on moving objects or people. Thank you for your understanding, and remember to have fun!
</aside>
Note: Keywords to type in the prompt are in yellow
Currently speech dialogues are not finished yet, as an alternative we display captions by default.