PlayTale AI is an endless game that uses on-device AI to unleash your imagination and take you to your own imaginary world. With dynamic content generated on the go, you'll never run out of stories.
I often lose myself in daydreams, crafting intricate stories and vivid worlds. With PlayTale AI, I've brought those daydreams to life, creating a Windows application that lets users build and explore their own unique narratives.
What it does
PlayTale AI uses an LLM (running on the device) to create dynamic stories based on the theme selected by the user. The application also considers age when generating stories to keep them friendly, fun, and interactive for people of all age groups.
How we built it
The frontend is built using React and Electron. To access the on-device AI, APIs from LM Studio were used.
Challenges we ran into
One of the bigger challenges was getting quick results to maintain user interest. In addition, I also had to do prompt engineering to get the desired outputs in the correct format from the AI model.
Accomplishments that we're proud of
I am very proud that in the end, I was able to put everything together and finally create exactly what I envisioned. Additionally, I am also happy that the application could be used by people of all ages.
What we learned
To begin with, I learned how easy it is to integrate on-device AI into an application using the tools provided in the competition. During the hackathon, I also learned new techniques of prompt engineering. Finally, I also got a chance to experiment with the Qualcomm Device on Cloud and really appreciate the user experience I had with the platform.
What's next for The PlayTale
One thing I would definitely like to add is image generation. Using the scene data from the text generation model, AI images could be created. This would enhance the user experience and make the overall experience more fun.
Log in or sign up for Devpost to join the conversation.