DEV Community

Habib-Ahmad
Habib-Ahmad

Posted on

1 1 1 1 1

Generate my Pet

This is a submission for the Cloudflare AI Challenge.

What I Built

This is a fun pet generation app. You generate a seed which contains the essence of your pet. Then you feed it words. Whatever you say to it will affect how it grows. You can tell it to become a princess or a warrior. Try out different words to get different outcomes!

Demo

https://generate-my-pet.pages.dev/

My Code

https://github.com/Habib-Ahmad/generate-my-pet

Journey

I actually learned about this hackathon fairly late. After reading through the requirements I realized that, in essence, it was a creativity competition which is an area I've never really been confident in. So even with limited time left I decided to challenge myself and make a submission.

I used NextJS for this project which means I had to learn how to use the NextJS api which I had been procrastinating for a long time. Creating the apis was a real challenge especially with models that expected data binaries. I had to learn about buffers and streams (which are still a bit confusing) but I'm happy with what I've been able to submit.

Moving forward I'd like to significantly improve the UI as well as make it responsive. I'd also like to include the model for sentiment analysis to be able to get more details from the words form the user.

The models I used are:

  1. uform-gen2-qwen-500m
  2. stable-diffusion-xl-lightning
  3. whisper

Multiple Models and/or Triple Task Types

  1. uform-gen2-qwen-500m
  2. stable-diffusion-xl-lightning
  3. whisper

API Trace View

Struggling with slow API calls?

Dan Mindru walks through how he used Sentry's new Trace View feature to shave off 22.3 seconds from an API call.

Get a practical walkthrough of how to identify bottlenecks, split tasks into multiple parallel tasks, identify slow AI model calls, and more.

Read more →

Top comments (0)

A Workflow Copilot. Tailored to You.

Pieces.app image

Our desktop app, with its intelligent copilot, streamlines coding by generating snippets, extracting code from screenshots, and accelerating problem-solving.

Read the docs

👋 Kindness is contagious

Please leave a ❤️ or a friendly comment on this post if you found it helpful!

Okay