Serve Stable Diffusion XL on Modal with a number of optimizations for blazingly fast inference.

Run large language models at SOTA performance by building a TRT-LLM engine on Modal.

Fine-tune a Stable Diffusion model on images of your pet using Dreambooth.

Build a real-time voice chat app by combining speech-to-text, an LLM, and text-to-speech.

Build an end-to-end podcast transcription app that leverages dozens of containers for super-fast processing.

Use Modal as an infinitely scalable job queue that can service async tasks from a web app.

Analyze data from the Taxi and Limousine Commission of NYC in parallel.

Build a question-answering web endpoint that can cite its sources.

Use Modal to deploy a cron job that periodically queries Hacker News for new posts, and posts the results to Slack.

Create a web endpoint that leverages HuggingFace models to do object detection in real-time.

Play with all 10 demo Gradio apps from the ControlNet project.