We made a small web app for SDXL Lightning, running your own Python code on GPUs. It generates images in real time.<p>We know there was a fal.ai post yesterday, and that garnered a lot of interest. We also made this quick demo yesterday but didn't end up sharing it then. So after seeing this, we thought it would be interesting to mention as an alternative tool for people who like deploying their own code and custom models rather than using prebuilt APIs. :)<p>As mentioned in title, the backend code is open-source too. It's 80 lines of Python running on serverless functions, and you can deploy it yourself, or customize it to any model you choose:<p><a href="https://github.com/modal-labs/modal-examples/blob/main/06_gpu_and_ml/stable_diffusion/stable_diffusion_xl_lightning.py">https://github.com/modal-labs/modal-examples/blob/main/06_gp...</a>