glid-3-xl VS meadowrun-dallemini-demo

If you’re anything like us, though, you’ll feel compelled to poke around the code and run the model yourself. We’ll do that in this article using Meadowrun, an open-source library that makes it easy to run Python code in the cloud. For ML models in particular, we just added a feature for requesting GPU machines in a recent release. We’ll also feed the images generated by DALL·E Mini into additional image processing models (GLID-3-xl and SwinIR) to improve the quality of our generated images. Along the way we’ll deal with the speedbumps that come up when running open-source ML models on EC2.

Personally, I've found GLID3 and GLID3-XL to be nice and straightforward. Worked right out of the box.

GLID-3-XL?

I've been using the Glid-3 XL model. Here are some examples of what I've been able to do with it:

This was made with Glid-3 XL

The above notebooks use GitHub repo GLID-3-XL from Jack000. Regarding CLIP guidance, Jack000 states, "better adherence to prompt, much slower" (compared to classifier-free guidance).

For the second half of this article, we’ll use meadowdata/meadowrun-dallemini-demo which contains a notebook for running multiple models as sequential batch jobs to generate images using Meadowrun. The combination of models is inspired by jina-ai/dalle-flow.