Hacker News Reader

Stable Diffusion 1.x isn't original work either; it uses OpenAI CLIP.

But training your own is pretty doable if you have the budget and enough image/text pairs. Most people don't have the budget, but at least Midjourney and Google have their own models.

Adobe Firefly is not based on Stable Diffusion.

(i work for Adobe)

Where did you read that they were using Stable Diffusion?

This is not based on just fine tuning Stable Diffusion.