Stable Diffusion, an open-source text-to-image model developed by stability.ai has officially been released
Bit lost? Don’t worry, we’re here to explain.
You can give the AI model a text prompt and it will create an image in pretty much whatever style you can think of.
Sound familiar? You’ve probably come across DALL-E or Midjourney before, but they’re not open-source. Open-source breeds experimentation, anyone can grab the code, tweak it and insert it into their own apps.
Here is what our Innovation Manager Giorgio Liapakis thinks will happen next:
- Expect an explosion of apps and services to start integrating this tech, finding new ways to use it outside of just creating novelty art.
- Expect a new category of artists to emerge that “co-create” with the AI.
- Expect a time period of cringe when big companies will try to aggressively commercialize it quickly without innovating on top of it.
- Bad people will probably use it to do bad things, but the good should outweigh it.
Want to know how you can get involved?
Create an account for the web app DreamStudio, get creative with your prompts and generate some breathtaking concepts!
Share your thoughts on Stable Diffusion and AI integration in the comments below!