Text to Image taks 🚀

[Atharva Phatak]

🚀 Feature

We all have been hearing about stable diffusion nowadays don't we ? I would like to integrate diffusers as backend for Text-To-Image tasks.

Motivation

Pitch

Simply follow the procedure as other tasks more or less. Ofcourse I am not sure of training pipeline for diffusion models but it would be fun to have Text-to-Image tasks. This could inturn be integrated as a component for apps :)

Alternatives

Additional context

I would love to work on this integration ❤️