search

invoke-ai / InvokeAI

Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.
https://invoke-ai.github.io/InvokeAI/
Apache License 2.0
23.64k stars 2.43k forks source link

Add frontend #28

Closed random29 closed 2 years ago

random29 commented 2 years ago

Hello, thanks for your hard work!

Wanted to ask if you could add frontend from this https://github.com/harubaru/waifu-diffusion repository (it's in scripts folder - called txt2img_gradio.py)

lstein commented 2 years ago

Thanks for the suggestion, but I'm not sure that's worth doing now. At some point soon the whole ecosystem will be replaced by interactive image editors that make calls into a stable-diffusion backend. By the time I have understood gradio and have done the implementation, there are going to be so many better solutions!

If there's a developer out there who is versed in gradio and wants to do the implementation, I'd very much welcome a contribution.

morganavr commented 2 years ago

Personally I don't see a benefit of GUI over terminal atm. When inpainting feature will be implemented by somebody it would be very nice to have a GUI to paint over image to specify areas that user wants to be redrawn by AI while keeping all other parts of the original image intact.

random29 commented 2 years ago

Okay, thanks, in that case I guess it's better to wait for interactive image editors