AI-Image-Generation\Offline\Stable-Deffusion-Model 🚀

[ParagGhatage]

Fixes: #232

Me and @Karn-x7 worked on this together and made this possible with couple of sleepless night.

PR OVERVIEW
This PR basically adds custom AI image generation which would work offline and would generate images from the user prompt .

Our Approach
We used one of the stable diffusion models which we trained, tweaked, fine tuned - a lot of optimization .
we took the model which was consuming the space around 8GB storage,4GB ram(for working)
And now guess what -
-This model only takes around 4GB STORAGE and ram less than 500mb.

-And wrapped the backend implementation in Fast API for seamless integration.

{Frontend}
-And for the frontend we created a very sweet, subtle, landing page which is highly interactive
With some great animation like you can see a star bouncing and many more .

-Which is dynamically adaptive to Dark Mode.
-And added a dynamic promt functionality to enhance UX.

Working Video-
BTW, this prompt was his idea. @Karn-x7 😂

image-generation.mp4

Sample images-

Prompt: Astronaut in a jungle, cold color palette, muted colors, detailed, 8k

Prompt: School in cosmic style

Prompt: Desert view in realistic style

[Karn-x7]

bro you forgot some secret ingredients.🤯
doses of coffee intake
i use to sleep on my morning alarm.
My laptop is cooked testing so many model i had clean

WORKING FLOWCHART @Pranav0-0Aggarwal

[Pranav0-0Aggarwal]

CC: discord convo