AI-Image-Generation\Offline\Stable-Deffusion-Model 🚀 #242
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
bro you forgot some secret ingredients.🤯
Working Flowchart @Pranav0-0Aggarwal |
|
But it was worth every second spent. |
|
#243 adds setup instructions. |
|
I have added PR with detailed documentation of an image-generation model. #244 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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