Skip to content

Pratik-Prakash-Sannakki/AI_Text-Image-Generator

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

34 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AI Text-Image Generator

An Application that genrates realistic-photo images with text input. The application was developed using PyQT5 with PyTorch-Cuda version. Model used in this project is Stable diffusion.

Stable Diffusion is a latent text-to-image diffusion model capable of generating High Resolution photo-realistic images given any text input.

Medium Article

https://medium.com/@pratikpsannakki1/text-to-image-a-gan-based-application-12e9248ea8d7

Results

the above images were geneareted by inputs "Bear on Mars", "a photo of an astronaut riding a horse on mars", "A fantasy landscape, trending on artstation"

User Interface

Commands

  1. pip install --upgrade diffusers transformers scipy
  2. huggingface-cli login
  3. pip install requirements.txt
  4. python app.py

Note - Authentication token has to be generated from: https://huggingface.co/docs/hub/security-tokens