Skip to content

Text-to-Image Synthesis using Multimodal (VQGAN + CLIP) Architectures

Notifications You must be signed in to change notification settings

sbmagar/VQGAN-CLIP-Text-to-Image

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 
 
 
 
 

Repository files navigation

VQGAN-CLIP-Text-to-Image

Project is here: Link to Colab
All step-by-step explanations of codes: Link to the post

Read story on Medium: Link to Medium
I guarantee that you'll completely understand every single steps. And complete a advanced GAN project.

text prompt(input): #A man fighting with a bull

Output: After 100 epochs
crop:


result: