Giters

lucidrains / DALLE-pytorch

Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

creating image variations

athena913 opened this issue · comments

commented

Hi,

Thanks for releasing the code. I trained the DiscreteVAE and DALLE transformer models on a custom dataset. The trained VAE is able to reconstruct a given image and the trained transformer is able to generate images for a given text. Currently it appears that I need to provide text to create image variations. How can I generate variations of a given image without providing any text input either using the trained DiscreteVAE on its own or using the trained transformer?

thanks