Where's the image generation code

[iBobbyTS]

This page from Open-AI official website lead me here, it says that "DALL·E is a 12-billion parameter version of GPT-3 trained to generate images from text descriptions", but in this repo called DALL-E, it says "The transformer used to generate the images from the text is not part of this code release."

Where should I go if I want to do real image generation? Is Open-AI going to release your pre-trained model?

[erinbeesley]

this is just the VAE - it can encode and decode images.. there is no text transformer part included in this. for text-to-image avaliable at the moment, please check out https://twitter.com/advadnoun's notebooks using CLIP to guide various image generators - it's almost as good as Dall-e - maybe even better artistically :)

[corbett3289]

Says it isn't included at this time so not an issue. But man do I want it.