DALL - E 2 (Hierarchical Text-Conditional Image Generation with CLIP Latents)

Hi all,

If you haven’t already, I suggest you take a look at “DALL - E 2” from OpenAI. Can, for example, turn a text description into an image corresponding the description. :slight_smile:

Paper: https://cdn.openai.com/papers/dall-e-2.pdf

Web page: DALL·E 2

Note: The reference to Wall·E (WALL·E (2008) - IMDb)

1 Like