- tags
- Transformers, GPT
- paper
- (Ramesh et al. 2021)
Architecture
It is a decoder architecture with a Variational autoencoders and a variant of GPT-3 to convert text to images.
Parameter count
12B
Bibliography
- Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, Ilya Sutskever. . "Zero-shot Text-to-image Generation". arXiv. DOI.