VQGAN + CLIP
Heidelberg UniversityText-to-imageOpen weights
VQGAN + CLIP is text-to-image model published by Heidelberg University in 2020.
About VQGAN + CLIP
Designed to learn long-range interactions on sequential data, transformers continue to show state-of-the-art results on a wide variety of tasks. In contrast to CNNs, they contain no inductive bias that prioritizes local interactions. This makes them
Details
- Provider
- Heidelberg University
- Task
- Text-to-image
- Released
- 2020-12-17
- Open weights
- Yes