Overview
A text-to-image research model combining a frozen language encoder with cascaded diffusion; this record marks its paper release.
Imagen
A text-to-image research model combining a frozen language encoder with cascaded diffusion; this record marks its paper release.
Research publication does not establish product availability.
MODEL NUMBER305
- First public date
- 2022-05-23
- Organization
- Google DeepMind
- Family
- Imagen
01
Specifications
Only published specifications are shown.
- Input modalities
- Text
- Output modalities
- Image
- Open weights
- No
- Status
- Legacy
02
Overview
03
Architecture & capabilities
Model capabilities
Image generation
04
Release history
Imagen was announced.
View source05
Related models
Select a card to view the related model.
06
Sources
Suggest a correction
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.