Imagen
A text-to-image research model combining a frozen language encoder with cascaded diffusion; this record marks its paper release.
FAMILY / GOOGLE DEEPMIND
Imagen
Google DeepMind’s high-quality image family focused on detail, typography, and flexible resolution.
- First model
- 2022
- Models
- 4
- Latest dated version
- Imagen 4
01 / RELEASE SEQUENCE
Family release sequence
02 / GENERATIONS
What changed
Imagen 2
An image-generation model offered to approved Vertex AI customers, improving image quality and text rendering.
Imagen 3
A major Google text-to-image generation with better detail, lighting, and prompt adherence.
Imagen 4
The base Imagen 4 service model with up to 2K output, multiple aspect ratios, and stronger detail, spelling, and typography; Ultra and Fast are not treated as aliases.