Imagen
Alphabet's text-to-image line, current generation Imagen 4, reached through the Gemini app and Google Labs' Whisk rather than sold under its own name.
At a glance
Current release
From the release row Imagen 4.
Family record: Official documentation · 18 Sep 2026
Built on it
No product in this catalogue records a dependency on this family yet. That is this directory’s coverage, not a statement about what is built on it.
Releases
-
Imagen
Research text-to-image diffusion model 'with an unprecedented degree of photorealism and a deep level of language understanding'.
-
Imagen 2
Second generation, generally available on Vertex AI for allowlisted customers, adding text and logo rendering.
-
Imagen 3
Announced at Google I/O 2024 as 'our highest quality text-to-image model yet'.
-
Imagen 4
Announced at I/O 2025; GA in the Gemini API and Vertex AI on 2025-08-14. The last Imagen generation: shut down on the Gemini API 2026-08-17 and on Vertex 2026-06-30, with image generation moved to Gemini Image.