Imagen 3
Imagen 3 announced at I/O: photorealism with fewer artifacts and markedly better in-image text rendering.
Described by Google as its highest-quality text-to-image model, with improved detail and legible text. Rolled into ImageFX, Gemini and Vertex AI during 2024; an updated version shipped 2024-12-16.
- Date
- Tuesday, 14 May 2024
- Lab
- Google DeepMind
- Kind
- model
- Access
- closed API
Sources
- blog.google/technology/ai/google-generative-ai-veo-imagen-3/
- blog.google/technology/google-labs/video-image-generation-update-december-2024
This record was checked against its sources on 6 October 2026. How we check