Recraft V4.1 Pro
FLUX.2 Pro
No longer available
The publisher shut this model down on September 24, 2025. It can no longer be used from its own API. Recommended replacement: gemini-2.5-flash-image. Publisher notice
- Pricing
- Not published
- Released
- 4y ago
Cost
Google's first Imagen text-to-image diffusion model, later offered on Vertex AI. Retired on Vertex AI.
How it compares
Level
FlagshipThe lab's most capable generally available line, priced for hard tasks.
Vs. your stack
Add the models you use to see how this one compares.
Sign inText provenance
Gemini app/webGoogle SynthID text watermarking
Google DeepMind says text generated in the Gemini app and web experience is watermarked with SynthID by adjusting token probabilities.
Official explanationFrequently asked questions
Quality and benchmarks
The closest alternatives are Midjourney V3 by Midjourney, Midjourney V2 by Midjourney, and Stable Diffusion 1.4 by Stability AI. They were matched on model kind and release date, with no comparable price.
Midjourney V3Imagen vs Midjourney V3Midjourney V2Imagen vs Midjourney V2Stable Diffusion 1.4Imagen vs Stable Diffusion 1.4
Qwen-Image-2.1, the highest-ranked open-weight model on Arena Text to Image at rank 21. Imagen itself is closed.
Versions and lineage
Yes. Imagen was retired on September 24, 2025, and the publisher's recommended replacement is Nano Banana (Gemini 2.5 Flash Image).
Licensing and access
No, Imagen is closed. Its license is proprietary.
Basics
Imagen was made by Google DeepMind and released on May 23, 2022.
Media
No, image editing via image input is not listed for Imagen.
Generated from Vertical Tabs data, updated November 5, 2026.
Discussion
No comments yet
Be the first to share your thoughts.