Try Gemini 1.5 models, the latest multimodal models in Vertex AI, and see what you can build with up to a 2M token context window. Try Gemini 1.5 models, the latest multimodal models in Vertex AI, and see what you can build with up to a 2M token context window.

Edit using Imagen 2 Controlled Editing

Input image	Other parameters	Output image
Input image. Image source: Alec Cutter on Unsplash.	Prompt: "digital art version" Negative prompt: "black and white" Guide image type: Standard RGB Control condition: canny edge Imagen Control scale: 0.95
Input image. Image source: Alec Cutter on Unsplash (canny edge detection applied).	Prompt: "digital art version" Negative prompt: "black and white" Guide image type: canny edge Imagen Control scale: 0.95

Input image

Other parameters

Output image

Input image. Image source: Alec Cutter on Unsplash.

Prompt: "digital art version"

Negative prompt: "black and white"

Guide image type: Standard RGB

Control condition: canny edge

Imagen Control scale: 0.95

Input image. Image source: Alec Cutter on Unsplash
(canny edge detection applied).

Prompt: "digital art version"

Negative prompt: "black and white"

Guide image type: canny edge

Imagen Control scale: 0.95

Feature and documentation access

This feature and documentation are available to approved users. To request access to use this Imagen feature, fill out the Imagen on Vertex AI access request form. To view all features and their launch stages, see the Imagen on Vertex AI overview.

What's next

Read articles about Imagen and other Generative AI on Vertex AI products: