Generate images using Imagen 3

Developing

POST

https://generativelanguage.googleapis.com/v1beta/models/imagen-3.0-generate-002:predict

The Gemini API provides access to Imagen 3, Google's highest quality text-to-image model, featuring a number of new and improved capabilities. Imagen 3 can do the following:

Generate images with better detail, richer lighting, and fewer distracting artifacts than previous models

Understand prompts written in natural language

Generate images in a wide range of formats and styles

Render text more effectively than previous models

Request Example

Shell

JavaScript

Java

Swift

curl --location -g --request POST 'https://generativelanguage.googleapis.com/v1beta/models/imagen-3.0-generate-002:predict?key=' \
--header 'Content-Type: application/json' \
--data-raw '{
        "instances": [
          {
            "prompt": "Robot holding a red skateboard"
          }
        ],
        "parameters": {
          "sampleCount": 4
        }
      }'

Response Example

{}

Request

Query Params

key

string

required

Example:

Header Params

Content-Type

string

required

Example:

application/json

Body Params application/json

instances

array [object {1}]

required

prompt

string

optional

parameters

object

required

sampleCount

integer

required

Examples

Responses

🟢200成功

application/json

Body

object {0}

Image editing with Gemini

Use thinking models