Imagen 4.0 Generate - Generate Image (AI Model · By )

API Documentation

API Reference

Images

Generate Image

Supported Model Code

Loading models...

Imagen 4.0 Generate (imagen-4-generate)

imagen-4-generate0 models support this endpoint

Google Imagen 4 is an advanced image generation model capable of delivering high-quality visual performance, with strong prompt-following capabilities and stable generation results across various styles and scenarios.

Generate image

https://api.modelstream.ai

POST/v1/images/generations

Authentication

BearerAuth

AuthenticationBearer <token>

All API requests must be authenticated using a Bearer token in the Authorization header. Please ensure your API key is active.Authorization: Bearer sk-xxxxxx

Parameter Location: Header Param

Request Body

application/json

These parameters come from the selected model form_schema. Switching models updates this list and the request example.

prompt*string

Text description of the image. Imagen 4 excels at detail, text rendering and photorealism; the more specific the prompt, the better.

RequiredExample Value: A futuristic architectural design, glass and steel, sunset lighting, ultra realistic.Placeholder: Describe the image you want in detail: subject, style, lighting, camera, etc.

negative_prompt?string

Negative prompt to exclude unwanted elements, styles or artifacts. Optional.

Placeholder: Describe what you do NOT want to appear (optional)...

size?string

Aspect ratio of the output image. Imagen 4 supports 1:1, 3:4, 4:3, 9:16, 16:9. Default 1:1.

Example Value: 1:1

Enum/Options:

1:13:44:39:1616:9

image_size?string

Output image resolution. Imagen 4 Standard supports 1K and 2K. Default 1K.

Example Value: 1K

Enum/Options:

n?number

Number of images to generate per request, 1 to 4. Default 1.

Example Value: 1Value Range: 1 ≤ value ≤ 4step: 1

person_generation?string

Controls whether people may be generated. 'Allow All' is not available in the EU, UK, Switzerland, and MENA regions. Default Allow Adult.

Example Value: allow_adult

Enum/Options:

Allow All: allow_allAllow Adult: allow_adultDon't Allow: dont_allow

seed?number

Random seed, from 1 to 2147483647. The same seed with the same parameters reproduces consistent results. Leave empty for random.

Placeholder: Leave empty for random seedValue Range: 1 ≤ value ≤ 2147483647

Response Parameters

application/json

200apiDocs.responses.successGenerateImage

created?integer

Parameter description for Created

data?array

Parameter description for Data

curl -X POST "https://api.modelstream.ai/v1/images/generations" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "imagen-4-generate",
  "prompt": "A futuristic architectural design, glass and steel, sunset lighting, ultra realistic.",
  "n": 1,
  "size": "1:1",
  "quality": "1K",
  "personGeneration": "allow_adult",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "A futuristic architectural design, glass and steel, sunset lighting, ultra realistic."
        }
      ]
    }
  ]
}'

{
  "created": 0,
  "data": [
    {
      "url": "string",
      "b64_json": "string",
      "revised_prompt": "string"
    }
  ]
}

API Documentation

API Reference

Images

Generate Image

Supported Model Code

Loading models...

Imagen 4.0 Generate (imagen-4-generate)

imagen-4-generate0 models support this endpoint

Generate image

https://api.modelstream.ai

POST/v1/images/generations

Authentication

BearerAuth

AuthenticationBearer <token>

All API requests must be authenticated using a Bearer token in the Authorization header. Please ensure your API key is active.Authorization: Bearer sk-xxxxxx

Parameter Location: Header Param

Request Body

application/json

These parameters come from the selected model form_schema. Switching models updates this list and the request example.

prompt*string

Text description of the image. Imagen 4 excels at detail, text rendering and photorealism; the more specific the prompt, the better.

RequiredExample Value: A futuristic architectural design, glass and steel, sunset lighting, ultra realistic.Placeholder: Describe the image you want in detail: subject, style, lighting, camera, etc.

negative_prompt?string

Negative prompt to exclude unwanted elements, styles or artifacts. Optional.

Placeholder: Describe what you do NOT want to appear (optional)...

size?string

Aspect ratio of the output image. Imagen 4 supports 1:1, 3:4, 4:3, 9:16, 16:9. Default 1:1.

Example Value: 1:1

Enum/Options:

1:13:44:39:1616:9

image_size?string

Output image resolution. Imagen 4 Standard supports 1K and 2K. Default 1K.

Example Value: 1K

Enum/Options:

n?number

Number of images to generate per request, 1 to 4. Default 1.

Example Value: 1Value Range: 1 ≤ value ≤ 4step: 1

person_generation?string

Controls whether people may be generated. 'Allow All' is not available in the EU, UK, Switzerland, and MENA regions. Default Allow Adult.

Example Value: allow_adult

Enum/Options:

Allow All: allow_allAllow Adult: allow_adultDon't Allow: dont_allow

seed?number

Random seed, from 1 to 2147483647. The same seed with the same parameters reproduces consistent results. Leave empty for random.

Placeholder: Leave empty for random seedValue Range: 1 ≤ value ≤ 2147483647

Response Parameters

application/json

200apiDocs.responses.successGenerateImage

created?integer

Parameter description for Created

data?array

Parameter description for Data

curl -X POST "https://api.modelstream.ai/v1/images/generations" \
  -H "Authorization: Bearer <token>" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "imagen-4-generate",
  "prompt": "A futuristic architectural design, glass and steel, sunset lighting, ultra realistic.",
  "n": 1,
  "size": "1:1",
  "quality": "1K",
  "personGeneration": "allow_adult",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "A futuristic architectural design, glass and steel, sunset lighting, ultra realistic."
        }
      ]
    }
  ]
}'

{
  "created": 0,
  "data": [
    {
      "url": "string",
      "b64_json": "string",
      "revised_prompt": "string"
    }
  ]
}