Imagen 4 Ultra Serverless API

Photorealistic images with native 2K resolution and precise text.

~12.07s

 1import requests
 2import json
 3
 4url = "https://api.segmind.com/v1/imagen-4-ultra"
 5headers = {
 6    "x-api-key": "YOUR_API_KEY",
 7    "Content-Type": "application/json"
 8}
 9
10data = {
11    "prompt": "A hyperrealistic portrait of a young woman with freckles in warm golden hour sunlight, cinematic shallow depth of field, ultra-detailed skin texture, professional photography, 8K",
12    "negative_prompt": "blurry, pixelated, ugly, deformed, cartoon, painting",
13    "aspect_ratio": "1:1"
14}
15
16response = requests.post(url, headers=headers, json=data)
17
18if response.status_code == 200:
19    result = response.json()
20    print(json.dumps(result, indent=2))
21else:
22    print(f"Error: {response.status_code}")
23    print(response.text)

 1import requests
 2import json
 3
 4url = "https://api.segmind.com/v1/imagen-4-ultra"
 5headers = {
 6    "x-api-key": "YOUR_API_KEY",
 7    "Content-Type": "application/json"
 8}
 9
10data = {
11    "prompt": "A hyperrealistic portrait of a young woman with freckles in warm golden hour sunlight, cinematic shallow depth of field, ultra-detailed skin texture, professional photography, 8K",
12    "negative_prompt": "blurry, pixelated, ugly, deformed, cartoon, painting",
13    "aspect_ratio": "1:1"
14}
15
16response = requests.post(url, headers=headers, json=data)
17
18if response.status_code == 200:
19    result = response.json()
20    print(json.dumps(result, indent=2))
21else:
22    print(f"Error: {response.status_code}")
23    print(response.text)

API Endpoint

POSThttps://api.segmind.com/v1/imagen-4-ultra

Parameters

promptrequired

string

Text prompt describing the image you want to generate

widthoptional

integer

Width of the generated image in pixels

Default: 512Range: 256 - 1024

heightoptional

integer

Height of the generated image in pixels

Default: 512Range: 256 - 1024

stepsoptional

integer

Number of denoising steps. Higher values generally produce higher quality images

Default: 25Range: 1 - 100

guidance_scaleoptional

number

Controls how closely the model follows the prompt. Higher values = more faithful to prompt

Default: 7.5Range: 1 - 20

negative_promptoptional

string

Negative prompt to specify what you do not want in the image

scheduleroptional

string

Sampling scheduler to use for generation

Default: "DDIM"

Allowed values :

"DDIM""PNDM""LMSDiscrete""DPMSolverMultistep""EulerAncestralDiscrete"

seedoptional

integer

Random seed for reproducible results. Use -1 for random seed

Default: -1Range: -1 - 2147483647

Response Type

Returns: Text/JSON

Common Error Codes

The API returns standard HTTP status codes. Detailed error messages are provided in the response body.

400

Bad Request

Invalid parameters or request format

401

Unauthorized

Missing or invalid API key

403

Forbidden

Insufficient permissions

404

Not Found

Model or endpoint not found

406

Insufficient Credits

Not enough credits to process request

429

Rate Limited

Too many requests

500

Server Error

Internal server error

502

Bad Gateway

Service temporarily unavailable

504

Timeout

Request timed out