Skip to main content
Image models

Ideogram 4.0 — Generate API

Generate with Ideogram 4.0: request parameters, examples and response handling.

← Ideogram 4.0

Endpoint: POST https://api.higgsfield.ai/ideogram/v4.0

Endpoint ID: ideogram/v4.0

▶Open API PlaygroundIdeogram 4.0 · Generate↗

#Usage notes

  • Omit image_url for text-to-image; provide image_url for remix/editing.
  • image_weight controls preservation of the input image and applies to editing requests only; values are integers from 1 to 100.
  • The square 1:1 aspect ratio is applied by default, including when an input image is supplied.
  • rendering_speed values are case-sensitive: TURBO, DEFAULT, QUALITY. prompt must contain 2–2048 characters.

#Quick start

cURL
curl --request POST \
  --url https://api.higgsfield.ai/ideogram/v4.0 \
  --header "Authorization: Key ${HF_API_KEY_ID}:${HF_API_KEY_SECRET}" \
  --header "Content-Type: application/json" \
  --header "Idempotency-Key: ${IDEMPOTENCY_KEY}" \
  --data '{
  "prompt": "A ceramic vase on a wooden table beside a sunlit window, soft natural shadows, editorial photograph.",
  "aspect_ratio": "1:1",
  "rendering_speed": "DEFAULT"
}'

#Input schema

prompt string required

Write your prompt here Minimum characters: 2. Maximum characters: 2048.

image_url string

Public URL of the input image. Format: uri.

aspect_ratio string (default: 1:1)

Output width-to-height ratio. Allowed values: "1:1", "1:2", "2:1", "2:3", "3:2", "4:5", "5:4", "9:16", "16:9", "5:8", "8:5", "3:4", "4:3", "9:22", "22:9", "9:23", "23:9", "3:8", "8:3", "5:12", "12:5", "1:3", "3:1".

image_weight integer

How strongly the output should preserve the input image. Minimum: 1. Maximum: 100.

rendering_speed string (default: DEFAULT)

Allowed values: "TURBO", "DEFAULT", "QUALITY".

Complete JSON schema
json
{
  "type": "object",
  "title": "Ideogram 4.0 Playground",
  "required": [
    "prompt"
  ],
  "properties": {
    "prompt": {
      "type": "string",
      "title": "Prompt",
      "maxLength": 2048,
      "minLength": 2,
      "description": "Write your prompt here"
    },
    "image_url": {
      "type": "string",
      "title": "Input image",
      "format": "uri"
    },
    "aspect_ratio": {
      "enum": [
        "1:1",
        "1:2",
        "2:1",
        "2:3",
        "3:2",
        "4:5",
        "5:4",
        "9:16",
        "16:9",
        "5:8",
        "8:5",
        "3:4",
        "4:3",
        "9:22",
        "22:9",
        "9:23",
        "23:9",
        "3:8",
        "8:3",
        "5:12",
        "12:5",
        "1:3",
        "3:1"
      ],
      "type": "string",
      "title": "Aspect ratio",
      "default": "1:1"
    },
    "image_weight": {
      "type": "integer",
      "title": "Image weight",
      "maximum": 100,
      "minimum": 1,
      "description": "How strongly the output should preserve the input image."
    },
    "rendering_speed": {
      "enum": [
        "TURBO",
        "DEFAULT",
        "QUALITY"
      ],
      "type": "string",
      "title": "Rendering speed",
      "default": "DEFAULT"
    }
  },
  "additionalProperties": false
}

#Response

Submission returns a request handle. Poll status_url until status is completed, or use webhooks.

Accepted
{
  "status": "queued",
  "request_id": "REQUEST_ID",
  "status_url": "https://api.higgsfield.ai/requests/REQUEST_ID/status",
  "cancel_url": "https://api.higgsfield.ai/requests/REQUEST_ID/cancel"
}

A completed response includes the following output fields:

json
{
  "status": "completed",
  "request_id": "REQUEST_ID",
  "images": [
    {
      "url": "https://example.com/output.png"
    }
  ]
}

See idempotent requests, polling, request errors and authentication for shared request handling.

Was this page helpful?
Navigation