Ideogram 3 Remix Serverless API

Ideogram 3 Remix enables versatile image transformation, enhancing creativity through customizable design iterations.

~10.54s
POST /v2/ideogram-3-remix · submit + poll
 1# pip install "segmind>=1.1.0"
 2# export SEGMIND_API_KEY="YOUR_API_KEY"
 3import segmind
 4
 5# Async (v2): submit to the queue and block until COMPLETED.
 6# run() returns the final result dict (600s deadline, 1.0s poll by default).
 7result = segmind.run(
 8    "ideogram-3-remix",
 9    prompt="Majestic waterfall under moonlight",
10    image="https://segmind-resources.s3.amazonaws.com/output/5cdc7a1e-14a5-4cdd-9b0f-ed7097114933-e1f80202-4999-4cb7-b89e-ed378cfc2b5a.jpeg",
11    image_weight=50,
12    seed=6522,
13    resolution="1024x1024",
14    rendering_speed="DEFAULT",
15    magic_prompt="AUTO",
16    negative_prompt="No people, no buildings",
17    style_codes=[],
18    style_type="GENERAL",
19    style_reference_images=[],
20)
21print(result["status"])                      # COMPLETED
22print(result.get("output"))                  # model output (e.g. media URL)
23print(result["metrics"]["inference_time"])   # server compute seconds
24
25# --- Or submit + poll manually (track request_id, control the cadence) ---
26from segmind import SegmindClient, InferenceFailed, InferenceTimeout
27
28client = SegmindClient()                      # reads SEGMIND_API_KEY
29payload = {
30    "prompt": "Majestic waterfall under moonlight",
31    "image": "https://segmind-resources.s3.amazonaws.com/output/5cdc7a1e-14a5-4cdd-9b0f-ed7097114933-e1f80202-4999-4cb7-b89e-ed378cfc2b5a.jpeg",
32    "image_weight": 50,
33    "seed": 6522,
34    "resolution": "1024x1024",
35    "rendering_speed": "DEFAULT",
36    "magic_prompt": "AUTO",
37    "negative_prompt": "No people, no buildings",
38    "style_codes": [],
39    "style_type": "GENERAL",
40    "style_reference_images": [],
41}
42job = client.submit_async("ideogram-3-remix", **payload)
43print(job.request_id)                         # available immediately
44try:
45    result = job.wait(timeout=600, interval=1.0)
46except InferenceTimeout as e:
47    print("still running:", e.request_id)
48except InferenceFailed as e:
49    print("failed:", e.detail)

API Endpoint

POSThttps://api.segmind.com/v1/ideogram-3-remix

Parameters

imagerequired
string (uri)

Initial image for creation. Opt for images matching the desired theme or scene.

Default: "https://segmind-resources.s3.amazonaws.com/output/5cdc7a1e-14a5-4cdd-9b0f-ed7097114933-e1f80202-4999-4cb7-b89e-ed378cfc2b5a.jpeg"
promptrequired
string

Guide image creation. Use detailed prompts like 'majestic waterfall under moonlight' for specific themes.

Default: "Majestic waterfall under moonlight"
aspect_ratiooptional
string

Defines aspect ratio. Use 1x1 for square, others for different dimensions.

Default: null
Allowed values (15 total):
"1x3""3x1""1x2""2x1""9x16""16x9""10x16""16x10""2x3""3x2"+5 more
color_paletteoptional
any | any

A color palette for generation

One of:
Preset Color Paletteoptional
any
namerequired
string
Custom Color Paletteoptional
any
membersrequired
object[]
image_weightoptional
integer

Sets the influence of the base image. Increase for strong influence, reduce for subtle impacts.

Default: 50
magic_promptoptional
string

Enhances prompts. Use 'ON' for enriched results or 'OFF' for manual input.

Default: "AUTO"
Allowed values :
"AUTO""ON""OFF"
negative_promptoptional
string

Excludes elements from results. Specify unwanted features here.

Default: "No people, no buildings"
rendering_speedoptional
string

Balances speed and quality. Use 'QUALITY' for detail, 'TURBO' for speed.

Default: "DEFAULT"
Allowed values :
"TURBO""DEFAULT""QUALITY"
resolutionoptional
string

Defines output resolution. Use high resolution for detail, low for speed.

Default: "1024x1024"
Allowed values (69 total):
"512x1536""576x1408""576x1472""576x1536""640x1344""640x1408""640x1472""640x1536""704x1152""704x1216"+59 more
seedoptional
integer

Ensures consistent outputs. Use specific seeds for reproducible results.

Default: 6522Range: 100 - 999999
style_codesoptional
string[]

Apply style codes for themes. Use codes for specific styles or moods.

style_reference_imagesoptional
string[]

Add sample images for style influence. Use relevant samples that fit size limits.

style_typeoptional
string

Choose overarching style. 'REALISTIC' for lifelike, 'DESIGN' for abstract.

Default: "GENERAL"
Allowed values :
"AUTO""GENERAL""REALISTIC""DESIGN"

Response Type

Returns: Image

Asynchronous requests (v2)

Use Async for video, long-running (>~60s), or high-concurrency workloads; Sync is simplest for fast image & LLM calls. Async submits a request and you poll it to completion.

  1. 1
    POST /v2/ideogram-3-remix

    Submitreturns request_id, status_url, response_url

  2. 2
    GET /v2/requests/{id}/status

    Polluntil COMPLETED or FAILED

  3. 3
    GET /v2/requests/{id}

    Resultfinal response body

Status states

QUEUEDAccepted, waiting for a worker
PROCESSINGRunning on a worker
COMPLETEDDone — result body is ready
FAILEDErrored (incl. content/RAI blocks)
  • A FAILED request is served as HTTP 422 — the body still carries the error detail.
  • An unknown or expired request_id returns HTTP 404.
  • Results are retained for 1 hour, then expire.
  • Content / RAI blocks surface as FAILED, not a separate state.
  • Track completion by polling the status endpoint.

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