Ideogram

Ideogram-Modelle werden über eine einheitliche, asynchrone Job-API aufgerufen. Starte einen Task mit POST /api/generate und frage dann GET /api/generate/{taskId} ab, bis er fertig ist. Diese Familie stellt 6 Endpunkte bereit.

Überblick

Jeder Endpunkt teilt sich dieselbe Hülle — nur model und die input-Felder ändern sich. Führe einen beliebigen im Playground des Modell-Markts aus.

Authentifizierung

Erstelle einen API-Schlüssel unter /api-keys und sende ihn als Bearer-Token. Anfragen aus dem Browser bei angemeldeter Sitzung funktionieren auch über das Session-Cookie.

Authorization: Bearer <YOUR_API_KEY>

Task erstellen

POST

POST https://api.lithovas.com/api/generate

Body: { "model": "<slug>", "input": { … } }

Antwort: { "taskId": "<id>", "state": "waiting" }

Ergebnis abfragen

GET

GET https://api.lithovas.com/api/generate/<taskId>

Antwort: { "taskId", "state": "waiting" | "success" | "fail", "resultUrls": [ … ], "creditsConsumed", "failMsg", "balance" }

Asynchron

Ein 200 von „Task erstellen“ bedeutet nur, dass der Task angenommen wurde — nicht, dass er fertig ist. Frage diesen Endpunkt ab, bis state zu success oder fail wird. Fehlgeschlagene Tasks werden nicht berechnet.

Endpunkte

Modell	Task	model slug
Ideogram	Image Editing	ideogram/character-edit
Ideogram	Image Editing	ideogram/character-remix
Ideogram	Image Editing	ideogram/character
Ideogram V3	Text to Image	ideogram/v3-text-to-image
Ideogram V3 Edit	Image Editing	ideogram/v3-edit
Ideogram V3 Remix	Image Editing	ideogram/v3-remix

Ideogram · Image Editing

POSTImage Editingideogram/character-edit

input-Felder

promptstringerforderlich

Text prompt to fill the masked image area (max 5000 chars)

image_urlstringerforderlich

Image URL to edit; must match mask dimensions (JPEG/PNG/WebP, max 10MB)

mask_urlstringerforderlich

Mask URL indicating region to inpaint; must match image dimensions

reference_image_urlsarray<string>erforderlich

Character reference images (1 supported, max 10MB total)

rendering_speedenum<string>optional

Speed/quality tradeoff for generation

styleenum<string>optional

Visual style for output image generation

expand_promptbooleanoptional

Enable MagicPrompt enhancement

num_imagesenum<string>optional

Number of images to generate

seedintegeroptional

Random seed for reproducible generation

Beispiel

cURL

curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "ideogram/character-edit",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "image_url": "https://example.com/input.jpg",
    "mask_url": "example",
    "reference_image_urls": [
      "https://example.com/input.jpg"
    ],
    "rendering_speed": "BALANCED",
    "style": "AUTO",
    "expand_prompt": true,
    "num_images": "1",
    "seed": 42
  }
}'

Ideogram · Image Editing

POSTImage Editingideogram/character-remix

input-Felder

promptstringerforderlich

Text description to remix the image with (max 5000 chars)

image_urlstringerforderlich

Image URL to remix (JPEG/PNG/WebP, max 10MB)

reference_image_urlsarray<string>erforderlich

Character reference images (1 supported, max 10MB)

rendering_speedenum<string>optional

Generation speed vs quality tradeoff

styleenum<string>optional

Style type for generation

expand_promptbooleanoptional

Enable MagicPrompt enhancement

image_sizeenum<string>optional

Output image dimensions

num_imagesenum<string>optional

Number of images to generate

seedintegeroptional

Random number generator seed

strengthnumberoptional

Input image influence strength (0.1-1.0, step 0.1)

negative_promptstringoptional

Content to exclude from generation (max 500 chars)

image_urlsarray<string>optional

Style reference images (max 10MB total)

reference_mask_urlsstringoptional

Masks for character references (1 supported, max 10MB)

Beispiel

cURL

curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "ideogram/character-remix",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "image_url": "https://example.com/input.jpg",
    "reference_image_urls": [
      "https://example.com/input.jpg"
    ],
    "rendering_speed": "BALANCED",
    "style": "AUTO",
    "expand_prompt": true,
    "image_size": "square_hd",
    "num_images": "1",
    "seed": 42,
    "strength": 0.8,
    "negative_prompt": "",
    "image_urls": [
      "https://example.com/input.jpg"
    ],
    "reference_mask_urls": ""
  }
}'

Ideogram · Image Editing

POSTImage Editingideogram/character

input-Felder

promptstringerforderlich

The prompt to fill the masked part of the image (max 5000 chars)

reference_image_urlsarray<string>erforderlich

Character reference images (1 supported, max 10MB total)

rendering_speedenum<string>optional

Speed setting for generation

styleenum<string>optional

Style type for generation

expand_promptbooleanoptional

Enable/disable MagicPrompt expansion

num_imagesenum<string>optional

Number of images to generate

image_sizeenum<string>optional

Output image resolution

seedintegeroptional

Random number generator seed for reproducibility

negative_promptstringoptional

Exclude specified elements from generation (max 5000 chars)

Beispiel

cURL

curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "ideogram/character",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "reference_image_urls": [
      "https://example.com/input.jpg"
    ],
    "rendering_speed": "BALANCED",
    "style": "AUTO",
    "expand_prompt": true,
    "num_images": "1",
    "image_size": "square_hd",
    "seed": 42,
    "negative_prompt": ""
  }
}'

Ideogram V3 · Text to Image

POSTText to Imageideogram/v3-text-to-image

input-Felder

promptstringerforderlich

Description of the image to generate (max 5000 chars)

rendering_speedenum<string>optional

Rendering speed vs quality tradeoff

styleenum<string>optional

Visual style type for generation output

expand_promptbooleanoptional

Whether to use MagicPrompt to enhance the request

image_sizeenum<string>optional

Resolution of the generated image

seedintegeroptional

Seed value for the random number generator

negative_promptstringoptional

Description of what to exclude (max 5000 chars)

Beispiel

cURL

curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "ideogram/v3-text-to-image",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "rendering_speed": "TURBO",
    "style": "AUTO",
    "expand_prompt": false,
    "image_size": "square",
    "seed": 42,
    "negative_prompt": "example"
  }
}'

Ideogram V3 Edit · Image Editing

POSTImage Editingideogram/v3-edit

input-Felder

promptstringerforderlich

Text describing what to fill in masked area (max 5000 chars)

image_urlstringerforderlich

URL of image to edit; must match mask dimensions

mask_urlstringerforderlich

URL of mask indicating areas to inpaint; must match image dimensions

rendering_speedenum<string>optional

Speed/quality tradeoff for generation

expand_promptbooleanoptional

Whether to apply MagicPrompt enhancement

seedintegeroptional

Random number generator seed for reproducible results

Beispiel

cURL

curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "ideogram/v3-edit",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "image_url": "https://example.com/input.jpg",
    "mask_url": "example",
    "rendering_speed": "BALANCED",
    "expand_prompt": true,
    "seed": 42
  }
}'

Ideogram V3 Remix · Image Editing

POSTImage Editingideogram/v3-remix

input-Felder

promptstringerforderlich

Text prompt to remix the image with (max 5000 chars)

image_urlstringerforderlich

URL of image to remix (JPEG/PNG/WebP, max 10MB)

rendering_speedenum<string>optional

Speed/quality tradeoff for generation

styleenum<string>optional

Visual style for output

expand_promptbooleanoptional

Enable MagicPrompt enhancement

image_sizeenum<string>optional

Output image resolution/aspect ratio

num_imagesenum<string>optional

Number of images to generate

seedintegeroptional

Random number generator seed for reproducibility

strengthnumberoptional

Influence of input image (0.01-1.0, step 0.01)

negative_promptstringoptional

Content to exclude from generation (max 5000 chars)

Beispiel

cURL

curl -X POST https://api.lithovas.com/api/generate \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "ideogram/v3-remix",
  "input": {
    "prompt": "A cinematic red panda surfing through neon rain at dusk.",
    "image_url": "https://example.com/input.jpg",
    "rendering_speed": "TURBO",
    "style": "AUTO",
    "expand_prompt": false,
    "image_size": "square",
    "num_images": "1",
    "seed": 42,
    "strength": 1,
    "negative_prompt": "example"
  }
}'