Ideogram AI Post Generate Image V 3
From 36 credits/call
ae_ideogramai_post_generate_image_v_3
Generate one or more images from a detailed text prompt with Ideogram 3.0. Choose an aspect ratio or resolution, and optionally add styles, reference images, color palettes, negative prompts, rendering speed, or a seed for reproducible results. Download images you want to keep because the links expire.
From 36 credits/call
Pricing
From 36 credits/call
| Rendering mode | Charge |
|---|---|
| Flash / Turbo | 36 credits/image |
| Standard / Not specified | 72 credits/image |
| Quality | 108 credits/image |
An omitted image count is charged as one image. Starting price applies to Rendering mode: Flash.
Parameters
Optional parameters use the platform defaults when omitted.
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
seed | integer | No | Random seed. Set for reproducible generation. | — |
prompt | string | Yes | 必填。用于生成图像的文本提示,必须是非空字符串。必须直接写清楚要生成的主体、风格、场景和关键视觉细节;禁止省略、传空字符串、数组、对象或占位符。示例:A realistic product photo of a red running shoe on a white background. | — |
num_images | integer | No | Number of images to generate. | 1 |
resolution | enum (512x1536 | 576x1408 | 576x1472 | 576x1536 | 640x1344 | 640x1408 | 640x1472 | 640x1536 | 704x1152 | 704x1216 | 704x1280 | 704x1344 | 704x1408 | 704x1472 | 736x1312 | 768x1088 | 768x1216 | 768x1280 | 768x1344 | 800x1280 | 832x960 | 832x1024 | 832x1088 | 832x1152 | 832x1216 | 832x1248 | 864x1152 | 896x960 | 896x1024 | 896x1088 | 896x1120 | 896x1152 | 960x832 | 960x896 | 960x1024 | 960x1088 | 1024x832 | 1024x896 | 1024x960 | 1024x1024 | 1088x768 | 1088x832 | 1088x896 | 1088x960 | 1120x896 | 1152x704 | 1152x832 | 1152x864 | 1152x896 | 1216x704 | 1216x768 | 1216x832 | 1248x832 | 1280x704 | 1280x768 | 1280x800 | 1312x736 | 1344x640 | 1344x704 | 1344x768 | 1408x576 | 1408x640 | 1408x704 | 1472x576 | 1472x640 | 1472x704 | 1536x512 | 1536x576 | 1536x640) | No | The resolutions supported for Ideogram 3.0. | — |
style_type | enum (AUTO | GENERAL | REALISTIC | DESIGN) | No | The style type to generate with. | GENERAL |
style_codes | array | No | A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style_type. | — |
aspect_ratio | enum (1x3 | 3x1 | 1x2 | 2x1 | 9x16 | 16x9 | 10x16 | 16x10 | 2x3 | 3x2 | 3x4 | 4x3 | 4x5 | 5x4 | 1x1) | No | The aspect ratio to use for image generation, which determines the image's resolution. Cannot be used in conjunction with resolution. Defaults to 1x1. Use the exact enum value with `x` as the separator, for example `3x4`, `4x3`, `16x9`, `9x16`, `1x3`, or `3x1`. Do not use colon forms like `3:4` or `16:9`, and do not use named variants like `landscape_4_3`. | — |
magic_prompt | enum (AUTO | ON | OFF) | No | Determine if MagicPrompt should be used in generating the request or not. | — |
style_preset | enum (80S_ILLUSTRATION | 90S_NOSTALGIA | ABSTRACT_ORGANIC | ANALOG_NOSTALGIA | ART_BRUT | ART_DECO | ART_POSTER | AURA | AVANT_GARDE | BAUHAUS | BLUEPRINT | BLURRY_MOTION | BRIGHT_ART | C4D_CARTOON | CHILDRENS_BOOK | COLLAGE | COLORING_BOOK_I | COLORING_BOOK_II | CUBISM | DARK_AURA | DOODLE | DOUBLE_EXPOSURE | DRAMATIC_CINEMA | EDITORIAL | EMOTIONAL_MINIMAL | ETHEREAL_PARTY | EXPIRED_FILM | FLAT_ART | FLAT_VECTOR | FOREST_REVERIE | GEO_MINIMALIST | GLASS_PRISM | GOLDEN_HOUR | GRAFFITI_I | GRAFFITI_II | HALFTONE_PRINT | HIGH_CONTRAST | HIPPIE_ERA | ICONIC | JAPANDI_FUSION | JAZZY | LONG_EXPOSURE | MAGAZINE_EDITORIAL | MINIMAL_ILLUSTRATION | MIXED_MEDIA | MONOCHROME | NIGHTLIFE | OIL_PAINTING | OLD_CARTOONS | PAINT_GESTURE | POP_ART | RETRO_ETCHING | RIVIERA_POP | SPOTLIGHT_80S | STYLIZED_RED | SURREAL_COLLAGE | TRAVEL_POSTER | VINTAGE_GEO | VINTAGE_POSTER | WATERCOLOR | WEIRD | WOODBLOCK_PRINT) | No | A predefined style preset that applies a specific artistic style to the generated image. | — |
color_palette | object | No | A color palette for generation, must EITHER be specified via one of the presets (name) or explicitly via hexadecimal representations of the color with optional weights (members). Not supported by V_1, V_1_TURBO, V_2A and V_2A_TURBO models. | — |
color_palette.name | enum (EMBER | FRESH | JUNGLE | MAGIC | MELON | MOSAIC | PASTEL | ULTRAMARINE) | Conditional | A color palette preset value. | — |
negative_prompt | string | No | Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt. | — |
rendering_speed | enum (FLASH | TURBO | DEFAULT | QUALITY) | No | The rendering speed to use. | DEFAULT |
style_reference_images | array | No | A set of images to use as style references (maximum total size 10MB across all style references). The images should be in JPEG, PNG or WebP format. | — |
character_reference_images | array | No | Generations with character reference are subject to the character reference pricing. A set of images to use as character references (maximum total size 10MB across all character references), currently only supports 1 character reference image. The images should be in JPEG, PNG or WebP format. | — |
character_reference_images_mask | array | No | Optional masks for character reference images. When provided, must match the number of character_reference_images. Each mask should be a grayscale image of the same dimensions as the corresponding character reference image. The images should be in JPEG, PNG or WebP format. | — |
Invocation example
Copy the request and explore its response example.
POST
/agent-api/v1/tool/executeX-Api-KeyRequest coderequest.sh
curl --request POST \
--url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_ideogramai_post_generate_image_v_3' \
--header "X-Api-Key: $AGENTEARTH_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
"params": {
"aspect_ratio": "4x3",
"color_palette": {
"members": [
{
"color_hex": "#4A66AC",
"color_weight": 1
},
{
"color_hex": "#629DD1",
"color_weight": 0.8
},
{
"color_hex": "#297FD5",
"color_weight": 0.6
},
{
"color_hex": "#242852",
"color_weight": 0.3
}
]
},
"magic_prompt": "OFF",
"negative_prompt": "text, words, letters, watermark, logo, photorealistic, 3d render, clutter",
"prompt": "Flat vector illustration for an academic presentation slide. A human brain side profile merged with fMRI brain imaging and neural network connectivity nodes, combined with traditional acupuncture needles, symbolizing the integration of traditional Chinese medicine and multimodal neuroimaging technology. Clean minimal modern flat style, blue and cyan color palette, soft light background. No text, no words, no letters, no watermark, no logo.",
"rendering_speed": "DEFAULT",
"style_preset": "FLAT_VECTOR",
"style_type": "GENERAL"
}
}'Response exampleresponse.json
{
"detail": "Parsed body must be a mapping",
"status": 400,
"title": "Bad Request",
"type": "https://developer.ideogram.ai/v2/llms.txt"
}Guides using this tool
See how this tool fits into real workflows
Anime & Illustration Generation with AI AgentsLet an AI agent generate anime-style characters and scenes from one plain-English prompt — compare multiple models, render text on posters, keep a character consistent, and batch out a full illustration set without leaving your editor.Text-to-Image Model Comparison on One PlatformRun the same prompt across multiple text-to-image models on one platform and have an AI agent compare them on realism, illustration and in-image text — pick the right model without signing up and paying for each one.





