Ideogram 3.0
Ideogram 3.0 is a text to image model for high fidelity design work. It improves text rendering, complex layout handling, and photorealism. It also adds stronger style controls and supports editing tasks like inpainting and background replacement for production workflows.
API Options
Platform-level options for task execution and delivery.
-
taskType
string required value: imageInference -
Identifier for the type of task being performed
-
taskUUID
string required UUID v4 -
UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.
-
outputType
string default: URL -
Image output type.
Allowed values 3 values
-
outputFormat
string default: JPG -
Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.
- `JPG`: Best for photorealistic images with smaller file sizes (no transparency).
- `PNG`: Lossless compression, supports high quality and transparency (alpha channel).
- `WEBP`: Modern format providing superior compression and transparency support.
**Transparency**: If you are using features like background removal or LayerDiffuse that require transparency, you must select a format that supports an alpha channel (e.g., `PNG`, `WEBP`, `TIFF`). `JPG` does not support transparency.Allowed values 3 values
-
outputQuality
integer min: 20 max: 99 default: 95 -
Compression quality of the output. Higher values preserve quality but increase file size.
-
webhookURL
string URI -
Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.
Learn more 1 resource
- Webhooks PLATFORM
- Webhooks
-
deliveryMethod
string default: sync -
Determines how the API delivers task results.
Allowed values 2 values
- Returns complete results directly in the API response.
- Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.
Learn more 1 resource
- Task Polling PLATFORM
-
uploadEndpoint
string URI -
Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.
Common use cases:
- Cloud storage: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- CDN integration: Upload to content delivery networks for immediate distribution.
// S3 presigned URL for secure upload https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600 // Google Cloud Storage presigned URL https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789 // Custom storage endpoint https://storage.example.com/uploads/generated-image.jpgThe content data will be sent as the request body to the specified URL when generation is complete.
-
safety
object -
Content safety checking configuration for image generation.
Properties 2 properties
-
safety»checkContentcheckContent
boolean default: false -
Enable or disable content safety checking. When enabled, defaults to
fastmode.
-
safety»modemode
string default: none -
Safety checking mode for image generation.
Allowed values 2 values
- Disables checking.
- Performs a single check.
-
-
ttl
integer min: 60 -
Time-to-live (TTL) in seconds for generated content. Only applies when
outputTypeisURL.
-
includeCost
boolean default: false -
Include task cost in the response.
-
numberResults
integer min: 1 max: 20 default: 1 -
Number of results to generate. Each result uses a different seed, producing variations of the same parameters.
Generation Parameters
Core parameters for controlling the generated content.
-
model
string required value: ideogram:4@1 -
Identifier of the model to use for generation.
Learn more 3 resources
-
positivePrompt
string required min: 1 max: 2000 -
Text prompt describing elements to include in the generated output.
Learn more 2 resources
-
negativePrompt
string min: 1 max: 2000 -
Prompt to guide what to exclude from generation. Ignored when guidance is disabled (CFGScale ≤ 1).
Learn more 1 resource
-
Width of the generated media in pixels.
Learn more 2 resources
-
Height of the generated media in pixels.
Learn more 2 resources
Provider Settings
Parameters specific to this model provider. These must be nested inside the providerSettings.ideogram object.
providerSettings.ideogram object.-
providerSettings»ideogram»characterReferenceImagescharacterReferenceImages
array of strings items: 1 -
Character reference images to preserve consistent facial and body traits across generations.
-
providerSettings»ideogram»characterReferenceImagesMaskcharacterReferenceImagesMask
array of strings items: 1 -
Mask images for character reference images. Must match the number of character reference images.
-
providerSettings»ideogram»magicPromptmagicPrompt
string default: AUTO -
Automatic prompt enhancement.
Allowed values 3 values
- Content-based enhancement.
- Always enhance.
- No enhancement.
-
providerSettings»ideogram»renderingSpeedrenderingSpeed
string default: DEFAULT -
Generation speed/quality tradeoff.
Allowed values 3 values
- Fastest generation.
- Balanced speed and quality.
- Best quality.
-
providerSettings»ideogram»stylePresetstylePreset
string -
Artistic style preset.
Allowed values 62 values
-
providerSettings»ideogram»styleReferenceImagesstyleReferenceImages
array of strings min items: 1max items: 4 -
Reference images for visual style transfer. The model extracts and applies the artistic style from these images.
-
providerSettings»ideogram»styleTypestyleType
string default: AUTO -
Visual style and rendering approach.
Allowed values 7 values
- Automatically selects the most appropriate style.
- Versatile style suitable for most content types.
- Photorealistic rendering with natural lighting and textures.
- Optimized for graphic design, logos, and typography.
- Three-dimensional rendering with depth and modeling effects.
- Anime/manga visual style.
- Stylized rendering for fictional and fantasy content.
Artisan Bakery Window Signage
{
"taskType": "imageInference",
"taskUUID": "ae5778d2-1043-4c67-b9d9-aa794e9327d3",
"model": "ideogram:4@1",
"positivePrompt": "A charming street-facing bakery facade at early morning, focused on beautifully designed window typography and signage. The main glass window features crisp readable text: \"MAPLE & FLOUR\" in elegant hand-painted serif lettering, with smaller text beneath reading \"Breads Pastries Coffee\" and a circular corner badge that says \"EST. 1986\". Include gold leaf details, subtle flourishes, balanced spacing, premium sign-painter craftsmanship, realistic reflections on glass, warm baked goods visible behind the window, flower boxes, weathered painted trim, highly detailed storefront branding, excellent text accuracy, coherent letterforms, professional graphic design composition, photorealistic scene.",
"negativePrompt": "blurry text, misspelled words, distorted letters, duplicated signage, extra windows, warped typography, low detail, messy layout, clutter, watermark, logo artifacts, frame crop, tilted horizon",
"width": 1344,
"height": 768
}{
"taskType": "imageInference",
"taskUUID": "ae5778d2-1043-4c67-b9d9-aa794e9327d3",
"imageUUID": "3dc1f956-33ea-4096-9a92-7e30d221308d",
"imageURL": "https://im.runware.ai/image/os/a16d07/ws/2/ii/3dc1f956-33ea-4096-9a92-7e30d221308d.jpg",
"seed": 40905735,
"cost": 0.06
}Handwritten Florist Awning Display
{
"taskType": "imageInference",
"taskUUID": "dc3dda2d-a398-421f-affc-f7e2e3673552",
"model": "ideogram:4@1",
"positivePrompt": "A charming neighborhood flower shop storefront at early morning, viewed straight-on, with a striped canvas awning and an elegant hand-painted sign that reads \"Marigold Stem House\" in large readable cream lettering. Beneath it, a smaller line reads \"fresh bouquets • dried stems • weekend workshops\". Outside the shop are galvanized buckets filled with dahlias, ranunculus, tulips, eucalyptus, and wild grasses, each with neat handwritten tags showing readable names and prices such as \"DAHLIAS 12\", \"TULIPS 9\", and \"EUCALYPTUS 7\". A sidewalk sandwich board says \"SPRING ARRANGEMENTS TODAY\" in bold chalk lettering. Warm natural sunlight, realistic textures, inviting small-business branding, excellent typography, balanced composition, subtle reflections in the window glass, tasteful color palette of sage, cream, blush, terracotta, and soft yellow, highly detailed photoreal scene designed like premium commercial signage photography.",
"negativePrompt": "blurry text, misspelled words, distorted letters, warped signage, duplicate buckets, crowded street, cars, people blocking the storefront, harsh shadows, oversaturated colors, low detail, fisheye distortion, messy composition",
"width": 1344,
"height": 768,
"providerSettings": {
"ideogram": {
"magicPrompt": "ON",
"stylePreset": "JAPANDI_FUSION"
}
}
}{
"taskType": "imageInference",
"taskUUID": "dc3dda2d-a398-421f-affc-f7e2e3673552",
"imageUUID": "75217815-7da1-4576-bfb8-5ae1f2067a48",
"imageURL": "https://im.runware.ai/image/os/a09d21/ws/2/ii/75217815-7da1-4576-bfb8-5ae1f2067a48.jpg",
"seed": 320317695,
"cost": 0.06
}Hand-Painted Arcade Wayfinding Mural
{
"taskType": "imageInference",
"taskUUID": "96e927a2-bcbf-4d3b-b78d-c3f58ba9932c",
"model": "ideogram:4@1",
"positivePrompt": "An imaginative indoor arcade corridor transformed into a hand-painted wayfinding mural wall, wide cinematic view, richly textured plaster and tiled floor, hanging paper lanterns and playful directional graphics. Large beautifully rendered painted text integrated into the environment reads: \"SKYLINE ARCADE\", \"PINBALL HALL\", \"TICKET BOOTH\", \"LEVEL 2 GAMES\", and \"THIS WAY\" with arrows. The lettering is crisp, readable, varied in scale, and perfectly aligned with the wall composition. Charming eclectic scene with families and players in the distance, claw machines, pinball glow, patterned ceiling beams, color-blocked shapes, whimsical mascots, polished yet handcrafted design language, vivid but tasteful palette of cobalt, coral, mustard, and cream, high detail, excellent typography, realistic materials, immersive depth, professional graphic design photography.",
"negativePrompt": "blurry text, misspelled words, distorted letters, duplicated signage, cropped text, low detail, empty scene, watermark, logo, frame, gloomy lighting",
"width": 1344,
"height": 768
}{
"taskType": "imageInference",
"taskUUID": "96e927a2-bcbf-4d3b-b78d-c3f58ba9932c",
"imageUUID": "7f18834b-9b52-4182-9cca-848584803b1f",
"imageURL": "https://im.runware.ai/image/os/a16d07/ws/2/ii/7f18834b-9b52-4182-9cca-848584803b1f.jpg",
"seed": 1128435637,
"cost": 0.06
}Subway Jazz Club Marquee
{
"taskType": "imageInference",
"taskUUID": "3a300027-be07-4fd4-a95b-4f1b8dd572ef",
"model": "ideogram:4@1",
"positivePrompt": "A richly detailed underground subway jazz club entrance transformed into an elegant live-music venue, warm amber bulbs, tiled walls, polished brass handrails, velvet rope, hand-painted sandwich board, framed gig flyers, and a large illuminated marquee with crisp readable text: 'THE COPPER NOTE' on the main sign, smaller text below: 'LIVE TONIGHT' and 'TRIO AT 8:30'. A diverse crowd in stylish evening attire gathers on the platform, saxophone case near the stairs, subtle haze, glossy floor reflections, dramatic perspective down the tunnel, photorealistic textures, sophisticated atmosphere, impeccable typography, balanced composition, high detail.",
"negativePrompt": "blurry text, misspelled words, duplicated people, extra limbs, warped hands, unreadable signage, low detail, oversaturated colors, empty scene, cartoonish rendering",
"width": 1280,
"height": 704
}{
"taskType": "imageInference",
"taskUUID": "3a300027-be07-4fd4-a95b-4f1b8dd572ef",
"imageUUID": "66b0a73f-0d0c-4d47-ad77-d82f09d2dac1",
"imageURL": "https://im.runware.ai/image/os/a24d12/ws/2/ii/66b0a73f-0d0c-4d47-ad77-d82f09d2dac1.jpg",
"seed": 1791711315,
"cost": 0.06
}