Ideogram
This page is auto-generated from model configurations. Last updated: 2026-10-09.
This reference lists all available Ideogram image generation models and their parameters. Use these parameter names when calling the Generation API.
- Ideogram 4.5
- Ideogram 4.5 Precise Edit
- Ideogram Character
- Ideogram V3 Balanced
- Ideogram V3 Generate Transparent
- Ideogram V3 Layerize Text
- Ideogram V3 Quality
- Ideogram V3 Turbo
- Ideogram V4
- Ideogram V4 Tiling
Ideogram 4.5
Section titled “Ideogram 4.5”Generate images, posters, and logos with accurate text rendering up to 2K, or edit an image guided by up to four reference images and an optional mask.
Model ID: model_ideogram-v4-5
Capabilities: txt2img, img2img
LLM Markdown: https://app.scenario.com/api/models/model_ideogram-v4-5/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe the image you want to generate, or the edit to apply, including any text that should appear in it. Refer to input images by position: image 1 is the source, image 2 the first reference, and so on. |
referenceImages |
file_array | No | - | - | - | - | Optional images to edit (up to 5, or 4 with a mask). The first is the source image to edit, the others are references. Leave empty to create from your prompt alone. |
mask |
file | No | - | - | - | - | Optional mask over the first reference image. White marks the region to edit, black the region to keep. Requires Aspect Ratio to stay on Auto. |
aspectRatio |
string | No | auto |
- | - | auto, source, 3:1, 8:3, 23:9, 22:9, 12:5, 2:1, 16:9, 8:5, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 5:8, 9:16, 1:2, 5:12, 9:22, 9:23, 3:8, 1:3 |
The shape of the image. Auto lets the model choose from the prompt and images; Source keeps the first reference image’s shape. |
resolution |
string | No | 2K |
- | - | 1K, 2K |
The output resolution when an explicit aspect ratio is set. 1K exists only for 1:1, 4:5, 3:4, 2:3, 5:8, 9:16, 1:2 and their landscape counterparts. |
quality |
string | No | high |
- | - | very_low, low, medium, high |
The quality-versus-speed tradeoff. Higher quality takes longer and costs more. Very Low requires a reference image. |
magicPrompt |
string | No | auto |
- | - | auto, on, off |
Whether the model enriches your prompt before generating. Applies to text-to-image only: edits are always turned into structured instructions. |
numOutputs |
number | No | 1 |
1 | 8 | - | How many images to generate (1-8). Each additional image adds to the cost. |
seed |
number | No | - | 0 | 2147483647 | - | A number that locks in the randomness of the generation. Leave blank for a new result each time. |
enableCopyrightDetection |
boolean | No | false |
- | - | - | Screens outputs for copyrighted content. Flagged images are withheld. Adds latency. |
Ideogram 4.5 Precise Edit
Section titled “Ideogram 4.5 Precise Edit”Edit an image in place while leaving everything else untouched, with an optional mask and up to four reference images.
Model ID: model_ideogram-v4-5-precise-edit
Capabilities: img2img
LLM Markdown: https://app.scenario.com/api/models/model_ideogram-v4-5-precise-edit/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe the edit to apply. Say what must stay unchanged for the strictest result. |
image |
file | Yes | - | - | - | - | The image to edit. The output keeps its size. |
mask |
file | No | - | - | - | - | Optional mask over the image. White marks the region to edit, black the region to keep. |
referenceImages |
file_array | No | - | - | - | - | Optional images that guide the edit (up to 4, or 3 with a mask), such as a pose skeleton or a product to insert. |
quality |
string | No | medium |
- | - | very_low, low, medium, high |
The quality-versus-speed tradeoff. High picks the best of several candidates: slower and costs more. |
numOutputs |
number | No | 1 |
1 | 8 | - | How many images to generate (1-8). Each additional image adds to the cost. |
seed |
number | No | - | 0 | 2147483647 | - | A number that locks in the randomness of the edit. Leave blank for a new result each time. |
enableCopyrightDetection |
boolean | No | false |
- | - | - | Screens outputs for copyrighted content. Flagged images are withheld. Adds latency. |
Ideogram Character
Section titled “Ideogram Character”Model ID: model_ideogram-character
Capabilities: img2img
LLM Markdown: https://app.scenario.com/api/models/model_ideogram-character/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Text prompt for image generation |
renderingSpeed |
string | No | Default |
- | - | Default, Turbo, Quality |
Turbo for faster and cheaper generation, quality for higher quality and more expensive generation, default for balanced. |
characterReferenceImage |
file | Yes | - | - | - | - | An image to use as a character reference. |
styleType |
string | No | Auto |
- | - | Auto, Fiction, Realistic |
The character style type. Auto, Fiction, or Realistic. |
aspectRatio |
string | No | 4:3 |
- | - | 1:3, 1:2, 2:3, 3:4, 4:5, 9:16, 10:16, 1:1, 3:2, 4:3, 5:4, 16:10, 16:9, 2:1, 3:1 |
Aspect ratio. Ignored if a resolution or inpainting image is given. |
resolution |
string | No | None |
- | - | None, 1536x512, 1472x576, 1408x528, 1408x704, 1280x720, 1280x768, 1024x768, 1024x1024, 768x1024, 832x1472, 704x1408, 512x1536 |
Resolution. Overrides aspect ratio. Ignored if an inpainting image is given. |
image |
file | No | - | - | - | - | An image file to use for inpainting. You must also use a mask. |
mask |
file | No | - | - | - | - | A black and white image. Black pixels are inpainted, white pixels are preserved. The mask will be resized to match the image size. |
seed |
number | No | - | - | 2147483647 | - | Use a seed for reproducible results. Leave blank to use a random seed. |
Ideogram V3 Balanced
Section titled “Ideogram V3 Balanced”Ideogram v3 balanced: Balance speed, quality and cost. Ideogram v3 creates images with stunning realism, creative designs, and consistent styles.
Model ID: model_ideogram-v3-balanced
Capabilities: txt2img, img2img
LLM Markdown: https://app.scenario.com/api/models/model_ideogram-v3-balanced/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe your image |
aspectRatio |
string | No | 4:3 |
- | - | 1:3, 1:2, 2:3, 3:4, 4:5, 9:16, 10:16, 1:1, 5:4, 4:3, 3:2, 16:10, 16:9, 2:1, 3:1 |
Aspect ratio. Ignored if a resolution or inpainting image is given. |
resolution |
string | No | None |
- | - | None, 512x1536, 576x1408, 640x1344, 704x1344, 768x1344, 832x1216, 896x1152, 960x1024, 1024x1024, 1088x960, 1152x896, 1216x832, 1280x768, 1344x704, 1408x640, 1472x576, 1536x512 |
Resolution. Overrides aspect ratio. Ignored if an inpainting image is given. |
magicPromptOption |
string | No | Auto |
- | - | Auto, On, Off |
Magic Prompt will interpret your prompt and optimize it to maximize variety and quality of the images generated. You can also use it to write prompts in different languages. |
image |
file | No | - | - | - | - | An image file to use for inpainting. You must also use a mask. |
mask |
file | No | - | - | - | - | A black and white image. Black pixels are inpainted, white pixels are preserved. The mask will be resized to match the image size. |
styleReferenceImages |
file_array | No | - | - | - | - | A list of images to use as style references. |
styleType |
string | No | None |
- | - | None, Auto, General, Realistic, Design |
The styles help define the specific aesthetic of the image you want to generate. |
stylePreset |
string | No | None |
- | - | None, 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, Children's 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 |
The style preset to use for the image generation. |
seed |
number | No | - | 0 | 2147483647 | - | Use a seed for reproducible results. Leave blank to use a random seed. |
Ideogram V3 Generate Transparent
Section titled “Ideogram V3 Generate Transparent”Generate images with transparent backgrounds using Ideogram V3.
Model ID: model_ideogram-v3-generate-transparent
Capabilities: txt2img
LLM Markdown: https://app.scenario.com/api/models/model_ideogram-v3-generate-transparent/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Text prompt describing the image to generate. |
negativePrompt |
string | No | - | - | - | - | Description of what should not appear in the generated image. |
aspectRatio |
string | No | 1:1 |
- | - | 1:3, 1:2, 9:16, 10:16, 2:3, 3:4, 4:5, 1:1, 5:4, 4:3, 3:2, 16:10, 16:9, 2:1, 3:1 |
Aspect ratio for the generated image. |
renderingSpeed |
string | No | BALANCED |
- | - | FLASH, TURBO, BALANCED, QUALITY |
Speed and quality tier for image generation. |
expandPrompt |
boolean | No | true |
- | - | - | Enable Magic Prompt expansion before generation. |
numOutputs |
number | No | 1 |
1 | 8 | - | Number of images to generate. |
seed |
number | No | - | 0 | 2147483647 | - | Seed for reproducible generation. |
Ideogram V3 Layerize Text
Section titled “Ideogram V3 Layerize Text”Remove text from flat graphics and return editable text layer metadata.
Model ID: model_ideogram-v3-layerize-text
Capabilities: img2img
LLM Markdown: https://app.scenario.com/api/models/model_ideogram-v3-layerize-text/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
image |
file | Yes | - | - | - | - | Flat graphic image to layerize. |
prompt |
string | No | - | - | - | - | Optional prompt to guide the layerization process. |
seed |
number | No | - | 0 | 2147483647 | - | Seed for reproducible layerization. |
fontNameH1 |
string | No | - | - | - | - | Optional font name for h1 text. |
fontNameH2 |
string | No | - | - | - | - | Optional font name for h2 text. |
fontNameBody |
string | No | - | - | - | - | Optional font name for body text. |
fontNameSmall |
string | No | - | - | - | - | Optional font name for small text. Cannot be used with font file. |
fontFileH1 |
string | No | - | - | - | - | Optional font file for h1 text. Cannot be used with font name. |
fontFileH2 |
string | No | - | - | - | - | Optional font file for h2 text. Cannot be used with font name. |
fontFileBody |
string | No | - | - | - | - | Optional font file for body text. Cannot be used with font name. |
fontFileSmall |
string | No | - | - | - | - | Optional font file for small text. Cannot be used with font name. |
Ideogram V3 Quality
Section titled “Ideogram V3 Quality”The highest quality Ideogram v3 model. v3 creates images with stunning realism, creative designs, and consistent styles.
Model ID: model_ideogram-v3-quality
Capabilities: txt2img, img2img
LLM Markdown: https://app.scenario.com/api/models/model_ideogram-v3-quality/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe your image |
aspectRatio |
string | No | 4:3 |
- | - | 1:3, 1:2, 2:3, 3:4, 4:5, 9:16, 10:16, 1:1, 5:4, 4:3, 3:2, 16:10, 16:9, 2:1, 3:1 |
Aspect ratio. Ignored if a resolution or inpainting image is given. |
resolution |
string | No | None |
- | - | None, 512x1536, 576x1408, 640x1344, 704x1344, 768x1344, 832x1216, 896x1152, 960x1024, 1024x1024, 1088x960, 1152x896, 1216x832, 1280x768, 1344x704, 1408x640, 1472x576, 1536x512 |
Resolution. Overrides aspect ratio. Ignored if an inpainting image is given. |
magicPromptOption |
string | No | Auto |
- | - | Auto, On, Off |
Magic Prompt will interpret your prompt and optimize it to maximize variety and quality of the images generated. You can also use it to write prompts in different languages. |
image |
file | No | - | - | - | - | An image file to use for inpainting. You must also use a mask. |
mask |
file | No | - | - | - | - | A black and white image. Black pixels are inpainted, white pixels are preserved. The mask will be resized to match the image size. |
styleReferenceImages |
file_array | No | - | - | - | - | A list of images to use as style references. |
styleType |
string | No | None |
- | - | None, Auto, General, Realistic, Design |
The styles help define the specific aesthetic of the image you want to generate. |
stylePreset |
string | No | None |
- | - | None, 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, Children's 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 |
The style preset to use for the image generation. |
seed |
number | No | - | 0 | 2147483647 | - | Use a seed for reproducible results. Leave blank to use a random seed. |
Ideogram V3 Turbo
Section titled “Ideogram V3 Turbo”Turbo is the fastest and cheapest Ideogram v3. v3 creates images with stunning realism, creative designs, and consistent styles
Model ID: model_ideogram-v3-turbo
Capabilities: txt2img, img2img
LLM Markdown: https://app.scenario.com/api/models/model_ideogram-v3-turbo/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe your image |
aspectRatio |
string | No | 4:3 |
- | - | 1:3, 1:2, 2:3, 3:4, 4:5, 9:16, 10:16, 1:1, 5:4, 4:3, 3:2, 16:10, 16:9, 2:1, 3:1 |
Aspect ratio. Ignored if a resolution or inpainting image is given. |
resolution |
string | No | None |
- | - | None, 512x1536, 576x1408, 640x1344, 704x1344, 768x1344, 832x1216, 896x1152, 960x1024, 1024x1024, 1088x960, 1152x896, 1216x832, 1280x768, 1344x704, 1408x640, 1472x576, 1536x512 |
Resolution. Overrides aspect ratio. Ignored if an inpainting image is given. |
magicPromptOption |
string | No | Auto |
- | - | Auto, On, Off |
Magic Prompt will interpret your prompt and optimize it to maximize variety and quality of the images generated. You can also use it to write prompts in different languages. |
image |
file | No | - | - | - | - | An image file to use for inpainting. You must also use a mask. |
mask |
file | No | - | - | - | - | A black and white image. Black pixels are inpainted, white pixels are preserved. The mask will be resized to match the image size. |
styleReferenceImages |
file_array | No | - | - | - | - | A list of images to use as style references. |
styleType |
string | No | None |
- | - | None, Auto, General, Realistic, Design |
The styles help define the specific aesthetic of the image you want to generate. |
stylePreset |
string | No | None |
- | - | None, 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, Children's 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 |
The style preset to use for the image generation. |
seed |
number | No | - | 0 | 2147483647 | - | Use a seed for reproducible results. Leave blank to use a random seed. |
Ideogram V4
Section titled “Ideogram V4”Generate images, posters, and logos with accurate text rendering and fine detail — ideal for designs where words need to appear clearly inside the image.
Model ID: model_ideogram-v4
Capabilities: txt2img
LLM Markdown: https://app.scenario.com/api/models/model_ideogram-v4/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe the image you want to generate, including subject, style, mood, and any text you want to appear in the image. Ideogram V4 handles in-image text better than most models — be explicit about wording and placement. |
imageSize |
string | No | square_hd |
- | - | portrait_16_9, portrait_4_3, square, square_hd, landscape_4_3, landscape_16_9 |
The dimensions and aspect ratio of the generated image. HD square gives the highest resolution; use portrait or landscape presets to match your intended format. |
renderingSpeed |
string | No | BALANCED |
- | - | TURBO, BALANCED, QUALITY |
The quality-versus-speed tradeoff. Turbo is fastest but less detailed; Quality takes longer and produces sharper results; Balanced is a good default for most use cases. |
enablePromptExpansion |
boolean | No | true |
- | - | - | When enabled, the model automatically enriches your prompt with additional detail before generating. Useful for short or simple prompts; disable if you want the output to follow your exact wording. |
acceleration |
string | No | none |
- | - | none, low, regular, high |
An additional speed boost on top of the rendering tier. Higher acceleration reduces generation time but may slightly affect output quality. Leave at None for best results. |
numOutputs |
number | No | 1 |
1 | 4 | - | How many images to generate from the same prompt. Useful for exploring variations. Each additional image adds to the cost. |
seed |
number | No | - | 0 | 2147483647 | - | A number that locks in the randomness of the generation. Copy the seed from a result you liked to reproduce it exactly, or leave blank for a new result each time. |
Ideogram V4 Tiling
Section titled “Ideogram V4 Tiling”Generate seamless, edge-matching textures and repeating patterns with Ideogram V4, optionally guided by an input image or mask.
Model ID: model_ideogram-v4-tiling
Capabilities: txt2img, img2img
LLM Markdown: https://app.scenario.com/api/models/model_ideogram-v4-tiling/markdown
| Parameter | Type | Required | Default | Min | Max | Allowed Values | Description |
|---|---|---|---|---|---|---|---|
prompt |
string | Yes | - | - | - | - | Describe the texture or repeating pattern you want. The result is built to repeat seamlessly in the direction you choose. |
image |
file | No | - | - | - | - | An optional starting image. When provided, it’s transformed into a seamless tile instead of generating one from scratch. |
strength |
number | No | 0.8 |
0 | 1 | - | How much the input image changes. Higher values transform it more; lower values keep it closer to the source. |
mask |
file | No | - | - | - | - | An optional black-and-white image marking which parts to redo. White areas are regenerated, black areas are kept. Requires an input image. |
tilingMode |
string | No | both |
- | - | both, horizontal, vertical |
Which directions the pattern repeats seamlessly. Both repeats in every direction; Horizontal repeats left-to-right; Vertical repeats top-to-bottom. |
imageSize |
string | No | square_hd |
- | - | portrait_16_9, portrait_4_3, square, square_hd, landscape_4_3, landscape_16_9 |
The size and shape of the generated tile. |
renderingSpeed |
string | No | BALANCED |
- | - | TURBO, BALANCED, QUALITY |
The tradeoff between speed and quality. Turbo is fastest, Quality is sharpest, and Balanced is a good default. |
expansionModel |
string | No | Medium |
- | - | None, Medium, Large |
Whether your prompt is automatically enriched with extra detail before generating. None uses your prompt exactly; Medium adds some detail quickly; Large uses Ideogram’s Magic Prompt for the richest results. |
acceleration |
string | No | none |
- | - | none, low, regular, high |
An extra speed boost on top of the rendering setting. Higher values generate faster but may slightly reduce quality. |
numOutputs |
number | No | 1 |
1 | 4 | - | How many tiles to create from the same prompt. |
seed |
number | No | - | 0 | 2147483647 | - | A number that makes results repeatable. Reusing the same seed and settings produces the same tile; leave it empty for a different result each time. |