ideogram-ai / ideogram-v3-balanced

Balance speed, quality and cost. Ideogram v3 creates images with stunning realism, creative designs, and consistent styles

Warm

Public
39.3K runs
$0.06 per output image
Commercial use
Paper
License

Iterate in playground

Run with an API

Playground API Examples README

Input

prompt

*string

Shift + Return to add a new line

The text "V3 Balanced" in the center middle. A color film-inspired portrait of a young man and a young woman looking at each other, a shallow depth of field that blurs the surrounding elements, drawing attention to their eyes. The fine grain and cast suggest a high ISO film stock, while the wide aperture lens creates a pleasing bokeh effect, enhancing the candid and natural documentary style.The text "V3 Balanced" in the center middle. A color film-inspired portrait of a young man and a young woman looking at each other, a shallow depth of field that blurs the surrounding elements, drawing attention to their eyes. The fine grain and cast suggest a high ISO film stock, while the wide aperture lens creates a pleasing bokeh effect, enhancing the candid and natural documentary style.

Text prompt for image generation

aspect_ratio

string

Aspect ratio. Ignored if a resolution or inpainting image is given.

Default: "1:1"

resolution

string

Resolution. Overrides aspect ratio. Ignored if an inpainting image is given.

Default: "None"

magic_prompt_option

string

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.

Default: "Auto"

image

file

An image file to use for inpainting. You must also use a mask.

mask

file

A black and white image. Black pixels are inpainted, white pixels are preserved. The mask will be resized to match the image size.

style_type

string

The styles help define the specific aesthetic of the image you want to generate.

Default: "None"

style_reference_images

file[]

Add multiple files

A list of images to use as style references.

seed

integer

(maximum: 2147483647)

Random seed. Set for reproducible generation

Run this model in Node.js with one line of code:

npx create-replicate --model=ideogram-ai/ideogram-v3-balanced

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run ideogram-ai/ideogram-v3-balanced using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  prompt: "The text \"V3 Balanced\" in the center middle. A color film-inspired portrait of a young man and a young woman looking at each other, a shallow depth of field that blurs the surrounding elements, drawing attention to their eyes. The fine grain and cast suggest a high ISO film stock, while the wide aperture lens creates a pleasing bokeh effect, enhancing the candid and natural documentary style.",
  resolution: "None",
  style_type: "None",
  aspect_ratio: "3:2",
  magic_prompt_option: "Auto"
};

const output = await replicate.run("ideogram-ai/ideogram-v3-balanced", { input });

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run ideogram-ai/ideogram-v3-balanced using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "ideogram-ai/ideogram-v3-balanced",
    input={
        "prompt": "The text \"V3 Balanced\" in the center middle. A color film-inspired portrait of a young man and a young woman looking at each other, a shallow depth of field that blurs the surrounding elements, drawing attention to their eyes. The fine grain and cast suggest a high ISO film stock, while the wide aperture lens creates a pleasing bokeh effect, enhancing the candid and natural documentary style.",
        "resolution": "None",
        "style_type": "None",
        "aspect_ratio": "3:2",
        "magic_prompt_option": "Auto"
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run ideogram-ai/ideogram-v3-balanced using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "input": {
      "prompt": "The text \\"V3 Balanced\\" in the center middle. A color film-inspired portrait of a young man and a young woman looking at each other, a shallow depth of field that blurs the surrounding elements, drawing attention to their eyes. The fine grain and cast suggest a high ISO film stock, while the wide aperture lens creates a pleasing bokeh effect, enhancing the candid and natural documentary style.",
      "resolution": "None",
      "style_type": "None",
      "aspect_ratio": "3:2",
      "magic_prompt_option": "Auto"
    }
  }' \
  https://api.replicate.com/v1/models/ideogram-ai/ideogram-v3-balanced/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

Generated in

8.3 seconds

Tweak it Report

Examples

View more examples

Pricing

Model pricing for ideogram-ai/ideogram-v3-balanced. Looking for volume pricing? Get in touch.

$0.06

per output image

or around 16 images for $1

Official models are always on, maintained, and have predictable pricing. Learn more.

Check out our docs for more information about how pricing works on Replicate.

Readme

Ideogram 3.0

Turbo: fastest and cheapest at $0.04/image
Balanced: a good balance between speed and quality at $0.07/image
Quality: slowest but highest quality at $0.10/image

Overview

Ideogram 3.0 is a text-to-image model available on ideogram.ai and iOS. The model features improved image-prompt alignment, photorealism, and text rendering capabilities.

Key Features

Style References

Upload up to 3 reference images to control generation aesthetics
Random style feature provides access to 4.3 billion style presets
Reuse styles via Style Codes

Text and Layout Generation

Precise text generation for graphic design applications
Support for complex and lengthy text compositions
Enhanced typesetting capabilities

Visual Quality

Sophisticated spatial compositions
Precise lighting and color control
Detailed environmental elements
Realistic rendering

Use Cases

Graphic design
Advertising
Marketing
Small business branding
Logo creation
Promotional materials
Product photography