Ideogram V3 API

Endpoint: POST https://fal.run/fal-ai/ideogram/v3 Endpoint ID: fal-ai/ideogram/v3

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/ideogram/v3",
    arguments={
        "prompt": "The Bone Forest stretched across the horizon, its trees fashioned from the ossified remains of ancient leviathans that once swam through the sky. Shamans with antlers growing from their shoulders and eyes that revealed the true nature of any being they beheld conducted rituals to commune with the spirits that still inhabited the calcified grove. In sky writes \"Ideogram V3 in fal.ai\""
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/ideogram/v3", {
  input: {
      prompt: "The Bone Forest stretched across the horizon, its trees fashioned from the ossified remains of ancient leviathans that once swam through the sky. Shamans with antlers growing from their shoulders and eyes that revealed the true nature of any being they beheld conducted rituals to commune with the spirits that still inhabited the calcified grove. In sky writes \"Ideogram V3 in fal.ai\""
    },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

curl --request POST \
  --url https://fal.run/fal-ai/ideogram/v3 \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "The Bone Forest stretched across the horizon, its trees fashioned from the ossified remains of ancient leviathans that once swam through the sky. Shamans with antlers growing from their shoulders and eyes that revealed the true nature of any being they beheld conducted rituals to commune with the spirits that still inhabited the calcified grove. In sky writes \"Ideogram V3 in fal.ai\""
}'

Input Schema

list<string>

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

RenderingSpeedEnum

default:"BALANCED"

The rendering speed to use. Default value: "BALANCED"Possible values: TURBO, BALANCED, QUALITY

ColorPalette

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)

list<string>

A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style

Enum

The style type to generate with. Cannot be used with style_codes.Possible values: AUTO, GENERAL, REALISTIC, DESIGN

boolean

default:"true"

Determine if MagicPrompt should be used in generating the request or not. Default value: true

integer

default:"1"

Number of images to generate. Default value: 1Range: 1 to 8

integer

Seed for the random number generator

boolean

default:"false"

If True, the media will be returned as a data URI and the output data won’t be available in the request history.

Enum

Style preset for generation. The chosen style preset will guide the generation.Possible values: 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

string

required

ImageSize | Enum

default:"square_hd"

The resolution of the generated image Default value: square_hdPossible values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

string

default:""

Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt. Default value: ""

Output Schema

list<File>

required

integer

required

Seed used for the random number generator

Input Example

{
  "rendering_speed": "BALANCED",
  "expand_prompt": true,
  "num_images": 1,
  "sync_mode": false,
  "prompt": "The Bone Forest stretched across the horizon, its trees fashioned from the ossified remains of ancient leviathans that once swam through the sky. Shamans with antlers growing from their shoulders and eyes that revealed the true nature of any being they beheld conducted rituals to commune with the spirits that still inhabited the calcified grove. In sky writes \"Ideogram V3 in fal.ai\"",
  "image_size": "square_hd",
  "negative_prompt": ""
}

Output Example

{
  "images": [
    {
      "url": "https://v3.fal.media/files/penguin/lHdRabS80guysb8Zw1kul_image.png"
    }
  ],
  "seed": 123456
}

Endpoint: POST https://fal.run/fal-ai/ideogram/v3/reframe Endpoint ID: fal-ai/ideogram/v3/reframe

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/ideogram/v3/reframe",
    arguments={
        "image_url": "https://v3.fal.media/files/lion/0qJs_qW8nz0wYsXhFa6Tk.png",
        "image_size": "square_hd"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/ideogram/v3/reframe", {
  input: {
      image_url: "https://v3.fal.media/files/lion/0qJs_qW8nz0wYsXhFa6Tk.png",
      image_size: "square_hd"
    },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

curl --request POST \
  --url https://fal.run/fal-ai/ideogram/v3/reframe \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "image_url": "https://v3.fal.media/files/lion/0qJs_qW8nz0wYsXhFa6Tk.png",
  "image_size": "square_hd"
}'

Input Schema

list<string>

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

RenderingSpeedEnum

default:"BALANCED"

The rendering speed to use. Default value: "BALANCED"Possible values: TURBO, BALANCED, QUALITY

ColorPalette

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)

list<string>

A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style

Enum

The style type to generate with. Cannot be used with style_codes.Possible values: AUTO, GENERAL, REALISTIC, DESIGN

integer

default:"1"

Number of images to generate. Default value: 1Range: 1 to 8

integer

Seed for the random number generator

boolean

default:"false"

If True, the media will be returned as a data URI and the output data won’t be available in the request history.

Enum

Style preset for generation. The chosen style preset will guide the generation.Possible values: 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

string

required

The image URL to reframe

ImageSize | Enum

required

The resolution for the reframed output imagePossible values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

Output Schema

list<File>

required

integer

required

Seed used for the random number generator

Input Example

{
  "rendering_speed": "BALANCED",
  "num_images": 1,
  "sync_mode": false,
  "image_url": "https://v3.fal.media/files/lion/0qJs_qW8nz0wYsXhFa6Tk.png",
  "image_size": "square_hd"
}

Output Example

{
  "images": [
    {
      "url": "https://v3.fal.media/files/zebra/LVW4AhVs3sCxsVKdg3EfT_image.png"
    }
  ],
  "seed": 123456
}

Endpoint: POST https://fal.run/fal-ai/ideogram/v3/generate-transparent Endpoint ID: fal-ai/ideogram/v3/generate-transparent

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/ideogram/v3/generate-transparent",
    arguments={
        "prompt": "A logo for Ideogram Coffee."
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/ideogram/v3/generate-transparent", {
  input: {
      prompt: "A logo for Ideogram Coffee."
    },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

curl --request POST \
  --url https://fal.run/fal-ai/ideogram/v3/generate-transparent \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "A logo for Ideogram Coffee."
}'

Examples

A low-poly 3D fox sitting upright, in warm orange and white geometric facets

Generated image: A low-poly 3D fox sitting upright, in warm orange and white geometric facets

Input Schema

string

required

AspectRatioEnum

default:"1:1"

The aspect ratio of the generated image. Default value: "1:1"Possible values: 1:3, 3:1, 1:2, 2:1, 9:16, 16:9, 10:16, 16:10, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 1:1

RenderingSpeedEnum

default:"BALANCED"

The rendering speed to use. Default value: "BALANCED"Possible values: FLASH, TURBO, BALANCED, QUALITY

boolean

default:"true"

Determine if MagicPrompt should be used in generating the request or not. Default value: true

string

default:""

Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt. Default value: ""

integer

default:"1"

Number of images to generate. Default value: 1Range: 1 to 8

integer

Seed for the random number generator

boolean

default:"false"

If True, the media will be returned as a data URI and the output data won’t be available in the request history.

Output Schema

list<File>

required

integer

required

Seed used for the random number generator

Input Example

{
  "prompt": "A logo for Ideogram Coffee.",
  "aspect_ratio": "1:1",
  "rendering_speed": "BALANCED",
  "expand_prompt": true,
  "negative_prompt": "",
  "num_images": 1,
  "sync_mode": false
}

Output Example

{
  "images": [
    {
      "url": "https://v3.fal.media/files/lion/AUfCjtLkLOsdc9zEFrV-5_image.png"
    }
  ],
  "seed": 123456
}

Endpoint: POST https://fal.run/fal-ai/ideogram/v3/edit Endpoint ID: fal-ai/ideogram/v3/edit

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/ideogram/v3/edit",
    arguments={
        "prompt": "black bag",
        "image_url": "https://v3.fal.media/files/panda/-LC_gNNV3wUHaGMQT3klE_output.png",
        "mask_url": "https://v3.fal.media/files/kangaroo/1dd3zEL5MXQ3Kb4-mRi9d_indir%20(20).png"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/ideogram/v3/edit", {
  input: {
      prompt: "black bag",
      image_url: "https://v3.fal.media/files/panda/-LC_gNNV3wUHaGMQT3klE_output.png",
      mask_url: "https://v3.fal.media/files/kangaroo/1dd3zEL5MXQ3Kb4-mRi9d_indir%20(20).png"
    },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

curl --request POST \
  --url https://fal.run/fal-ai/ideogram/v3/edit \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "black bag",
  "image_url": "https://v3.fal.media/files/panda/-LC_gNNV3wUHaGMQT3klE_output.png",
  "mask_url": "https://v3.fal.media/files/kangaroo/1dd3zEL5MXQ3Kb4-mRi9d_indir%20(20).png"
}'

Input Schema

list<string>

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

RenderingSpeedEnum

default:"BALANCED"

The rendering speed to use. Default value: "BALANCED"Possible values: TURBO, BALANCED, QUALITY

ColorPalette

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)

list<string>

A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style

boolean

default:"true"

Determine if MagicPrompt should be used in generating the request or not. Default value: true

integer

default:"1"

Number of images to generate. Default value: 1Range: 1 to 8

integer

Seed for the random number generator

boolean

default:"false"

If True, the media will be returned as a data URI and the output data won’t be available in the request history.

Enum

Style preset for generation. The chosen style preset will guide the generation.Possible values: 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

string

required

The prompt to fill the masked part of the image.

string

required

The image URL to generate an image from. MUST have the exact same dimensions (width and height) as the mask image.

string

required

The mask URL to inpaint the image. MUST have the exact same dimensions (width and height) as the input image.

Output Schema

list<File>

required

integer

required

Seed used for the random number generator

Input Example

{
  "rendering_speed": "BALANCED",
  "expand_prompt": true,
  "num_images": 1,
  "sync_mode": false,
  "prompt": "black bag",
  "image_url": "https://v3.fal.media/files/panda/-LC_gNNV3wUHaGMQT3klE_output.png",
  "mask_url": "https://v3.fal.media/files/kangaroo/1dd3zEL5MXQ3Kb4-mRi9d_indir%20(20).png"
}

Output Example

{
  "images": [
    {
      "url": "https://v3.fal.media/files/panda/xr7EI_0X5kM8fDOjjcMei_image.png"
    }
  ],
  "seed": 123456
}

Endpoint: POST https://fal.run/fal-ai/ideogram/v3/layerize-text Endpoint ID: fal-ai/ideogram/v3/layerize-text

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/ideogram/v3/layerize-text",
    arguments={
        "image_url": "https://v3.fal.media/files/lion/0qJs_qW8nz0wYsXhFa6Tk.png"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/ideogram/v3/layerize-text", {
  input: {
      image_url: "https://v3.fal.media/files/lion/0qJs_qW8nz0wYsXhFa6Tk.png"
    },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

curl --request POST \
  --url https://fal.run/fal-ai/ideogram/v3/layerize-text \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "image_url": "https://v3.fal.media/files/lion/0qJs_qW8nz0wYsXhFa6Tk.png"
}'

Examples

Input Schema

string

required

URL of the flat graphic image to layerize. Must be JPEG, PNG, or WebP (max 10MB).

string

Optional prompt to guide the layerization.

integer

Seed for the random number generator.

string

URL of the font file to use for h1 text. Cannot be used with font_name_h1.

string

Name of the font to use for h1 text. Cannot be used with font_file_h1_url.

string

URL of the font file to use for h2 text. Cannot be used with font_name_h2.

string

Name of the font to use for h2 text. Cannot be used with font_file_h2_url.

string

URL of the font file to use for body text. Cannot be used with font_name_body.

string

Name of the font to use for body text. Cannot be used with font_file_body_url.

string

URL of the font file to use for small text. Cannot be used with font_name_small.

string

Name of the font to use for small text. Cannot be used with font_file_small_url.

boolean

default:"false"

If True, the media will be returned as a data URI and the output data won’t be available in the request history.

Output Schema

File

required

The background image with text removed.

string

required

The prompt used for layerization. May differ from the input prompt if MagicPrompt expanded it.

list<object>

Structured text containers with hierarchical text data (container -> items -> spans).

string

Rendered overlay HTML for compositing text over the background image.

list<object>

Image layers extracted from the design.

integer

required

Seed used for the random number generator.

Input Example

{
  "image_url": "https://v3.fal.media/files/lion/0qJs_qW8nz0wYsXhFa6Tk.png",
  "sync_mode": false
}

Output Example

{
  "image": {
    "url": "",
    "content_type": "image/png",
    "file_name": "z9RV14K95DvU.png",
    "file_size": 4404019
  },
  "prompt": "",
  "seed": 123456
}

Endpoint: POST https://fal.run/fal-ai/ideogram/v3/remix Endpoint ID: fal-ai/ideogram/v3/remix

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/ideogram/v3/remix",
    arguments={
        "prompt": "Old ancient city day light",
        "image_url": "https://v3.fal.media/files/lion/9-Yt8JfTw4OxrAjiUzwP9_output.png"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/ideogram/v3/remix", {
  input: {
      prompt: "Old ancient city day light",
      image_url: "https://v3.fal.media/files/lion/9-Yt8JfTw4OxrAjiUzwP9_output.png"
    },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

curl --request POST \
  --url https://fal.run/fal-ai/ideogram/v3/remix \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "Old ancient city day light",
  "image_url": "https://v3.fal.media/files/lion/9-Yt8JfTw4OxrAjiUzwP9_output.png"
}'

Input Schema

list<string>

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

RenderingSpeedEnum

default:"BALANCED"

The rendering speed to use. Default value: "BALANCED"Possible values: TURBO, BALANCED, QUALITY

ColorPalette

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)

list<string>

A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style

Enum

The style type to generate with. Cannot be used with style_codes.Possible values: AUTO, GENERAL, REALISTIC, DESIGN

boolean

default:"true"

Determine if MagicPrompt should be used in generating the request or not. Default value: true

integer

default:"1"

Number of images to generate. Default value: 1Range: 1 to 8

integer

Seed for the random number generator

boolean

default:"false"

If True, the media will be returned as a data URI and the output data won’t be available in the request history.

string

required

The prompt to remix the image with

string

required

The image URL to remix

float

default:"0.8"

Strength of the input image in the remix Default value: 0.8Range: 0.01 to 1

ImageSize | Enum

default:"square_hd"

The resolution of the generated image Default value: square_hdPossible values: square_hd, square, portrait_4_3, portrait_16_9, landscape_4_3, landscape_16_9

string

default:""

Description of what to exclude from an image. Descriptions in the prompt take precedence to descriptions in the negative prompt. Default value: ""

Output Schema

list<File>

required

integer

required

Seed used for the random number generator

Input Example

{
  "rendering_speed": "BALANCED",
  "expand_prompt": true,
  "num_images": 1,
  "sync_mode": false,
  "prompt": "Old ancient city day light",
  "image_url": "https://v3.fal.media/files/lion/9-Yt8JfTw4OxrAjiUzwP9_output.png",
  "strength": 0.8,
  "image_size": "square_hd",
  "negative_prompt": ""
}

Output Example

{
  "images": [
    {
      "url": "https://v3.fal.media/files/koala/eYZG26O54NTdWzdpDWBL-_image.png"
    }
  ],
  "seed": 123456
}

Endpoint: POST https://fal.run/fal-ai/ideogram/v3/replace-background Endpoint ID: fal-ai/ideogram/v3/replace-background

Try it in the Playground

Run this model interactively with your own prompts.

Quick Start

import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/ideogram/v3/replace-background",
    arguments={
        "prompt": "A beautiful sunset over mountains that writes Ideogram v3 in fal.ai",
        "image_url": "https://v3.fal.media/files/rabbit/F6dvKPFL9VzKiM8asJOgm_MJj6yUB6rGjTsv_1YHIcA_image.webp"
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)

import { fal } from "@fal-ai/client";

const result = await fal.subscribe("fal-ai/ideogram/v3/replace-background", {
  input: {
      prompt: "A beautiful sunset over mountains that writes Ideogram v3 in fal.ai",
      image_url: "https://v3.fal.media/files/rabbit/F6dvKPFL9VzKiM8asJOgm_MJj6yUB6rGjTsv_1YHIcA_image.webp"
    },
  logs: true,
  onQueueUpdate: (update) => {
    if (update.status === "IN_PROGRESS") {
      update.logs.map((log) => log.message).forEach(console.log);
    }
  },
});
console.log(result.data);
console.log(result.requestId);

curl --request POST \
  --url https://fal.run/fal-ai/ideogram/v3/replace-background \
  --header "Authorization: Key $FAL_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "prompt": "A beautiful sunset over mountains that writes Ideogram v3 in fal.ai",
  "image_url": "https://v3.fal.media/files/rabbit/F6dvKPFL9VzKiM8asJOgm_MJj6yUB6rGjTsv_1YHIcA_image.webp"
}'

Input Schema

list<string>

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

RenderingSpeedEnum

default:"BALANCED"

The rendering speed to use. Default value: "BALANCED"Possible values: TURBO, BALANCED, QUALITY

ColorPalette

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)

list<string>

A list of 8 character hexadecimal codes representing the style of the image. Cannot be used in conjunction with style_reference_images or style

Enum

The style type to generate with. Cannot be used with style_codes.Possible values: AUTO, GENERAL, REALISTIC, DESIGN

boolean

default:"true"

Determine if MagicPrompt should be used in generating the request or not. Default value: true

integer

default:"1"

Number of images to generate. Default value: 1Range: 1 to 8

integer

Seed for the random number generator

boolean

default:"false"

If True, the media will be returned as a data URI and the output data won’t be available in the request history.

Enum

Style preset for generation. The chosen style preset will guide the generation.Possible values: 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

string

required

Cyber punk city with neon lights and skyscrappers

string

required

The image URL whose background needs to be replaced

Output Schema

list<File>

required

integer

required

Seed used for the random number generator

Input Example

{
  "rendering_speed": "BALANCED",
  "expand_prompt": true,
  "num_images": 1,
  "sync_mode": false,
  "prompt": "A beautiful sunset over mountains that writes Ideogram v3 in fal.ai",
  "image_url": "https://v3.fal.media/files/rabbit/F6dvKPFL9VzKiM8asJOgm_MJj6yUB6rGjTsv_1YHIcA_image.webp"
}

Output Example

{
  "images": [
    {
      "url": "https://v3.fal.media/files/lion/AUfCjtLkLOsdc9zEFrV-5_image.png"
    }
  ],
  "seed": 123456
}

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Examples

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Examples

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

Try it in the Playground

​Quick Start

​Input Schema

​Output Schema

​Input Example

​Output Example

​Related

​Limitations

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Examples

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Examples

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Quick Start

Input Schema

Output Schema

Input Example

Output Example

Related

Limitations