Available now

Ideogram V3: image editing

By Ideogram

Ideogram V3 makes images, posters and designs from a prompt, and also edits a masked area, remixes a photo, swaps a background or renders on a transparent background.

Model ID
Maker
Ideogram

Input

Fields marked * are required. Review the price before generating.

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

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

The prompt to fill the masked part of the image.

Example prompt. Edit it or write your own.

MUST have the exact same dimensions (width and height) as the mask image.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

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

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

Additional settings

A list of 8 character hexadecimal codes representing the style of the image.

Determine if MagicPrompt should be used in generating the request or not.

Seed for the random number generator

The chosen style preset will guide the generation.

Estimated total · Balanced$0.10

You sign up first. Your settings are kept.

About this model

Overview

Ideogram V3 makes up to 8 images per run. Steer the look with a style type, one of over 60 style presets, style reference images or style codes, and choose Turbo, Balanced or Quality rendering.

Four more modes work on images: fill a masked area from a prompt, remix a photo with a strength you set, replace the background behind a subject, or create artwork on a transparent background for logos and stickers.

What you can build

  • Posters, flyers and covers with readable titles
  • Logos and stickers on a transparent background
  • A product photo placed in a new setting
  • Variations of an image in a new style
  • Fixes to one part of a picture with a mask

Prompting tips

  • Put the exact words you want in the image in quotes.
  • Use Turbo while you search for the layout and Quality for the final version.
  • Turn prompt expansion off when your prompt is already long and exact.
  • In remix, a lower strength moves further from the original photo.

What to check

Proofread text and check that reference styling has not obscured the subject.

Inputs

  • Images (optional): 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.
  • Rendering Speed (optional): The rendering speed to use. Options: Turbo, Balanced, Quality.
  • Style Codes (optional): A list of 8 character hexadecimal codes representing the style of the image.
  • Enable Prompt Expansion (optional): Determine if MagicPrompt should be used in generating the request or not.
  • Number of Images (optional): Number of images to generate. From 1 to 8.
  • Seed (optional): Seed for the random number generator.
  • Style Preset (optional): Style preset for generation. The chosen style preset will guide the generation. Options: 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.
  • Prompt (required): The prompt to fill the masked part of the image.
  • Image (required): The image URL to generate an image from. MUST have the exact same dimensions (width and height) as the mask image.
  • Mask (required): The mask URL to inpaint the image. MUST have the exact same dimensions (width and height) as the input image.

Output and limits

  • Up to 8 images per run.
  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • Turbo: $0.05 / image
  • Balanced: $0.10 / image
  • Quality: $0.15 / image