Avatar

Make character images, from a clean portrait to a full avatar with its outfit, several shots on one sheet, or an outfit flat lay.

The Avatar tab makes still images of characters: who the person is, what they wear, and how they look from several angles. To make a character speak on video, use the Avatar input mode of Video.

Avatar ComposerFull avatar mode with identity, outfit, background, and contact-sheet variations.
PortraitClean white-background portrait generation with visible subject controls and optional builder details.
OutfitTop-down flat-lay outfit generation with all available outfit reference slots for the selected model.

A common path: set the face in Portrait, build the clothes in Outfit, then bring both into Avatar Composer.

Avatar Composer

Avatar Composer combines up to three references into one character image. Its slots are all optional:

Slot What it gives the result
Character The person: face, hair, identity.
Outfit The clothes.
Environment The place. Hidden while Production Sheet is on.

A slot can also hold a snippet: its text is used instead of an image. Some models need at least one reference image, and Create tells you before you generate. The prompt is optional: use it for anything the references do not cover.

The settings panel adds:

  • Gender: Prompt, Woman or Man. Prompt leaves it to your prompt. It locks when a Character image is loaded, since the image decides.
  • Contact Sheet Variations: on by default. Shows the same character in several shots on one image, in a 2x2 or 3x3 grid.
  • Production Sheet: one page for the whole character, as Simple (a turnaround and a face close-up above a name bar) or Detailed (an info block, a turnaround, expressions, accessories and a color palette). Contact Sheet Variations is off while it is on.
  • Style: adds a Style Reference slot and a style preset picker. This switch is in every input mode.

Model

  • Avatar Generator
ChatGPT Image 2.5 FlareOpenAI

Inputs

  • @identityCharacters
  • Léa
  • PersonalityPlayful, Creative, Bold, Elegant
A production sheet from one Character image, with a name and a personality set in the builder.

Portrait

Portrait makes a clean portrait on a white background. It has no character, outfit or environment slots: describe the person in the prompt, pick a Gender, and add details in the builder. It runs on text-to-image models, so its model list differs from the other two input modes.

Model

  • Avatar Generator
Krea 2.0 Medium TurboKrea

Prompt

ballet dancer

  • Age Range20-30
  • EthnicitySoutheast Asian
  • Skin ToneMedium warm
  • Hair ColorBlonde
  • Hair StyleSoft waves
  • MakeupClassic red lip

Settings

  • CreativityMedium
  • Intensity0
  • Complexity0
  • Movement0
A two-word prompt, with age, skin tone, hair and makeup set in the builder.

Outfit

Outfit makes a top-down flat lay of a full outfit on a white background, with no person. Load garments in Outfit Reference 1, Outfit Reference 2 and so on: the panel offers as many slots as the model accepts images. Or leave the slots empty and describe the outfit in the prompt and the builder.

Avatar Builder

Open Builder in the prompt bar to set the character with menus instead of words. Its sections follow the input mode:

  • Avatar Composer and Portrait: Character (age range, ethnicity, skin tone, eye color, hair color, length and style) and Styling (expression, outfit, makeup, and a portrait finish in Portrait). With Production Sheet on, it adds a name, an activity or role, and personality traits.
  • Outfit: Audience (Women’s, Men’s or Unisex), then Core Outfit, Styling Pieces and Presentation.

Loaded references take over from the builder. In Avatar Composer, a Character image locks the identity fields. In Outfit, loading outfit references locks the builder.

Models

Each input mode offers its own models. The default model is ChatGPT Image 2.5 Flare.

Avatar Composer

OpenAI
  • ChatGPT Image 2.5 FlareDefault
  • ChatGPT Image 2.5 Sunburst
  • ChatGPT Image 2.0
GeminiGoogle
  • Nano Banana 2.1
  • Nano Banana 2.0
  • Nano Banana 2.0 Lite
  • Nano Banana Pro
SeedreamBytePlus
  • Seedream 5.0 Pro
  • Seedream 5.0 Flash
Meta
  • Muse Image
GrokxAI
  • Grok Imagine 2.0
FluxBlack Forest Labs
  • Flux 3.0
12 models from 6 providers. The same list as the model picker in the app.

Portrait

OpenAI
  • ChatGPT Image 2.5 FlareDefault
  • ChatGPT Image 2.5 Sunburst
  • ChatGPT Image 2.0
GeminiGoogle
  • Nano Banana 2.1
  • Nano Banana 2.0
  • Nano Banana 2.0 Lite
  • Nano Banana Pro
SeedreamBytePlus
  • Seedream 5.0 Pro
  • Seedream 5.0 Flash
KlingKlingAI
  • Kling 3.0
WanAlibaba
  • Wan Image 2.7
  • Wan Image 2.7 Pro
GrokxAI
  • Grok Imagine 2.0
  • Grok Imagine
QwenAlibaba
  • Qwen 3.0 Pro
  • Qwen 3.0
  • Qwen 2.1 Pro
  • Qwen 2.0
FluxBlack Forest Labs
  • Flux 3.0
  • Flux 2.0 Pro
  • Flux Klein 2.0 4B
  • Flux Klein 2.0 9B
Recraft
  • Recraft 4.1
  • Recraft 4.1 Pro
  • Recraft 4.1 Utility
  • Recraft 4.1 Utility Pro
  • Recraft 4.1 Flash
  • Recraft 4.0
  • Recraft 4.0 Pro
Z-ImageAlibaba
  • Z-Image Turbo
Ideogram
  • Ideogram 4.5
Krea
  • Krea 2.0 Large
  • Krea 2.0 Medium
  • Krea 2.0 Medium Turbo
Microsoft
  • MAI Image 2.6 Flash
  • MAI Image 2.6
  • MAI Image 2.5 Flash
  • MAI Image 2.5
  • MAI Image 2.5 Pro
Meta
  • Muse Image
40 models from 14 providers. The same list as the model picker in the app.

Outfit

OpenAI
  • ChatGPT Image 2.5 FlareDefault
  • ChatGPT Image 2.5 Sunburst
  • ChatGPT Image 2.0
GeminiGoogle
  • Nano Banana 2.1
  • Nano Banana 2.0
  • Nano Banana 2.0 Lite
  • Nano Banana Pro
SeedreamBytePlus
  • Seedream 5.0 Pro
  • Seedream 5.0 Flash
KlingKlingAI
  • Kling 3.0 Omni
WanAlibaba
  • Wan Image 2.7
  • Wan Image 2.7 Pro
GrokxAI
  • Grok Imagine 2.0
  • Grok Imagine
Meta
  • Muse Image
FluxBlack Forest Labs
  • Flux 3.0
16 models from 8 providers. The same list as the model picker in the app.

Learn more

Esc
Type to search the documentation and changelog.