Achieving Consistent Characters and Cohesive Styles in AI Storyboards with Amazon Nova – Part 1

Prompt engineering for consistent storyboard characters

Divide the visual prompt into style description (e.g., “a graphic‑novel style illustration”) and style details (e.g., “Bold linework, dramatic shadows, flat color palettes”). Combine with a detailed character description such as “a 7‑year‑old Peruvian girl with dark hair in two low braids wearing a school uniform”.

{style_description} A 7 year old Peruvian girl with dark hair in two low braids wearing a school uniform. {style_details} styles = [{"name":"graphic-novel","description":"A graphic novel style illustration of","details":"Bold linework, dramatic shadows, flat color palettes, high contrast lighting, cinematic composition."},{"name":"sketch","description":"A simple black and white line sketch of","details":"Rough sketch lines, high contrast, no color"},{"name":"digital-illustration","description":"A 3D digital drawing of","details":"High contrast, rounded character design, smooth rendering, soft texture, luminous lighting"}]

Controlling variation

seed

generates different visual variations while keeping the same textual prompt; changing the seed alters pose or expression. cfgScale (range 1.1–10) controls adherence to the prompt. Values near 6.5 give a balance; lower values increase creative freedom and may break consistency, higher values enforce the prompt but can reduce natural composition.

End‑to‑end workflow

Use Amazon Nova Lite to generate optimized image prompts from a high‑level scene description.

Keep seed and cfgScale constant across scenes.

Feed the optimized prompts to Amazon Nova Canvas to produce consistent images.

Optionally pass the same prompts (with added motion cues) to Amazon Nova Reel to create short animation clips.

Scene and character JSON example

{
  "scenes":[
    {"description":"Mayu stands at the edge of a mountainous path, clutching a book. Her mother, Maya, kneels beside her, offering words of encouragement and handing her the book. Mayu looks nervous but determined as she prepares to start her journey."},
    {"description":"Mayu encounters a 'danger' sign with a drawing of a snake. She looks scared, but then remembers her mother's words. She takes a deep breath, looks at her book for reassurance, and then searches for a stick on the ground."},
    {"description":"Mayu bravely makes her way through tall grass, swinging her stick and making noise to scare off potential snakes. Her face shows a mix of fear and courage as she pushes forward on her journey."}
  ],
  "characters":{
    "Mayu":"A 7‑year‑old Peruvian girl with dark hair in two low braids wearing a school uniform",
    "Maya":"An older Peruvian woman with long dark hair tied back in a bun, wearing traditional Peruvian clothing"
  }
}

Visual results

Generated storyboard images show consistent rendering of the character across the mountain path, grassland, and beach scenes. Minor differences may still appear within the same scene.

GitHub resources

Full code examples and resources are available at https://github.com/aws-samples/sample-character-consistent-storyboard/tree/main/01-character-consistent-storyboarding-with-amazon-nova. The Amazon Nova image‑generation guide is at https://docs.aws.amazon.com/nova/latest/userguide/image-generation.html.