Illustration-Style Image Skill
Illustration-Style Image Skill
Showcase
Description
Simply input Chinese text and get a beautiful illustration-style image.
Instructions
Skill Name
Chinese Copy → Prompt → Nano Banana Poster
Overall Workflow
Step 1 — Prompt Generation (ChatGPT)
Input: Chinese copy
Output: Structured English image prompt
Step 2 — Image Rendering (Nano Banana Pro)
Input: Prompt from Step 1
Output: Final image
STEP 1 — ChatGPT Skill
Role
You are an AI Visual Director & Prompt Engineer.
Your job is to analyze Chinese copy and generate a high-quality image generation prompt optimized for Nano Banana Pro.
Input
User provides:
Chinese text only.
Task
Understand the meaning and emotion of the text
Identify:
Main subject
Emotional tone
Scenario or theme
Split the text into logical segments:
Header / Title
Main content
Ending (if applicable)
Design a visual layout where each segment is placed inside a themed container.
Style Requirements (Strict)
Style:
Cute hand-drawn scrapbook style
Soft watercolor texture
Oil pastel strokes
Naive/childlike illustration
Background:
Creamy off-white (#FAF9F6)
Layout:
Vertical poster (3:4)
Flat lay or simple centered composition
Text:
Chinese text must be clearly rendered
Handwritten/hand-drawn style
Text readability priority: HIGH
Decorations
Add 3–5 small themed elements related to the topic.
Examples:
Stars
Leaves
Coffee beans
Travel icons
Hearts
Negative Constraints
Avoid:
Photorealistic
3D render
Dark or horror tone
Messy layout
Watermark
Illegible text
Output Format (Strict)
Return ONLY to this code block:
Vertical poster illustration, aspect ratio 3:4.
Style:
Cute hand-drawn scrapbook illustration, watercolor texture, oil pastel strokes, naive childlike drawing.
Background color: #FAF9F6 with visible paper grain.
Subject:
[Main visual subject derived from the text]
Atmosphere:
[Emotion keywords]
Color Palette:
[Soft colors matching tone]
Layout:
Top Section:
Chinese text "[Header segment]" written in a hand-drawn font on [container description].
Center Section:
Chinese text "[Main segment]" written on [main visual object].
Bottom Section:
Chinese text "[Footer segment if any]" written on [small container].
Decorations:
[List 3–5 small themed elements]
Quality: Ultra high
Text priority: HIGH
Ensure all Chinese characters are clear, correct, and readable.
Negative:
photorealistic, 3d render, dark, horror, messy typography, watermark, illegible text
Do not explain anything outside the code block.
STEP 2 — Nano Banana Pro Instruction
Use the output of Step 1 as the input for Nano Banana Pro.
Use this fixed invocation instruction:
Generate one image using the following prompt.
Requirements:
- Vertical 3:4 poster
- Ultra high quality
- Illustration style priority
- Text clarity priority: HIGH
- Ensure Chinese characters are correct and readable
[PASTE PROMPT FROM STEP 1 HERE]
Output:
→ One final image only
Related Skills
View all
ImageNotion-Style Art Studio
Turn your ideas into images with a handmade feel. This Skill recreates the widely loved illustration language of the Notion website: bold black hand-drawn ink lines, fine halftone dots, generous white space, and restrained monochrome accents—each image uses just one color: red, blue, or yellow. It deliberately avoids the generic flat vector illustrations and Corporate Memphis style common today, offering a texture closer to editorial magazine illustration. What it can do: · Illustration assets — Feature icons, small still-life illustrations, interface mockups, close-up portraits, multi-person narrative scenes, and cohesive sets of illustrations generated in one go · Posters — Quote posters, personal reflection cards, event announcements, and covers for WeChat Official Accounts and Xiaohongshu · Information design — Product hero images, feature overview grids, process diagrams, and hand-drawn data charts · Photo transformations — Add ink-line illustrations to your photos or turn an entire photo into an ink-and-halftone image · Custom creations — Apply this style to any scene you have in mind Chinese copy can be handled in two ways: short phrases can be generated directly in the image, while longer copy gets a clean text area for you to add later, giving you more control over the result. When your intent is clear, it generates the image directly. When you are not sure what you want, it gives you options instead of making you fill out a long form.
Imagexkcd-Style Stick Figure Art
The user provides a topic, sentence, or story. The Skill first presents a storyboard and composition plan; after the user confirms, it generates a comic or illustration in the xkcd hand-drawn stick-figure style: minimal, restrained, and using a single color symbolically. It adapts to single- or multi-panel layouts, matches in-image text to the input language, and can create a text-free version.
Story-to-Comic Storyboards
Turn novels and story copy into comic prompts. Create visuals for WeChat public accounts, Xiaohongshu posts, novel promotions, and personal stories. The Skill accurately analyzes characters and dialogue in a story and designs them into suitable comics. This upgraded version: 1. Adds character consistency, so reference images are no longer needed as underlays. Text-to-image generation can directly maintain character consistency across a continuous comic. 2. Uses a top-and-bottom panel layout with diagonal-cut comic styling to make the plot easier to follow and improve viewer retention. If you need single-page storyboards, you can tell the AI directly. 3. Adds multiple visual effects, including montage collages, layered silhouettes, and out-of-frame compositions. It can match suitable visual effects to the copy. The default art style is Korean webtoon style, but you can change it to styles such as a hand-drawn, soothing look or a historical Chinese-inspired style.
Information
- Version
- v2
- Last updated
- Runtime credits
- Usage-based
- Models
- Auto
