AI Prompt Library

subject: >   The character exactly as shown in the reference image,   preserving the original art style, proportions, line quality,   coloring, texture, and overall visual appearance without alteration. composition: >   Bust-up shot, frontal view,   framing from the upper chest to the top of the head,   balanced composition consistent with the reference image style.   Aspect ratio is 16:9. action: >   The character performs a clear pre-attack pose,   crossing both arms above the head with clenched fists,   slightly lowering the hips (implied through posture and shoulder angle),   while shouting loudly with mouth wide open.   The posture conveys physical tension and preparation.   No additional visual effects. location: >   Same environment as the reference image,   unchanged background and setting. style: >   Identical to the reference image.   Do not modify or reinterpret the art style in any way. camera_lighting: >   Same camera angle, lighting direction, and shading   as the reference image, without enhancement or dramatization. colors: >   Preserve the original color palette exactly as in the reference image. text: >   None. edit_instructions: >   Change only the character’s pose:   bust-up framing,   arms crossed above the head,   shouting facial expression.   Lowered hips are implied through upper-body posture only.   Do not add effects, glow, motion lines, or stylistic changes. references: >   Reference Image A: character identity, art style, and environment. extras: >   High fidelity reproduction of the reference image style,   no stylization, no reinterpretation.

do this for {argument name="superhero name" default="Iron Man"} <instructions>Subject: An open graphic novel. A superhero character is doing his signature move through a page in 3D, with the right sound effect bubbles floating in the air. Style: Pop art mixed with character appropriate style, comic book cel-shading, vibrant primary colors, halftone patterns. Environment: A messy [audience appropriate] desk with action figures and soda cans related to the this super hero's universe. Lighting: Bright, flat, high-key lighting typical of comic book coloring mixed with character appropriate colors. Composition: Dynamic, foreshortened perspective emphasizing the signature move coming toward the viewer.</instructions>

Depict separate figures in each individual shard of flying broken glass

Please generate a manga page. #Character (Highest Priority): **[Important: Perfect reproduction of the attached image (image_urls)] This is not a reference image but an “unalterable master data.” Strictly adhere to the following processes in all generated panels.** 1. **Fixing Features:** Maintain 100% of the attached image's **“hair style, hair color, eye shape, clothing, and accessories.”** Unauthorized arrangements or simplifications are prohibited. 2. **Deformation Rules:** When applying the #Style (chibi character), **only the “head-to-body ratio” should be reduced, and the “face part arrangement and hairstyle design” must not deviate from the attached image.** 3. **Maintaining Identity:** Even if the angle changes, it must be “the same character viewed from a different angle.” Do not change the face to look like a different person. 4. **Do not cause “Prompt Bleed (instruction leakage).”** #Output Size 9:16 #Style: **Basic Art Style:** Monochrome, Japanese manga, gag manga style, thick outline lines. **Style prompt:** Japanese manga, chibi style, thick outline lines, monochrome. **Format:** Vertical writing, Japanese panel layout read from right to left. #Text Generation Rules (Strict Adherence): **[Important: Natural Japanese and Elimination of Duplication]** When generating dialogue in the manga, perform proofreading immediately before output to absolutely prevent the following errors: 1. **Prohibition of Tautology:** Do not repeat the same word or conjunction twice, such as “that is, that is,” “but, but,” or “really, really.” Stuttering expressions are prohibited. 2. **Natural Colloquial Language:** Use natural speech appropriate for the character's personality, not textbook sentences. 3. **Garbled Text Check:** Confirm that Kanji and Hiragana are not corrupted. #Direction/Camera Work: **[Important: Direction while maintaining features]** Use the following camera work within the range that does not distort the character's face or hairstyle to avoid monotony: - **Close-up:** Emphasizing emotion (※Do not overly deform facial parts) - **Long Shot:** Explaining the situation - **High/Low Angle:** Expressing impact or cuteness - **Diagonal Composition:** Expressing agitation or action #Scenario Progression: If no specific panel designation is given, summarize and compose in 3 to 5 panels. Panel arrangement should not be uniform but irregular or free-form, while maintaining the line of sight guidance from “top right to bottom left.” #Negative Prompt (Elements to Avoid): **repeating words, stuttering text, duplicate phrases, tautology,** altering character design, changing hair color, changing hairstyle, different outfit, monotonous composition, repetitive angles, character facing forward in all panels, flat lighting, messy panel borders, text overlap. #Scenario: {argument name="scenario" default="Think of the continuation of the attached manga."}

Step 1: Generate a satisfactory base image: MJ Prompt: cute anime character --sref 3076266117 Step 2: Upload Image 1 to Nano Banana to generate the character: create a sheet with various emotions for this character Step 3: Upload Image 2 to Nano Banana to generate the scene: make a picture in the same style where this character stands in a street

make a manga page with {argument name="character 1" default="[your character]"} and {argument name="character 2" default="[your character]"}, have them do the fusion technique from Dragon Ball Z, and reveal their combined form.

It will output everything, including a simple plot, dialogue, and panel division, if you leave it to the AI.

I constructed a prompt for NanobananaPro that draws manga nicely!

# User Input (Rewrite and submit this) 【Character Settings】 {argument name="character settings" default="Brown hair, twin tails, red eyes, fangs, black cloak, white shirt"} 【Main Character's Worry】 * Content: {argument name="worry" default="I want to eat lots of donuts"} # Command You are an image generation engine. Follow the steps below to generate one image based on the user's input. **Do not output intermediate thoughts or script text. Generate the image immediately.** # Process (Internal Processing) 1. **Automatic Dialogue Determination**: * **Main Character**: Monologues the 【Worry】 input by the user. * **Optimistic Mini-Character**: Responds to the worry with a bright "That's great!" and offers support/encouragement. * **Pessimistic Mini-Character**: Anticipates the worst-case scenario for the worry, saying "No good..." and despairs. * **My-Pace Mini-Character**: **【IMPORTANT】Talks about something completely unrelated to the worry (e.g., tonight's dinner, sleepiness, hobbies).** * **Logical Mini-Character**: **【IMPORTANT】Performs a coin toss and randomly decides to speak either "For" (presenting a rational solution) or "Against" (pointing out risks).** 2. **Image Generation**: Combine the determined dialogue and character settings into the prompt and generate the image. ### Image Generation Prompt Requirements * **Aspect Ratio**: 2:3 * **Style**: Japanese comic/anime style, high quality. * **Composition**: Four "mini-characters (chibi-style)" of the same character are aligned along the main character's head line. 【IMPORTANT】The four mini-characters are lined up "in a horizontal row." 【IMPORTANT】The feet of the mini-characters are hidden (overlapping) by the main character's head or hair. * **【IMPORTANT: Prohibitions】**: * **Absolutely do not write names or roles (e.g., "Logical," "Optimistic") below or around the characters.** * **The only place text is allowed is inside the "speech bubbles."** * Bottom 1/3 of the screen: Extreme close-up of the main character's face. Serious expression. Thinking, hand on chin or mouth, gaze downward. A large horizontal thought bubble. * Top 2/3 of the screen: Four mini-characters are lined up "in a horizontal row" right behind the main character's head. * **Important**: The mini-characters are close enough that their feet are hidden by the main character's head or hair. * **Mini-Character Arrangement and Pose**: From left to right: 1. Logical: Serious face, adjusting glasses, or pointing with a finger. 2. My-Pace: Blank face, yawning, or drinking tea. 3. Pessimistic: Pale face, holding head in despair, vertical line effect. 4. Optimistic: Full smile, hands raised in joy, music note mark. * **Speech Bubbles**: Add comic-style speech bubbles to each character.

A cinematic photorealistic portrait of a young psychic woman inside an underground government research facility inspired by {argument name="inspiration" default="Hawkins Lab"}. Sterile concrete walls, glass observation panels, tangled cables, and industrial equipment surround her. Fluorescent ceiling lights flicker, casting cold white and red emergency lighting across the room. The woman stands centered, calm yet intensely focused. Her dark wavy hair lifts subtly as if affected by invisible force. Her warm brown eyes are locked forward with controlled concentration. A faint nosebleed traces down her upper lip, suggesting mental strain. She wears a simple institutional gown with muted red tones, minimal and utilitarian. One hand is extended toward the viewer, palm open, generating a dense sphere of psychic energy—glowing red-orange, crackling with electrical filaments, heat distortion, and suspended particles, bending the air around it. Lab equipment levitates, glass fractures midair, sparks erupt from torn cables, and debris hangs frozen in suspension. A dim red-orange dimensional glow seeps through cracks in the walls, hinting at another realm pressing through reality. Cinematic lighting, strong rim light, dramatic shadows, sharp focus on face and hand, shallow depth of field, ultra-detailed textures, photorealistic supernatural realism, high contrast, volumetric lighting, tense psychological atmosphere.

Ultra-realistic cinematic scene inspired by Stranger Things. Steve Harrington (from Image 1) is suspended in mid-air inside the Upside Down, his face clearly visible and emotionally broken—eyes glassy with tears, lips trembling, fear mixed with acceptance. His body is slightly contorted by an unseen psychic force, veins subtly visible, a faint trail of blood from his nose. Vecna (from Image 2) appears behind him, partially emerging from darkness and red mist, not attacking violently but silently controlling the moment, one hand raised with cracked, organic skin and glowing red energy. Vecna’s presence feels inevitable and overwhelming rather than loud. The environment is alive: black vines crawl along ruined structures, spores floating slowly through the air like falling ash. Steve’s bat lies broken on the ground below, symbolizing loss and sacrifice. Lighting is highly emotional—cold blue light on Steve’s face to highlight vulnerability, contrasted with deep crimson and shadow around Vecna. Shallow depth of field, cinematic focus on Steve’s expression, volumetric fog, dramatic backlighting, hyper-real skin detail, emotional micro-expressions, Netflix dark horror drama style, photorealistic, ultra-detailed, 35mm film look

A medieval illuminated manuscript depicting the subject in the uploaded image. Neo is rendered as a saintly figure in heavy velvet robes, flanked by Morpheus and Trinity, who are stylized as cloaked scholars. The background is pure gold leaf and vellum, with the digital rain motif replaced by ornate, vine-like gothic borders and calligraphic text.

Please generate an image using this character. - Do not change the character's design or style at all. The lightning bolt character is hospitalized. The lightning bolt character is slowly walking and rehabilitating in the hospital corridor while receiving an IV drip. The crescent moon character is accompanying them.

◆Charging Pose Prompt ・Basic Prompt The character from the reference image takes a charging pose. ⠀ ・Option: Dialogue Places the dialogue: "{argument name="dialogue" default="Ka... me... ha... me..."}" *Changeable ⠀ ◆Kamehameha-Style Wave Prompt ・Basic Prompt Releases a Kamehameha-style energy wave horizontally. There is also a prompt to release it towards the camera. ⠀ ・Option: Dialogue/Sound Effects Places dialogue and sound effects. "{argument name="dialogue 2" default="Wave---!!!"}" "{argument name="sound effect" default="Don!!"}" *Changeable ⠀ ・Option: Speed Lines Draws speed lines.

Please generate an image using this character. Do not change the design, colors, or taste of this character at all. The character on the left is hospitalized in a hospital. The character on the left is resting in bed. The character on the right is sitting on a chair beside the bed, looking worriedly at the character on the left.

I have Opal create the prompt for the manga composition, and then I use Nano Banana Pro via Gemini to create the actual manga.

Make a comic book page

a 4-panel comic, a post-apocalyptic movie poster, and a photorealistic scene

<instructions> you are a world class visual artist and viral content generator tasked with creating high-concept diorama for games or books. For every input, you will analyze the core identity, the defining artifacts, the atmosphere, characters and the underlying narrative of the subject. you will then construct a specific container, the appropriate shell based on the title and year it was made: for any title, analyze the mechanics and aesthetic. visualize a hollowed-out item. the interior is a diorama of a famous level or scene. it contains miniature elements, assets, tiny protagonist, and other relevant elements to the subject. lighting & style should be appropriate for the title </instructions>

Using the uploaded reference image, generate a four-panel composition (upper-left, upper-right, lower-left, lower-right). Keep the person’s face, hairstyle, and clothing exactly the same as in the uploaded image for all panels. Maintain a realistic photo style, consistent identity, and natural lighting. Upper-left (Joy / Joy): A close-up of her face from a slightly high angle. She is smiling brightly with sparkling eyes, expressing pure joy and happiness. Her expression feels open, warm, and genuinely delighted. Upper-right (Anger / Anger): A medium shot of her upper body. She is visibly angry, with furrowed brows and a sharp, intense expression. Her posture is tense, and she slightly clenches her fists or crosses her arms, clearly showing irritation or frustration. Lower-left (Sadness / Sadness): An over-the-shoulder or slightly downward-angled shot. Her body language is subdued and closed off. She looks down with a sorrowful, quiet expression, conveying loneliness or emotional pain, with a soft, muted mood. Lower-right (Fun / Fun): A casual selfie-style shot. She looks playful and energetic, laughing or making a cheerful, fun expression. The mood is lighthearted and carefree, showing her enjoying the moment.

a 2 x 1 grid, a hand-carved alpine chalet mechanism (cuckoo-clock adjacent but not strictly a clock) built into a classic book base with shutters, pendulums, and tiny moving figures. Panel A ({argument name="panel A theme" default="Don Quixote"}): carved windmill roofline with rotating sails and a spring-lunge knight. Panel B ({argument name="panel B theme" default="1984"}): carved brutalist watchtower façade with a blinking iris shutter and sweeping searchlight arm. Style: Photoreal hand-carved woodcraft, visible chisel marks and oiled walnut grain, cozy warm hearthlight + cool moon rim, soft volumetric haze, shallow depth of field, centered on rustic plinths, 65mm perspective, background in deep forest green seamless.

Read the motif depicted in the attached image, generate multi-angle shots, and create four scenes divided into a 2x2 grid. [Action 1] The senior colleague (senpai) is looking at books on a shelf. The photographer presses a button on a remote control in their hand, and a distinctive electronic sound/chime rings. [Dialogue 1] The senpai is surprised, immediately turns to the camera, and playfully says, "Stop it." [Action 2] The photographer rings the electronic sound again. [Action 3] The senpai looks down shyly, squats momentarily, then stands up, laughing and covering their face with their hands. [Text Overlay] "{argument name="text overlay 1" default="Tried pressing the senpai's switch while they were shopping at the bookstore"}" "{argument name="text overlay 2" default="#This feeling is too cute www"}" "{argument name="text overlay 3" default="#Definitely inviting me www"}"

# Image Generation Prompt: Nano Banana Pro v1.2 # 1. Basic Instructions - Task: Image Generation - Reference: Faithfully reproduce and maintain the character, clothing, and image style of the attached image - Quality: Super High Definition # 2. Technical Specifications - Aspect Ratio: 16:9 - Rendering Style: Based on the attached image style, apply Cell Shading + Volumetric Lighting - Line Art: Thin # 3. Camera Work and Composition - Camera: Virtual Camera / Focal Length 50mm / Aperture f/2.8 - Angle: 15-degree Dutch Angle - Focus: Focus on subject - Depth of Field: Shallow depth of field in the background (with blur) # 4. Scene Details A. Character - Appearance (Hair/Eyes/Clothing): [Completely maintain the style of the attached image] - Hair is flowing in reaction to energy pressure - Eyes are glowing, with a sharp anime-style shape - Pose & Action: - Action: Charging an energy attack - Stance: Feet spread and braced, torso twisted forward to the right - Hands: Cupped together facing each other (at hip height on the right), muscles are strongly tensed - Expression: Filled with determination and intense effort, mouth open shouting B. Lighting and Atmosphere - Global Illumination: #ffffff - Key Light: - Source: Energy ball between both hands - Color: Cyan Blue Electric - Intensity: 2.5EV overexposure (High Luminance) - Shadows: Sharp, dynamic shadows extending away from the center C. Visual Effects - Main Element: Spherical, turbulent plasma energy ball (between hands) - Core Color: #ffffff - Outer Glow: #00ffff - Particles: Blue sparks floating and rising - Lens Flare: Anamorphic blue light streaks - Bloom: Intensity 0.8 D. Background - Context: Abstract studio space - Visual: Simple gradient background - Colors: #ffffff to #c0efff * Prioritize layer detail colors over introduction specified colors - Detail Level: Low (to emphasize the subject) # 5. Text Elements - Manga Style Speech Bubbles Place vertical oval speech bubbles reacting to the timing of the shout, using the following coordinate image for placement Adjust flexibly so as not to interfere with the character - "{argument name="shout 1" default="ka..."}" : Top Left (X: 0.08, Y: 0.15) - "{argument name="shout 2" default="me..."}" : Middle Left (X: 0.22, Y: 0.35) - "{argument name="shout 3" default="ha..."}" : Middle Right (X: 0.78, Y: 0.55) - "{argument name="shout 4" default="me..."}" : Bottom Right (X: 0.90, Y: 0.75)

Use the uploaded image only to accurately reconstruct the subject’s face. Preserve exact facial identity, proportions, skin texture, pores, beard detail, eye shape, and realism. Do not reuse pose, lighting, or composition from the upload. Create an ultra-realistic cinematic action moment frozen at the absolute peak of chaos. A powerful adult male fills the extreme foreground, lunging toward the camera with one arm fully extended, fingers reaching past the lens. His expression is pure survival panic — eyes wide, mouth open mid-scream. The face is razor-sharp, perfectly integrated, and emotionally intense. In his other arm, he clutches a panicking tabby cat. The cat is fully alive and reactive: eyes wide and dilated, ears flattened back, mouth open in a silent hiss or scream, whiskers flared, body tense, claws fully extended, hind legs kicking slightly. Fur strands are hyper-detailed and bristled from fear. The cat’s panic mirrors the human’s, amplifying the chaos. Behind them, a massive stadium environment erupts. A violent explosion blossoms outward, throwing concrete, metal fragments, and dust into the air. A police vehicle is launched sideways mid-blast, twisted realistically, emergency lights flashing through smoke. Human silhouettes are flung backward, suspended mid-air in slow-motion realism. Lighting is physical and cinematic: blazing orange firelight rim-lighting the subjects, cold blue emergency strobes slicing through smoke, volumetric haze, flying embers, realistic shadow falloff, extreme dynamic range. Camera is ultra-wide and close, natural perspective distortion, shallow depth of field, sharp subject separation, no fisheye, no artificial blur. Photorealistic, hyper-detailed, cinematic color grading. No cartoon look. No AI artifacts. No softness. Mood: explosive, intense, absurdly unforgettable, viral blockbuster realism.