Ai Image Prompts

◆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.

[Format] Horizontal 3-panel manga (left to right). Anime style + pop. Bright color scheme. Clean lines. Simple office background.
[Characters] Emma (20s female, black bob, white shirt + navy jacket, expressive face). Consistent appearance across all panels.
[Text] Japanese text displayed clearly and legibly. No typos, garbled characters, or broken text. Use the following text in the speech bubbles "exactly as written":

Panel 1 (Left):
Emma is explaining while pointing.
Speech bubble text (exact match):
"{argument name="Panel 1 Text" default="ChatGPT Images is good at illustrations, anime, and 3D expressions"}"

Panel 2 (Center):
Emma is doing design work (layout and typesetting).
Speech bubble text (exact match):
"{argument name="Panel 2 Text" default="Nano Banana is good at Japanese text and design"}"

Panel 3 (Right):
Comparison panel. Split the screen left/right, with headings "ChatGPT Images" on the left and "Nano Banana" on the right.
Include checklists for each (in Japanese, short, and readable).
Left (ChatGPT Images): 'Illustration', 'Anime', '3D Expression'
Right (Nano Banana): 'Japanese Text', 'Design', 'Layout'
Also, place a large "VS" in the center to compare the two compositions.

[NG] No unnecessary text, arbitrary English additions, watermarks, signatures, unreadable text, or broken Japanese.
[Image Quality] High resolution, sharp, suitable for SNS posting.