AI Prompt Library

Using a cat image and noise images, create a diagram explaining the image generation process of a diffusion model. In the training process, show the process of adding noise to the cat image through forward diffusion, and depict the process of creating the noise prediction model.

Please create illustrations that show the procedures for protecting yourself from bears. The people appearing in the illustrations should be Japanese. Please provide the explanations in Japanese.

Transform the user-uploaded image (photo or illustration) into a dramatic Japanese-inspired anime artwork. Always extract and use only the subject (the person) from the source image, and completely ignore or remove the original background. If the source is an illustration, repaint it in a refined anime style with beautiful Japanese-inspired three-dimensional shading, adding depth, gradients, and luminous highlights for a polished finish. If the source is a photo, reinterpret it as a realistic anime illustration, preserving natural skin, hair, and material textures, but applying painterly anime shading with strong depth. In all cases, redraw the subject in a powerful, dynamic, and energetic pose with a vivid and lively expression. Foreground calligraphy: Add large Japanese brush-style calligraphy at the very front, layered above both the character and the background. Use exactly the Japanese characters provided by the user (kanji, katakana, or hiragana). Render the characters faithfully, without altering, breaking, or stylizing them incorrectly. Do not translate or replace them. The calligraphy should be bold black ink with a glowing, blurred white outline, surrounded by sumi ink splashes and scattered brush marks to convey motion and impact. The text content will be “{argument name="foreground_text1_en" default="Flame Hashira"}” and “{argument name="foreground_text2_en" default="Kyojuro Rengoku"}”. Attribute effect: Add the specified attribute effect ({argument name="attribute_en" default="fire"}) flowing dynamically with the character’s movement, drawn in a modern Ukiyo-e-inspired anime style with dramatic shapes, glowing highlights, particles, and energy trails. Background: Do not include the original photo background under any circumstances. Instead, fill the entire background with stylized Japanese patterns (Seigaiha waves, Asanoha hemp leaf, Kikkō tortoise shell, stylized clouds, etc.) combined with glowing elemental effects. Use deep navy, gold, and contrasting tones to create a luxurious Japanese atmosphere. Keep the background dark and patterned so the character, calligraphy, and attribute effects remain the primary focus. Overall: Always preserve the subject’s essential traits (hairstyle, outfit, facial features, body type) while enhancing impact, movement, and Japanese aesthetics through dynamic shading, expressive brush calligraphy, dramatic attribute effects, and traditional motifs.

I want it to be shot from a slightly low angle so that the distant dinosaur’s whole body is included. Tilt this image from a slightly low angle so that the distant dinosaur’s entire body is in frame, and then make it a tall smartphone screen with an aspect ratio of {argument name="aspect_ratio_en" default="6:19"}.

A YouTube thumbnail where this man is {argument name="theme_en" default="introducing Nano Banana Pro"}. Style: {argument name="style_en" default="for businesspeople"}. Font: {argument name="font_en" default="dynamic, glossy, italic"}. Target: {argument name="target_en" default="for Japanese viewers"}. Text: {argument name="text_en" default="In-depth guide to Google’s new AI ‘Nano Banana Pro’"}.

From all our past interactions so far, pick an episode that really represents my personality and turn it into a 4-panel manga. Create that image. Make the image vertical so that the panels progress from top to bottom.

{argument name="nationality_en" default="Japanese"} {argument name="world_en" default="near future"} {argument name="subject_en" default="beautiful woman"} {argument name="location_en" default="city center"}

Hey, Nano Banana Pro, add annotations to the original Transformer architecture diagram.

I want to create a 4-panel manga with a woman as the main character. The woman is {argument name="nationality_en" default="Japanese"}. She has a bright expression. {argument name="hairstyle_en" default="Blonde ponytail tied with a red ribbon."} {argument name="top_outfit_en" default="A white shirt with a rainbow-colored flower patch on her chest."} {argument name="bottom_outfit_en" default="Jeans and red high heels."} 1: The woman is walking and saying “{argument name="line1_en" default="Ahh, I’m so hungry"}”. 2: The woman looks at a shop’s show window and says “{argument name="line2_en" default="Those pancakes look so delicious"}”. 3: The woman is sitting at a table in the shop saying “{argument name="line3_en" default="I can’t wait to eat"}”. 4: The woman is eating pancakes and says “{argument name="line4_en" default="So tasty! But I’m going to get fat!"}”.

Act as a “comprehensive creative” who simultaneously holds the following three perspectives: Author’s perspective 　→ Naturally capture nuances of the character’s emotions, atmosphere, and movement Editor’s perspective 　→ Manage composition, natural flow of text, and consistency of information density Reader’s perspective 　→ Prioritize the kind of emotion that instantly draws the viewer in and maximizes appeal Make sure these three perspectives are fused without contradiction in your output. ■ Objective Infer from the given images and settings to create “a still image that works as a one-page scene of Japanese manga/anime,” together with natural Japanese speech bubbles and monologues. Make “micro-emotion” and “the pull of texture” the core of the scene. ■ Basic policy (axes for the AI’s free inference) Place focus on depictions that embed emotion in subtle motions and textures, such as the character’s gestures, fingertips, gaze, and the sway of their hair. Use the three personas to simultaneously achieve “visually strong × natural to read × compelling to look at.” Do not treat it as a single panel, but give it the structural strength of “a one-page scene.” Arrange backgrounds and small props so that they complement the character’s inner world. Leave a rhythmic sense of empty space in the frame where speech bubbles can be placed. Create a “pulling pause” through distance, light direction, and shadows. Treat it not as a magazine cover, but as “a frozen decisive moment in the story.” ■ Lines to keep (coherence and aesthetic guidelines) Natural Japanese (no typos, no AI-ish phrasing). Physical consistency of hands, joints, light sources, shadows, and posture. Avoid excessive information density; respect empty space and pauses. Real URLs, QR codes, and JAN codes are prohibited. Avoid AI noise and visual breakage. Do not damage the character’s dignity or psychological realism. Do not lean toward sexual expression; keep “the charm of micro-emotion” as the core. Treat “micro-emotion” as texture description that touches the psyche and do not use specific fetishistic terms. ■ Areas you may infer (creative freedom) Fluctuations in the character’s emotions and inner movements. The relationship between light direction and psychology. “Touchable” textures of hair, clothing, and materials. Angles of hands, wavering gaze, and body tilt. Narrative meaning of the background. Temperature of the air (silence/humidity/tension). The visual focal point of attraction. Strength of the composition as a one-page layout. Add small props when needed (within the bounds of consistency). ■ Output style (manga one-page spec) A readable flow as a single page: 　→ empty space → character → text → background support. Speech bubbles should be in natural Japanese, placed in a way that captures the character’s breath and edges of emotion. Treat monologue as words sinking inside the character (not explanatory text but a shadow of feeling). Make the still image feel like it contains a drift of time. From gestures and textures, depict the “peak of micro-emotion.” ■ One-sentence summary “Integrate the three perspectives (author, editor, reader) and, focusing on micro-emotion and the pull of texture, infer and finish a one-page Japanese-language scene that captivates.”

Summarize the good points of {argument name="region_en" default="Fukuoka"} in a single image.

A photo where a character is sitting on a real sandy beach, with a horizon line and sunset, emotional photo filter effects, bokeh, lens flare, strong shadows and contrast, medium shot, the character is an illustration and the background is a photo, and the background’s angle of view must match the character’s angle of view.

Please depict a downtown shopping street scene in {argument name="location_en" default="Japan"} during the {argument name="era_en" default="high economic growth period"}.

A {argument name="object_en" default="metal ball"} dropping into water, with a slow-motion splash, realistic physics and refraction, at {argument name="resolution_en" default="2K"} resolution.

Photograph a taxi stopped on {argument name="location_en" default="Yasukuni-dori in front of Kabukicho Ichibangai"} on a rainy night, from a front diagonal angle with cinematic camera angle and lighting.

Change this banner image to a {argument name="aspect_ratio_en" default="1:1"} size.

Add large Japanese onomatopoeia text in classic manga style. Insert ONLY bold, dynamic text: 「{argument name="sfx_text_en" default="ゴゴゴゴーッ！！！"}」 Style requirements: - Heavy black ink manga typography - Thick strokes with a white outline - Slightly rough, hand-drawn texture like shonen manga sound effects - Diagonal placement from lower left toward upper right - Strong perspective distortion for impact - Add subtle speed lines and impact rays around the text - Slight drop shadow for depth Do NOT change the woman, the lighting, or the background. Keep photo realism intact. Only overlay manga-style sound effect text.

Please create the image for page 1 of the following manga featuring the girl in the picture, "{argument name="character_name_en" default="Neon"}." Speech bubbles should be vertical. Panels are read from right to left, top to bottom. Make it a manga image with an {argument name="aspect_ratio_en" default="9:16"} size. Title: "{argument name="title_en" default="Sparkling Boot-Up! It’s Neon!"}" Page 1

A hand-drawn map of a fictional town in {argument name="country_en" default="Japan"}.

It can output Japanese perfectly. I had it create an image showing that the fictional diner "{argument name="shop_name_en" default="Teishokuya Nagame"}" has started serving {argument name="new_menu_en" default="oyakodon"}.

A castle town from the {argument name="era_en" default="Edo period"}.

--- generation_parameters: aspect_ratio: "1:3" manga_page_generation_prompt: layout_structure: type: Full page vertical 4-panel comic strip (yon-koma layout). arrangement: Four roughly square panels stacked perfectly vertically from top to bottom. spacing: Clear white gutters separating each of the four panels. title_area: (Optional) A small space at the very top for a title. overall_aesthetic: A printed comic magazine page look with slightly textured paper. art_style: description: {argument name="style_desc_en" default="1970s–80s Japanese Gekiga style: gritty, heavy shadows, serious tone."} color_palette: Desaturated, heavy oil-painting colors, sepia tones, dark atmosphere. texture: Rough ink lines, analog brushwork, dramatic cross-hatching shadows, and ink bleed effects. manga_elements: speech_bubbles: - Presence: Multiple hand-drawn speech bubbles (fukidashi) within panel boundaries. Style: Rough, organic outlines containing placeholder Japanese marks. sound_effects: - Presence: Bold Katakana sound effects integrated into the art. Style: Rough calligraphy (e.g., "ドォォォン", "ゴゴゴゴ"). panel_content_sequence: panel_1_top (Intro): - Scene: [Wide angle] Knight Alex (grim face, full armor) standing stiffly behind a modern convenience store counter. - Text/FX: Speech bubble with formal greeting. Small "ウィーン" (door sound). panel_2_upper_mid (Development): - Scene: A scared salaryman customer shrinking away, Alex glaring intensely and leaning forward over the counter. - Text/FX: Customer's scared bubble. Large "ゴゴゴゴ" (menacing FX) around Alex. panel_3_lower_mid (Twist): - Scene: [Dramatic close-up] Alex pulling out his giant claymore sword just to point at a bento box. - Text/FX: Spiky shout bubble "貴様の糧はこれか!!" and intense "ジャキィィン！" (sword FX). panel_4_bottom (Conclusion): - Scene: The exhausted store manager (looser art style) smacking Alex's head with a rolled magazine. Alex looks comically dejected. - Text/FX: Manager's angry bubble "剣をしまうんだよ！" and sharp "スパン！" (slap FX). negative_prompt: - Single illustration, square image, landscape orientation - Panels arranged horizontally in a 2x2 grid - Modern clean digital art, anime style - Bright cheerful colors, no shadows

I want to create {argument name="sticker_count_en" default="8"} LINE stickers using the person in this image. (I will attach the image.) I want everyday greetings and phrases. Change the expressions and poses to match those phrases.

This girl is my original character, "{argument name="character_name_en" default="Anna"}." She is the female warrior holding a sword in the second image. Please create a 4-panel manga with an RPG game-style world. The panels are arranged vertically. The dialogue should be in Japanese.