PROMPT GALLERY
Meme Prompt Gallery
Reaction images and meme formats, generated on demand: sticker packs, expression progressions, MS-Paint redraws and satirical formats. Copy the prompt, generate the base image, then drop your caption in any editor.
14 curated prompts with real reference images
请将我上传的每一张照片分别制作成一张独立的高级设计海报，不多图拼接，每张照片单独输出。整体采用3:4竖版构图，上下两个区域高度严格1:1，各占画面50%。 上半部分保留原始照片，准确保持主体身份、情绪、姿态、空间关系、真实质感、自然光影和原有色彩氛围，仅进行轻微高级摄影调色，使其具有时尚杂志、艺术出版物与展览摄影质感。为适配画幅，可自然扩展天空、地面或环境背景，但不得拉伸、扭曲或改变主体。 下半部分提取照片中最具识别性的主体、轮廓、姿态与叙事关系，重构为轻盈、稚拙、复古的手绘编辑插画。不要机械复刻细节，以概括造型、适度夸张比例、符号化特征和幽默视觉隐喻重新表达，同时保持原物一眼可辨。融合现代主义编辑插画、包豪斯平面构成、儿童绘本、稚拙艺术与时尚速写气质，形体简练，轮廓略带迟疑与手工误差，局部特征可适度放大，让画面兼具故事感、时尚感与俏皮感。 配色从上方照片中提取，采用高明度、低至中等饱和度的柔和有限色盘，以近似色统一氛围，小面积互补色制造视觉跳点。使用水彩、水粉、彩铅、粉蜡笔与干刷混合质感，保留纸张颗粒、透底、笔触断裂、边缘毛糙、轻微脏色与旧印刷套色偏差。背景大面积留白，仅以松散淡彩、局部斜线或简单几何元素承托主体，避免复杂场景堆积、写实光影、光滑矢量、3D渲染和过度精修。 文字从照片的地点、人物、场景或主题中提炼少量英文关键词、标题、编号或适配金句，并延续下半部分的手绘编辑语言。主标题采用略带稚拙与复古感的手写艺术字，辅助文字使用克制温和的无衬线或衬线字体，可轻微错位、倾斜、拉伸、叠色或产生旧印刷套色偏移，让文字像插画的一部分自然生长在画面中，而不是后期贴上的排版元素。 整体使用米白或浅色背景与大量留白，上下画面通过相同的主体特征、色彩、姿态和视觉符号形成呼应。整体气质轻松、俏皮、复古、温柔、聪明、时髦、幽默、浪漫、松弛，略带笨拙与古怪自信，像一页被精心保存的旧时尚绘本与现代艺术杂志。
Using the provided reference image, redraw the same cat as a deliberately clumsy computer-mouse doodle in a simple MS Paint style. Keep the original centered composition and plain light background, but transform the realistic photo into rough hand-drawn line art with visible wobbly strokes, minimal detail, and an amateur low-effort look. Use thin orange outlines for the head, ears, fur stripes, chest fluff, and body edges; pink scribbled inner ears and nose; black curved closed-eye lines and mouth; and light gray whiskers. Preserve the sleepy closed-eye expression and front-facing pose, but make the drawing look awkward, naive, and slightly messy, like a quick bad sketch traced from the photo.
Redibuja la imagen adjunta de manera torpe, garabateada y lo más absolutamente patética posible. Usa un fondo blanco, y haz que parezca que fue dibujada en MS Paint con un ratón. Debería ser similar pero también distinta, algo así como coincidente pero desfasado de una manera confusa y torpe, con esa sensación de baja calidad píxel por píxel que realmente enfatiza lo ridículamente malo que es. En realidad, sabes qué, da igual, solo dibújalo como quieras.
Restore the attached image in the most clumsy, scribbly, and utterly pathetic way possible. Use a white background, and make it look like it was drawn in MS Paint with a mouse. It should be vaguely similar but also not really, kind of matching but also off in a confusing, awkward way, with that low-quality pixel-by-pixel feel that really emphasizes how ridiculously bad it is. Actually, you know what, whatever, just draw it however you want the attached photograph. this is the image of dragon ball entire franchise in one Apologies for the photo's content, I know it's extremely strange and disturbing! No questions, no explanatory text, just the restored image please.
Use the uploaded character image to create 16 personalized chibi chat stickers in a 4×4 grid, plus a white-background GIF slideshow and individual PNG files. CHARACTER IDENTITY Preserve the character’s recognizable hairstyle, hair color, eyes, outfit, accessories, and signature colors across all 16 stickers. If I identify a fictional character, reflect their established personality without inventing lore or presenting original captions as official quotes. If the character is unknown, use their visual design as a creative personality cue. Prioritize any personality details I provide. EVERYDAY CHAT COMES FIRST These stickers should be useful in ordinary conversations with friends—not character posters, promotional slogans, or dramatic monologues. First choose a familiar conversational purpose, then adapt its wording and expression to the character. Cover a balanced selection of: greetings, agreement, refusal, thanks, apologies, laughter, confusion, surprise, affection, encouragement, celebration, waiting, tiredness, frustration, playful teasing, and saying goodbye. Create short, natural English captions, usually 1–4 words. Use wording that English speakers would actually send in a casual chat. Examples of the desired naturalness include: “Hey!”, “Got it!”, “Nope.”, “Thank you!”, “My bad.”, “Wait, what?”, “Seriously?”, “You got this!”, “Not today.”, “On my way!”, “Need a break.”, and “Talk later!” These are examples, not a fixed caption list. Choose captions that fit this character and the expressions you create. PERSONALITY WITHOUT AWKWARD DIALOGUE Express the character’s personality mainly through facial expressions, gestures, posture, and tone. For example: • A proud character can say “Nailed it!” with a smug smile. • A shy character can say “Thank you!” while blushing. • A dramatic character can say “Seriously?!” with an exaggerated reaction. • A reserved character can say “Got it.” with a subtle nod. At least 12 of the 16 stickers should work in common everyday conversations. Up to 4 may include recognizable character interests or gentle fandom references, as long as they still have a clear conversational use. ART STYLE Use polished big-head chibi anime sticker illustrations: expressive glossy eyes, soft cel shading, clean outlines, and cute, readable gestures. Preserve recognizable character details while simplifying them for small sticker sizes. Use mostly chest-up compositions. Add thick white die-cut borders with a subtle light-gray outer outline. Use a solid pure-white background. Match each expression and gesture to its caption. Make all 16 reactions visually distinct. Use small decorative symbols sparingly and keep them relevant. TEXT AND LAYOUT Arrange exactly 16 complete stickers in 4 equal rows and 4 equal columns. Place one English caption above each character in large, readable, playful lettering. Use colors that complement the character’s palette. Keep the entire caption, character, hands, hair, accessories, props, and sticker border inside its own cell with generous white margins. No overlapping cells, cropped elements, grid lines, numbering, watermarks, or extra text. DELIVERABLES 1. One PNG containing the complete 4×4 sticker sheet. 2. A ZIP containing all 16 stickers as separate PNG files. 3. One GIF cycling through the 16 stickers in reading order, holding each for approximately 1.2 seconds and looping continuously. Use identical canvas dimensions and consistent positioning for all GIF frames. Every frame must have an opaque pure-white background. Explicitly disable transparency and preserve pure white in the GIF palette. The GIF should be a sticker slideshow, not a continuous character animation. FINAL CHECK Before delivery, inspect: • Natural English and correct spelling. • Practical everyday uses and varied conversational meanings. • Clear agreement between captions and expressions. • Consistent character identity and correct anatomy. • Complete text and sticker borders. • Clean individual crops without neighboring sticker fragments. • A genuinely white, nontransparent GIF background. Proceed with sensible creative choices without asking me to select every caption. Briefly explain the personality direction, then provide the finished files. If GIF export or file extraction is unavailable, clearly state the limitation. Do not present a still image as an animated GIF.
Create a clean, high-resolution character expression sheet featuring a single chibi-style young man with messy black hair, round glasses, and a grey hoodie. The image must be arranged in a precise 4x4 grid (16 panels total), numbered 1 through 16 in the top-left corner of each cell. The sequence depicts an escalating emotional journey from calm to extreme rage: - Panels 1-4: Neutral states. Panel 1 is blank-faced; Panel 2 is smiling; Panel 3 is annoyed/skeptical; Panel 4 is confused with a question mark. - Panels 5-8: Growing irritation. Panel 5 has hands on hips with anger marks; Panel 6 is gritting teeth; Panel 7 is shaking with clenched fists; Panel 8 is squinting in frustration. - Panels 9-12: Active anger. Panel 9 is leaning forward aggressively; Panel 10 is screaming with arms raised; Panel 11 is roaring with motion lines; Panel 12 is kicking the ground. - Panels 13-16: Peak rage and aftermath. Panel 13 has steam shooting from ears; Panel 14 has a red face and popping veins; Panel 15 is a monstrous scream with dark aura and debris; Panel 16 shows the character collapsed on the floor, exhausted and defeated. Style: Flat vector illustration, thick outlines, white background for each panel, consistent character design throughout.
{"type":"satirical collectible action figure packaging illustration","style":"retro toy blister pack mockup with gritty streetwear design, distressed cardboard backing, bold comic-style typography, highly legible packaging text, humorous anti-AI culture parody","subject":{"product_name":"AI HATER","product_type":"action figure","theme":"skeptical anti-hype tech critic parody toy","age_label":"AGES 14+","warning_label":{"title":"WARNING:","text":"MAY CAUSE PRODUCTIVITY AND ORIGINAL THOUGHT."},"burst_badge":"100% ORGANIC SKEPTICISM"},"figure":{"count":1,"appearance":"stylized male action figure with intentionally obscured face, standing with arms crossed inside blister packaging","outfit_count":5,"outfit_pieces":["black cap with white text 'THINK FOR YOURSELF'","black hoodie with white text 'CTRL+ COMMON SENSE'","blue distressed jeans with ripped knees and a side chain","black-and-white low-top sneakers","dark undershirt peeking from the hoodie"]},"layout":{"packaging_style":"vertical retail toy box with clear plastic blister window","sections":[{"title":"includes","position":"left-middle pink badge","count":1,"labels":["0 FAITH IN HYPE"]},{"title":"ACCESSORIES","position":"upper-right","count":5,"labels":["black mug reading 'HUMAN TEARS (FUEL)'","spiral notepad reading 'THINGS AI STILL CAN'T DO:' with 4 checklist items: 'BE FUNNY', 'HAVE SOUL', 'LOVE DOGS', 'GET SARCASM'","device reading 'TOUCH GRASS MODE' with a green 'ON' button","grumpy gray-and-white cat figure","sign on wooden stake reading 'PROMPT BETTER. BRO.'"]},{"title":"EXTRA HEADS","position":"mid-right lower than accessories","count":3,"labels":["extra head 1 with obscured face","extra head 2 with obscured face","extra head 3 with obscured face"]},{"title":"BONUS ITEMS","position":"bottom-right","count":3,"labels":["spray can reading 'BULLSHIT DETECTOR SPRAY' with small text 'APPLY DIRECTLY TO PROJECT'","pink brain labeled 'LAST WORKING BRAIN CELL'","metal trash can labeled 'AI SLOP'"]},{"title":"COLLECT THEM ALL!","position":"bottom center strip","count":5,"labels":["DOOMSCROLLER","CRYPTO BRO","INFLUENCER","CORPORATE NPC","YOU?"]},{"title":"mission","position":"bottom-right pink note","count":1,"labels":["KEEP HUMANITY FROM BECOMING BORING."]}]} ,"extra_graphics":{"count":2,"labels":["small illustrated portrait of the character in lower-left corner holding a speech bubble that says 'CRITICAL THINKING IS MY SUPERPOWER.'","black banner under title reading 'NOT ANTI-TECH. ANTI-BS.'"]},"color_palette":{"cardboard":"aged beige with grime and scuffs","accent_colors_count":3,"accent_colors":["hot pink","black","warning yellow"]},"composition":"front-facing product shot, centered figure on left half, accessories arranged in molded compartments on right half, bottom strip of collectible silhouettes, realistic toy packaging reflections and shadows, clean studio lighting"}
2x2 grid, 16:9, do this for 4 topics in the news this week: CLASSIFY(input) → {
domain: editorial_satire × pop_up_engineering × hybrid_2D_3D_diorama
intent: critique + delight + literalize (making abstract hypocrisy physically tangible)
audience: editorial readers, political cartoon consumers, art-toy collectors
platform: 4:5 vertical or 1:1 square, high-res digital spread, viral infographic
complexity: extreme (requires strict 2D/3D material separation, kinetic metaphor mechanics,
dense typographic integration, and ironic contradiction logic)
}
CORE DESIGN LAWS (IMMUTABLE):
⚠ THE INK IS FLAT. THE CLAY IS ROUND. THE JOKE IS PHYSICAL.
• Base: 2D B&W comic pages / printed guide (Matte, flat, hatched).
• Pop-Up: 3D miniature metaphor machine rising from the pages (Glossy/Clay, dimensional).
• Actors: Tiny 3D figures enacting the irony (Self-defeating, exaggerated).
• Annotations: Labels, bubbles, and signs bridging the 2D/3D gap.
• The Joke: The 3D action must physically contradict the 2D text.
SEMANTIC_VARIABLES (AI infers from {{SUBJECT}}):
{{SUBJECT}} → [e.g., Corporate Greenwashing, Social Media Outrage, Modern Dating]
{{METAPHOR_MACHINE}}→ [e.g., A PR Factory, A Treadmill of Validation, A Slot Machine of Swipes]
{{2D_BASE}} → [e.g., An open corporate manifesto, a self-help comic guide]
{{3D_MATERIAL}} → [e.g., Polymer clay, painted resin, papercraft]
{{CONTRADICTION}} → The core hypocrisy (Stated Intent vs. Actual Output)
{{ACTORS}} → Tiny figures trapped in or operating the machine
{{ANNOTATIONS}} → Blunt labels, warning signs, scoreboard stats
Using my uploaded photo as the primary facial reference, transform me into an outrageously exaggerated, hyper-realistic, classic children’s TV puppet-inspired trash-can creature while keeping my identity and recognizable facial features unmistakably intact. CHARACTER DESIGN: Enormous head, tiny upper body, narrow shoulders, short, skinny puppet-like arms, huge expressive eyes, heavy downward-slanting brown eyebrows, long bulbous green nose, and a pronounced grouchy frown. Cover my entire visible head, face, eyebrows, neck, and exposed upper body in vibrant, thick, shaggy green fur with individually defined strands, wild spiky tufts, unruly hair, and tactile, messy texture. Preserve my underlying facial structure and recognizable identity. Expression: comically irritated, judgmental, sarcastic, mischievous, and lovable—not frightening or monstrous. Slightly hunch my shoulders and lean my oversized head forward as if preparing a hilarious sarcastic one-liner. TRASH CAN AND ANATOMY: My upper torso, shoulders, and arms emerge directly from a classic, battered, open-topped cylindrical galvanized-steel trash can with a thick rolled rim. My entire lower body remains concealed inside. The can is upright, intact, separate from my body, and firmly resting directly on the sidewalk. Show its complete structure from rim to bottom base, including realistic dents, scratches, worn edges, subtle rust, metallic reflections, and a clear contact shadow. Absolutely no visible legs, feet, shoes, or body parts beneath, through, or outside the can. I am sitting inside it, not wearing it as a costume. No floating, hovering, sinking, or hidden visible limb support. ENVIRONMENT: A richly detailed residential neighborhood at nighttime on Halloween. Include charming suburban houses, glowing jack-o’-lanterns along the sidewalk and on porches, spooky decorations, artificial cobwebs, skeletons, bare tree branches, scattered autumn leaves, warm orange window and porch lights, purple and orange string lights, distant trick-or-treater silhouettes, and subtle drifting nighttime mist. Deep midnight-blue sky, soft moonlight, balanced warm pumpkin illumination and cool blue ambient lighting. Festive, quaint, whimsical, playfully spooky—not genuine horror. Keep the background softly focused and subordinate to my face. COMPOSITION: Vertical 2:3 portrait, three-quarter camera angle, slightly low perspective. Show the complete trash can from its upper rim to its fully grounded base, my entire visible upper body, oversized head, face, shoulders, and visible arms without cropping. Position the can prominently in the lower and central frame, with my expressive face as the primary focal point. Maintain a strong silhouette, clear separation between green fur, metal rim, and dark background, and enough surrounding scenery to establish the Halloween neighborhood. RENDERING: Premium cinematic CGI combining practical puppet craftsmanship with photorealistic 3D character artistry. Extraordinary tactile fur detail, layered shaggy eyebrows, realistic eye reflections, convincing facial and mouth anatomy, physically accurate weathered metal, and natural material textures. Use cinematic moonlight, warm pumpkin glow, subtle purple accents, global illumination, physically based materials, ambient occlusion, volumetric mist, delicate rim lighting, realistic contact shadows, and cinematic depth of field. Sharp facial details; softly blurred background.
Turn this photo into a chaotic funny doodle illustration, intentionally messy and low-skill, as if drawn quickly with a cheap marker, crayon, or worn-out felt pen on paper. Create exaggerated facial features with awkward proportions, uneven eyes, oversized head, tiny body, crooked smile, and clumsy anatomy while still keeping the person recognizable. Use rough childish sketch lines, shaky hand-drawn strokes, visible scribbles, overlapping outlines, accidental marks, and random doodles around the scene. Add a simple cartoon-style background with badly drawn buildings, trees, clouds, street elements, and uneven perspective. Coloring should look careless and imperfect, with visible stroke texture, inconsistent fill areas, wax crayon texture, marker bleed, and irregular shading. Include playful imperfections like crossed-out lines, unfinished details, random arrows, tiny notes, stars, swirls, and abstract scribbles. Overall aesthetic should feel humorous, spontaneous, handmade, energetic, goofy, and intentionally unpolished, resembling a child's sketchbook mixed with absurd internet meme art. High texture detail, paper grain visible, asymmetrical composition, awkward framing, expressive doodle chaos, raw sketch energy.
Ultra realistic vintage Indonesian catnip advertisement poster, retro 1970s paper texture, distressed print, faded colors. A black-and-white tuxedo cat wearing cute vintage housewife clothes floating happily in the air after smelling catnip, euphoric expression, swirling catnip leaves, absurd Indonesian meme energy. Bold retro typography: “BIKIN KUCING SENENG FLY!” fake catnip jar product, old-school badges, price tag, nostalgic warung advertisement aesthetic, cinematic lighting, grain, scratches, authentic aged poster look.
Ultra-realistic F1 live TV broadcast screenshot. A strikingly beautiful, 25-year-old young woman with bright light blue hair and captivating bright cerulean blue eyes is sitting in the VIP paddock / team garage during a Formula 1 race. Shown on the official live race broadcast as the girlfriend of an F1 driver, she is listening to the team radio through a professional racing headset. It is the final lap, and she is watching the garage monitors with a proud, enchanting smile. She wears a fitted white tank top, an oversized racing team jacket (with generic, unbranded or blank team logos) draped over her shoulders, large black team-radio headset with boom mic, gold jewelry, and soft glam makeup. A slim, unbranded paddock pass hangs naturally from her neck. Add realistic F1 broadcast graphics: "FINAL LAP" banner, lap counter showing final lap, driver timing tower on the left, small F1-style logo bug, "LIVE" indicator, and a lower-third identifying her as a driver partner / paddock guest (e.g., "MIA ANDERSEN - Paddock Guest / Partner"). No fake oversized badges, no selfie angle. Team staff (in generic kit), headsets, garage screens, and generic race equipment are blurred around her. Telephoto broadcast camera shot from across the garage, professional depth of field, compression artifacts, digital noise, bright paddock lighting, natural skin texture, no smoothing, 8k quality, cinematic lighting.
**STYLE AND VISUAL QUALITY** Premium modern Japanese anime film style, cinematic 2D animation quality, beautifully detailed Japanese character designs, expressive faces, soft cel shading, delicate linework, painterly backgrounds, realistic fabric folds, natural skin tones, rich atmospheric lighting, and emotional visual storytelling. The image should resemble a beautifully animated Japanese drama film, with warm cinematic lighting, rich colors, subtle depth of field, and emotionally powerful facial expressions. Avoid generic cartoon aesthetics, 3D rendering, or photorealism. **CHARACTER DESCRIPTIONS — MAINTAIN THESE EXACT APPEARANCES** **WIFE (Late 20s):** A beautiful young Japanese woman, approximately 27 years old, with fair warm-toned skin, a delicate oval face, large expressive dark-brown eyes, straight dark eyebrows, a small natural nose, and soft feminine facial features. She has long, silky, dark-brown hair reaching the middle of her back, styled with soft face-framing strands and a simple half-up hairstyle. She wears an elegant, modest, dusty-rose pink knitted cardigan over a cream-colored blouse, paired with a flowing sage-green midi skirt. Her appearance is graceful, gentle, and slightly delicate. Her large expressive eyes should communicate intense emotional pain, vulnerability, and quiet dignity. **HUSBAND (Early 30s):** A handsome Japanese man, approximately 32 years old, with fair-to-medium warm skin, short neatly styled black hair, dark-brown eyes, straight eyebrows, a clean-shaven face, and a defined but natural jawline. He wears a slate-blue button-up shirt with a cream-colored undershirt, dark tailored trousers, and a simple silver wristwatch on his left wrist. Average-to-tall height, lean-to-medium build, attractive but realistic anime facial proportions. His personality should be reflected through subtle, emotionally expressive reactions. **MOTHER-IN-LAW (Late 50s):** A Japanese woman, approximately 58 years old, with fair-to-medium warm skin, a slightly rounded face, visible fine wrinkles around her eyes and mouth, sharp eyebrows, narrow expressive dark-brown eyes, and a stern, authoritative appearance. Her dark hair, lightly streaked with gray, is neatly arranged in an elegant low bun. She wears a sophisticated deep-maroon Japanese kimono with subtle gold floral embroidery, a cream-colored obi belt, and a traditional decorative hairpin. Her posture and facial expressions communicate pride, authority, harsh judgment, and a controlling personality. **SETTING — JAPANESE NEW YEAR FAMILY DINNER** Inside a beautiful, cozy, traditional-modern Japanese family home during an Oshōgatsu (Japanese New Year) celebration in the evening. A long, low polished wooden dining table dominates the tatami-mat room. The table is covered with a generous Japanese New Year feast, including: - Beautifully arranged osechi ryōri in traditional lacquered jubako boxes. - Grilled fish served on ceramic plates. - Ozōni soup in traditional bowls. - Sushi and neatly arranged sashimi. - Decorative mochi and traditional Japanese sweets. - Elegant ceramic teacups and wooden chopsticks. The room features authentic Japanese interior design: warm wooden beams, shoji paper sliding doors, tatami flooring, a decorative tokonoma alcove, a traditional flower arrangement, and soft hanging lanterns. Through a partially open shoji door, a peaceful Japanese garden is faintly visible beneath the evening sky. Warm golden interior lighting creates a beautiful festive atmosphere. The peaceful New Year celebration contrasts sharply with the painful family confrontation unfolding around the table. **MAIN SCENE — PUBLIC HUMILIATION AT THE FAMILY DINNER** Capture a deeply emotional and dramatic moment at the exact instant a family celebration turns into a humiliating confrontation. The mother-in-law sits at the head of the low Japanese dining table, leaning forward aggressively. She points her index finger directly toward her daughter-in-law. Her expression is harsh, mocking, and judgmental. Her mouth is slightly open as if she has just delivered a cruel, insulting remark in front of everyone. The young wife stands beside the dining table, holding a beautiful ceramic serving platter with both hands. She looks completely shocked and humiliated. Her shoulders are tense, her lips slightly parted, and her large brown eyes are filled with tears she is desperately trying to hold back. Her cheeks are faintly flushed with embarrassment. Her expression communicates heartbreak, helplessness, and the unbearable pain of being publicly disrespected in front of her husband's entire family. The husband sits on a floor cushion beside his mother. He suddenly looks up with a frozen, stunned expression. His body is tense, his eyes widened in disbelief, as though he cannot believe what his mother has just said to his wife. Capture the precise moment before he decides whether to speak. **SIX ADDITIONAL FAMILY MEMBERS** Six adult Japanese relatives sit on floor cushions around the table. The men wear a mixture of elegant casual shirts, sweaters, and traditional Japanese clothing. The women wear tasteful modern outfits or subtle traditional kimono. All six relatives have turned their attention toward the young wife. Some look visibly shocked. Others exchange uncomfortable glances. One elderly relative lowers their eyes in embarrassment. Another relative watches the confrontation with a judgmental expression. Their reactions should amplify the wife's painful realization that everyone has witnessed her humiliation. **EMOTIONAL VISUAL STORYTELLING** The mother's aggressive pointing gesture, the wife's devastated expression, the husband's stunned reaction, and the relatives' uncomfortable stares must immediately communicate the entire conflict without any written dialogue. The viewer should instantly understand: A young Japanese wife has just been publicly insulted by her mother-in-law during an important family celebration, and everyone is waiting to see whether her husband will defend her. **CAMERA AND COMPOSITION** Portrait 4:5 aspect ratio. Final resolution: 1080 × 1350 pixels. Cinematic medium-wide shot at a natural eye-level camera angle, carefully framed to emphasize the emotional tension between the three main characters. The composition should resemble a dramatic freeze-frame from a premium Japanese animated feature film. **CRITICAL COMPOSITION RULE — TEXT OVERLAY SPACE** The entire dramatic scene must occupy only the UPPER 55% of the image. This includes: - All important character faces. - The mother-in-law's pointing gesture. - The wife's shocked expression. - The husband's frozen reaction. - The relatives' uncomfortable stares. The LOWER 45% of the image must remain a clean, darker, visually calm, uncluttered foreground. Use the near section of the low wooden dining table, softly shadowed tatami flooring, and subtle atmospheric shadows to create this negative space. Do not place important faces, hands, food plates, or distracting decorations in the lower 45%. Create a natural transition from the detailed dramatic scene above into the quieter, darker foreground below. The bottom area must be suitable for adding large, highly readable text overlays later. **LIGHTING AND MOOD** Warm golden Japanese lantern lighting. Soft cinematic interior illumination. Subtle shadows and atmospheric depth. Beautiful highlights on expressive anime eyes. Detailed painterly Japanese interiors. Rich but natural color grading. The emotional atmosphere should feel: Heartbreaking, tense, humiliating, uncomfortable, dramatic, and deeply human. The beautiful peaceful Japanese New Year setting should contrast strongly with the cruelty of the family confrontation. **STRICT REQUIREMENTS** - Generate ONE single cinematic anime illustration. - Portrait 4:5 aspect ratio, 1080 × 1350 pixels. - Premium Japanese animated film quality. - Consistent character anatomy and natural body proportions. - Beautiful expressive faces with accurate hands and fingers. - All characters must have Japanese facial features and styling. - The wife must wear her dusty-rose cardigan and sage-green skirt. - The husband must wear his slate-blue shirt and silver wristwatch. - The mother-in-law must wear her deep-maroon kimono with cream obi. - Preserve the emotional intensity of the confrontation. - Concentrate all important storytelling in the upper 55%. - Reserve the lower 45% for future text overlays. - No text. - No letters. - No speech bubbles. - No subtitles. - No captions. - No logos. - No borders. - No watermarks. - No 3D rendering. - No CGI. - No photorealism.
A photorealistic humorous academic presentation in a conference room: an anthropomorphic otter scientist stands at the left side of the frame wearing a crisp white lab coat and holding a thin pointing stick toward a large presentation board on an easel. The otter is upright like a human, with realistic brown fur, dark paws, and a professional posture. The lab coat has a stitched name tag reading "Dr. Otter" and a smaller line reading "Aquatic Systems Lab," plus two pens in the chest pocket. The otter’s face is partially censored by a square blur block. Behind the otter is a whiteboard with faint handwritten notes and doodles, including "WiFi > Fish," "H2O," "Hydration," a fish sketch, and a wifi symbol. The main focus is a large clean presentation slide with sharp readable text and polished corporate-academic layout. At the top, a bold title reads "Ethan Mollick’s Otter Test" and beneath it a subtitle reads "Prompt: \"An otter sitting on an airplane seat using in-flight wifi on a laptop\"". Below that is a boxed section titled "Sample AI-Generated Images" containing exactly 4 side-by-side sample images of a realistic otter seated in an airplane seat using a laptop or tablet, each framed like model outputs, with one showing a large wifi symbol above the seat. Beneath the images is a section labeled "Performance Results (Pass = otter, airplane seat, in-flight wifi, laptop/tablet)" with exactly 5 score boxes: "DALL·E 3" with no visible numeric score, "GPT-4o" with "4/4" and "100%", "Midjourney v6" with "3/4" and "75%", "Stable Diffusion XL" with "2/4" and "50%", and "SD 1.5" with "0/4" and "0%". On the right side is a large highlighted box reading "Average Score" and "70%" in large blue type. At the bottom of the slide is a "Key Findings" box with exactly 3 bullet points: "Modern models understand complex, specific prompts surprisingly well.", "Otters + airplanes + wifi = a reliable benchmark.", and "Further research is otter-ly necessary." A small simple cartoon otter doodle appears in the lower-right corner of the slide. The room is warmly lit with wood-paneled walls, shallow depth of field, and a few blurred audience members in the foreground, including a laptop at the bottom edge showing an otter image on its screen and a glass pitcher on a table. Style: ultra-realistic editorial photography, deadpan scientific satire, believable conference presentation, high detail, natural indoor lighting, professional lens compression, readable slide typography, polished yet absurd.
Frequently asked questions
How do I add the caption text?
Generate the base image first — most of these prompts leave room for text on purpose. Then add the caption in any editor (or ask the image model to render short text, which now works reliably for a few words). Classic Impact-style top/bottom text is added after generation, not inside the prompt.
Which formats are easiest to start with?
Sticker packs and expression progressions: one prompt yields a whole set of reactions in a consistent style — the highest hit-rate per generation. Redraw formats (“MS-Paint version of X”) need a reference image but get laughs with almost no tuning.
Can I make a meme of a specific character or photo?
Yes — use the image-edit prompts and supply the source frame. Keep the description of the subject generic (“the character in the image”) so the model applies the format instead of inventing a new subject.
Where do these meme prompts come from?
They are curated from public prompt showcases with the original posts linked on each card. Formats riff on well-known meme conventions; the prompts themselves are short functional texts you can adapt freely.