102 copy-paste prompts, each labelled with what it demonstrates
102 worked prompt fragments across 4 media, each labelled with the technique it demonstrates. Take the shape, replace the subject. Free PDF at the bottom, no sign-up.
The problem
Prompt lists on the internet are unlabelled. You get a wall of text that worked once, for a model that may not be the one you are using, with no indication of which part mattered.
What this gives you
Every line here says what it is demonstrating — a camera move, a negative rewritten as a positive, a music cue's structure — so you can take the technique and not just the sentence.
Video
- camera dollies incamera movement
- cinematic handheld shot, neon rainy streetcamera movement + setting
- subtle product reveal, camera slowly pulls back, ambient motioncamera movement + subject motion
- non-photorealistic, illustrated, not a photo, no live-action, no realismstyle descriptor tail
- flat 2D vector animation, bold clean outlines, solid vibrant flat fills, no shading, no gradientsSTYLE descriptor
- hand-inked black marker on off-white paper, solid jet-black fills, thin white scratch highlights, marker grain, strictly monochromeSTYLE descriptor
- strict monochrome minimalism, black silhouettes on white void, high contrast, lots of negative spaceSTYLE descriptor
- hand-painted storybook gouache, soft textures, warm muted palette, visible brush strokesSTYLE descriptor
- Block N STYLE REFERENCE: Match the attached reference image EXACTLY. Replicate its look precisely: {STYLE tokens}. Every element below rendered in that identical style. SCENE: {scene and one clear action matching Block N narration}. MOTION: {camera move and animation behavior, slow push-in, drift, scale shock, hard contrast cut}. AUDIO: {ambient SFX or music only, NO voice, dialogue, or narration}. NEGATIVE: color drift, photorealism, 3D render, lip-sync, captions, on-screen text, logos, watermark{, plus style-specific bans}.full block template
- MOTION: Very slow push-in; the figure erodes grain by grain and particles drift sideways.camera movement + subject motion
- NEGATIVE: color, gray midtones, photorealism, 3D render, lip-sync, captions, on-screen text, logos, watermark.negative block
- Premium 5-second motion cover reveal, smooth cinematic easing. The scene starts WITHOUT any text or plates: [SCENE AT START + CONTEXT MOTION, e.g. "the fluffy lime creature slowly rotates, its fur rippling in the light, stars drifting"]. Then the title "[TITLE TEXT]" [ENTRANCE MOTION matched to its typography], the tagline fades up beneath it, and the small rounded pill button slides in with a soft bounce. All elements ease precisely into their final positions and the video ends exactly on the provided end frame, holding still for the last moments. Subtle camera push-in, no flicker, no extra text, no new objects.full reveal template
- The solid color frame, corner dots and capsule shape stay perfectly static at all times.static-element lock
- no cuts, no camera shake, slow steady motion only, locked exposure, no on-screen textfootage contract
- START state ≠ END state, or the scrub has no payoff.resolving ends
- push-in + rack focus soft to sharp, subject turn/eyes to camera, light sweep, object assemblingcamera movement menu
- camera locked, no camera movement, no zoom, subject stays fully in frame, plain static backgroundcamera lock negative
- the character performs ONLY this action, nothing else happensaction inertia negative
- the <prop> stays inert and is never used, no firing, no muzzle flash, no swinging, no raising itprop inertia negative
- the subject keeps facing the SAME direction for the entire video, never turns around, never rotates toward or away from the camera, no head turns past the shoulderfacing lock negative
- smooth idle breathing cycle, subtle weight shiftone-action motion
- single sword slash, fast wind-up, sharp strike, follow-throughone-action motion
- make the jacket redvideo edit instruction
Image
- a red fox curled in a snowy pine forest, golden hour, cinematicsubject + setting + style
- transform into anime style, vibrant colors, soft cel shadingimage-to-image edit instruction
- Pure {STYLE} STYLE REFERENCE plate. No characters, no faces, no people, no objects, no scene, no letters, an abstract style swatch only. A balanced arrangement that demonstrates the rendering grammar clearly: {line quality}, {fill behavior}, {highlight/edge behavior}, {texture/grain}. {palette constraint, with hex if strict}. High contrast, clean background, generous negative space. Flat, raw, hand-illustrated, non-photorealistic. No text, no logos, no watermark.style-key swatch template
- {STYLE}. Full-body character: {HOST}, a {species/persona} narrator, expressive, clear readable silhouette, looking at camera, centered, simple background. Recurring-character design. No text, no logos, no watermark.mascot style-key template
- Make an Animated Explainer. Take only the visual render style and color grading of the input image(s); mix the styles if there is more than one image. Never use the characters, inscriptions, etc. from the input image(s) unless the instructions below ask you to. Use only the render style, and follow the user's instructions below:style-reference prefix
- Bold, punchy YouTube-thumbnail composite, poster-grade, photoreal and high-impact, NOT a muted cinematic movie still, <ratio>, single unified frame, no split-screen, no diagonal divide, everything blends smoothly and organically across the same continuous shot.frame block
- No text, no readable UI labels, no watermark.text policy default
- TEXT: bold thumbnail headline text baked into the image, reading exactly "<TEXT>", massive, ultra-legible sans-serif with a clean outline/glow treatment, placed where it never covers the subject's face. No other text, no watermark.baked headline
- All faces crisply sharp as the anchors of the shot.subject sharpness
- signature YouTube thumbnail lighting rig, strong key light sculpting the face, soft dreamy fill lifting shadows, and defined back light plus hair light tracing a clean bright rim around hair, shoulders and silhouette.lighting setup
- CHARACTER N: the person from attached face reference #K, IDENTITY LOCK: reproduce this exact person with a photographic identity match, same bone structure, eye shape, nose, lips, jawline, skin tone, hairline and hair texture. Do not beautify, average, or restyle the face. Expression: <emotion phrase>.identity lock
- IMAGE REFERENCES: image 1 = CHARACTER 1 face reference; image 2 = brand logo.reference manifest
- Transform the attached 2D logo into a premium 3D logo render: extrude the exact logo shapes into glossy dimensional volumes; preserve every letterform, proportion and brand color; soft studio reflections, subtle bevels, crisp edges, clean dark neutral background, soft contact shadow, centered, generous margins, no extra text, no watermark.3D logo render
- Change ONLY the person's facial expression to: <phrase>. Keep identity, face structure, hair, pose, body, clothing, logo, background, lighting and composition EXACTLY unchanged, pixel-faithful. Keep the YouTube thumbnail lighting rig intact.surgical edit
- a film editor in a bold red bomber jacket mid-leap, cutting a giant arc of 35mm film with oversized chrome scissorssubject + action
- waist-up, subject fills two thirds of the frame, positioned right-of-centerscale + placement
- soft open negative space upper-left on a warm white wallreserved negative space
- bright soft key with punchy shadows, low wide angle, commercial editorial gradelight + lens
- no text, no letters, no logos, no captions, no UInegative tail
- icon set, consistent 2px-stroke line glyphs, [motifs], flat on solid background, no texticon-set prompt
- seamless repeating patterntileable pattern
- website design mockup, desktop landing page section, [SECTION ROLE], [theme paradigm + exact palette words], [typography character] typography, [hero architecture / composition anchor], [background mode], [narrative spine motif], professional layout, clear hierarchy and spacing, award-winning web designdesign board recipe
- no watermark, no browser chromenegative tail
- flat vector cartoon, deep violet dungeon palette, glowing teal accents, warm amber torchlight, thick dark-plum outlinesSTYLE TOKEN
- environment in deep violet stone with charcoal shadows, hero in warm coral-cream tones contrasting the surroundings, hazards and pickups marked with acid-green glowpalette by role
- rounded blobby shapes with thick dark-plum outlinesshape and line language
- moody but playful underground atmosphere, flat ambient lightlight and mood
- high contrast between game elements and backgrounds, clean readable silhouettes, consistent side-view perspective across all assetsgame-readability
- game sprite of <description>, single character/object, full body visible, centered,sprite kind template
- , on a solid uniform bright <KEY COLOR> background, no shadows cast on the background, no ground plane, nothing cropped at the edgessprite kind suffix
- seamless tileable game texture tile of <description>, uniform pattern density,tile kind template
- , perfectly seamless edges that wrap horizontally and vertically, no border, no vignette, flat even lighting, no single focal objecttile kind suffix
- game background of <description>, wide establishing view,background kind template
- , no characters, no UI elements, slightly muted detail so foreground game elements stay readable, soft depth layeringbackground kind suffix
- seamless tileable surface texture of <description>,texture kind template
- , perfectly seamless edges, flat even lighting, no perspective, no objects, photographed-flat appearancetexture kind suffix
- game UI element: <description>, single element, centered,ui kind template
- , on a solid uniform bright <KEY COLOR> background, crisp edges, no drop shadow outside the elementui kind suffix
- <STYLE FORMULA>. <single key-pose instruction>. Full body in frame with empty margin above the head and below the feet. Clean uniform <key color> background.key-pose prompt
- Reproduce the attached image as faithfully as possible: the SAME {MATERIAL}, same colors, same lighting, same shapes and detail, pixel-level similarity everywhere possible. Only make the MINIMAL adjustments needed so the image becomes a perfectly seamless tileable texture: the left edge must continue into the right edge and the top edge into the bottom edge with no visible seam when tiled. Do not restyle, do not add or remove elements, do not change colors or scale. Square 1:1.seamless edit
- hand-painted cracked dry earth with small grey stones{MATERIAL} example
- The repeating units must be aligned so rows continue across the tile borders: unit boundaries at the left edge continue into the right edge and across top/bottom.structured-material add-on
- Reduce the visible periodic repetition of distinctive features so the pattern feels organic.anti-repetition add-on
- Remove any watermark text.stock-image add-on
- This {MATERIAL} game texture is damaged along a vertical line and a horizontal line through the center: some pattern elements there are faded, semi-transparent, streaky or cut in half. Replace every damaged element with a brand-new complete one painted in the exact same crisp style: fully opaque, sharp confident strokes, same element size, same colors. No blur, no soft transparent elements, no smoothing - the repaired area must be indistinguishable in sharpness and detail from the rest of the image. Keep everything outside the damaged lines unchanged. The final image must be a perfectly seamless tileable texture: the left edge continues into the right edge and the top edge continues into the bottom edge with no visible seam when tiled. Flat even lighting, no shadows, no vignette.offset-inpaint pass
- [CREATE ONE FINISHED BRANDED MOCKUP] <specific object/application, credible setting, camera, material, lighting, composition, and one brand-specific art-direction idea>mockup scene block
- [AUTHORITATIVE LOGO] <ImageN> is the exact approved <full-color/black/white> logo. Preserve its spelling, silhouette, geometry, proportions, internal negative space, and exact color. Do not redraw, simplify, crop, stretch, outline, or add effects.logo preservation block
- [PLACEMENT LOCK] Target surface: <exact object panel/face/material>. Position: <exact alignment and location, e.g. horizontally centered, upper third, optical center aligned to panel>. Scale: logo occupies <specific proportion> of the target surface while keeping <specific clear-space margin>. Orientation: align to <panel edge/seam/baseline>; follow surface perspective without changing logo proportions. Color: use the supplied <full-color/black/white> variant exactly. State why it contrasts correctly with the material/background.placement lock block
- [PHYSICAL APPLICATION] Render the logo using <credible print/emboss/foil/engraving/ink behavior>. Respect folds, grain, perspective, occlusion, reflections, scale, and manufacturing limits.material application block
- No extra logos, pseudo-text, invented labels, warped marks, floating print, unrelated props, arbitrary gradients, plastic sheen, or generic luxury staging.mockup negative tail
- [BRAND LOCK, DO NOT DEVIATE] Brand spelling: <exact> Authoritative logo: <reference index/id and preservation instruction> Palette: <exact hex + role> Typography: <exact font/style when rendered> Layout: <grid/alignment/spacing> Shape language: <radius/border/forms> Graphic device: <motif/pattern rule> Must preserve: <fixed invariants> Never: <forbidden treatments>brand lock prompt block
- Image 1: official logoreference labelling
- Flat vector design, clean lines, no shadows, no texture, no text. Clean editable vector paths, SVG-friendly, minimal anchor points.flat_vector constraint tail
- Monoline vector design, uniform stroke weight, rounded line caps, no fills, no shadows, no texture, no text. Clean editable vector paths, SVG-friendly, minimal anchor points.monoline constraint tail
- Flat vector design with the specified locked vector gradient, no shadows, no texture, no text. Clean editable vector paths, SVG-friendly, minimal anchor points.vector_gradient constraint tail
- Intentional hand-drawn vector strokes, approved surface variation, clear scalable silhouette, no shadows, no text.hand_drawn_vector constraint tail
- locked primary tonepalette role language
- mark type to central subject/mechanism to shape logic to style register to palette behavior to composition to constraint tailprompt order
- Reference: User specifically likes: Palette behavior: Typography character: Composition/grid: Shape/material language: Overall mood: Do not copy:reference description template
- brief, generic subject pose/action, elements, location, composition, background, split (true/false), split_count, person_count, emotion, emotion_detailreference-thumbnail extraction template
- bottle of cold-brew on a sunlit kitchen counter, IG feedshort intent line
- vertical pin for my candle brand, cottagecore moodshort intent line
- Christmas version, quiet-luxury aestheticrestyle intent line
- founder using product in 5 distinct IG-feed scenes: morning coffee setup, desk workspace, outdoor café, gym, home officemulti-variant intent line
- premium skincare serum, clean clinical marketplace visual systemshort intent line
- anime character concept, expressive posecharacter prompt
- neon city at duskscene prompt
Audio
- AUDIO: Low sustained drone and a soft whisper of falling sand, no voice.diegetic clip audio
- short isolated sword impact, dry studio recording, no musicSFX prompt
- instrumental cozy forest loop, warm marimba and soft strings, no vocalsmusic prompt
- single heavy wooden door slam, close microphone, no ambienceSFX prompt
- The gate is open. Move!voice line
- cinematic rain ambience with distant thunderambience prompt
- cinematic synthwave trackmusic prompt
- glass breaking in a large hallSFX prompt
- same voice, calmer deliveryvoice reference edit
- For four and a half thousand years, the pyramids of Egypt have stood against the desert, silent and immense.narration line
Any medium
- Instead of "no blur" to "tack sharp"positive phrasing of negatives
- Instead of "no people" to "uninhabited landscape"positive phrasing of negatives
Free, no sign-up, no email
All 102, as a PDF
Every entry on this page, in the same order, over 2 printable pages. Nothing is trimmed to make it fit — the count in the title is the count in the file.
Common questions
Can I just copy AI prompts from the internet?
You can, and research says most people learn this way — a three-month study of text-to-image communities found practitioners control output with short phrases they collect from each other. The trap is copying a prompt without knowing which clause did the work, which is why each line here is labelled.
Do prompts transfer between models?
The structure does, the vocabulary partly. Naming a decision clearly works everywhere. A specific style phrase tuned to one model can do nothing on another, so treat these as shapes to fill rather than strings to paste.
Where this comes from, and what to read next
This page is a list. It does not explain the material — Prompt craft does, group by group, with what each decision controls and why. Research on how people actually prompt is collected under how people really use AI.