Vol. 1 · The AI Prompt Library Free · No signup · Copy & paste

Prompt Library

For Image Generators

AI Image Prompts

Copy-ready text-to-image prompts for Midjourney, Stable Diffusion (SDXL), GPT Image (ChatGPT), FLUX and Firefly. Each one has fill-in variables for subject, style and lighting — and an example of what it produces.

A great image prompt is built, not guessed. The prompts below give the model what it actually needs — the subject, a lens or medium, a lighting setup, and a colour or style direction — instead of a vague one-liner that returns generic AI art. They cover the jobs people reach for image generators to do: cinematic and professional portraits, clean product, lifestyle and food shots, sweeping landscapes, interiors and architecture, stylized anime, 3D, pixel-art and picture-book characters, posters, stickers, tattoo flash and printable coloring pages, and logo or app-icon concepts. Every prompt uses [BRACKETED] placeholders you can fill in right on this page before you copy.

These work across the major text-to-image tools, with small differences. Midjourney reads flags like --ar (aspect ratio) and --style raw; Stable Diffusion / SDXL and FLUX set aspect ratio in their own UI, so you can drop the flags; GPT Image (the image model in ChatGPT, which replaced DALL·E) and Adobe Firefly take the same plain-English description without flags. Each card lists the tools the prompt suits best. Copy one, swap in your details, and treat the result as a strong first draft to iterate on.

27 prompts · free to copy · example output on each

MidjourneySDXLFLUX

Cinematic close-up portrait

A film-still style headshot with controllable subject, mood and lighting.

The prompt 4 fields to fill
cinematic close-up portrait of ,  expression, shot on 85mm f/1.4 lens, shallow depth of field with creamy bokeh,  lighting,  color grade, fine skin texture and catchlights in the eyes, photorealistic, 35mm film grain --ar 4:5 --style raw
Example output
A tight head-and-shoulders portrait of a weathered fisherman in his 60s, a faint knowing smile, lit by warm low-key window light from the left that falls off into shadow on the right cheek. The teal-and-amber grade and visible film grain read like a frame pulled from an indie drama; the eyes are sharp with twin catchlights while the background dissolves into soft bokeh.

TipSwap in any subject and keep the lens + lighting + grade scaffolding — that trio is what makes it read as a cinematic still rather than a generic AI face. On Midjourney, `--style raw` reduces the over-polished default look; in SDXL/FLUX drop the `--ar/--style` flags and set aspect ratio in the UI.

MidjourneyFLUXFirefly

Editorial fashion portrait

A magazine-style full-look shot with styling, set and lens control.

The prompt 6 fields to fill
full-length editorial fashion photograph of  wearing , styled for a  editorial, posed , shot on medium format, ,  backdrop, high-end retouching, sharp fabric detail, fashion-magazine composition with negative space for text --ar 4:5
Example output
A model in an oversized scarlet wool coat stands three-quarters to camera against a seamless concrete-grey backdrop, weight on the back foot, chin slightly down. A large softbox from camera-right wraps the face and rim-lights the shoulder; the coat's texture and stitching stay crisp. The off-centre framing leaves clean space at the top — exactly where a cover line or masthead would sit.

TipNaming a real publication or brand aesthetic (e.g. "Kinfolk", "Vogue Italia", "an Aesop campaign") steers wardrobe, palette and grain far more reliably than the word "editorial" alone. Keep the negative-space note if you plan to drop in a headline later.

FLUXSDXLGPT Image

Professional headshot for LinkedIn

A clean, approachable corporate headshot you can use as a profile photo.

The prompt 4 fields to fill
professional corporate headshot of ,  years old, wearing , warm genuine smile, soft three-point studio lighting, neutral  background with gentle gradient, eyes in sharp focus, natural skin tones, shot on 85mm lens, head and shoulders, LinkedIn profile photo, photorealistic --ar 1:1
Example output
A square, chest-up headshot of a woman around 35 in a charcoal blazer, smiling naturally with relaxed eyes. Even, flattering studio light removes harsh shadows; the soft grey-blue gradient backdrop keeps all attention on the face. Skin looks real (pores and subtle texture, not plastic), and the 1:1 crop drops straight into a profile slot.

TipKeep lighting "soft three-point" and the background a plain gradient — that is what separates a hireable headshot from an obvious AI render. If a tool warps the eyes or teeth, regenerate rather than upscaling a flawed frame; faces are where artifacts show most.

MidjourneyFLUXFirefly

Studio product shot on seamless background

A clean e-commerce hero shot of a single product with crisp light.

The prompt 2 fields to fill
professional studio product photograph of , centered on a seamless  background, soft even softbox lighting with a subtle gradient, gentle reflection beneath the product, crisp focus edge to edge, true-to-life color, high-resolution commercial product photography, ample negative space --ar 1:1
Example output
A matte-black insulated water bottle stands dead-centre on a seamless pale-grey sweep. A broad softbox gives an even highlight down one side with no blown reflections, and a faint mirror reflection grounds it on the surface. Edges are tack-sharp, the colour is accurate, and the surrounding empty space leaves room for a price badge or logo.

TipFor a packshot you can drop onto a website, "seamless background + subtle reflection + negative space" is the reliable recipe. Generate on a light background first — it composites onto store pages and ads far more easily than a busy scene.

MidjourneyFLUXFirefly

Product in a lifestyle scene

Show a product in a real-life context to make an ad or social post feel human.

The prompt 5 fields to fill
lifestyle product photograph of  being used in ,  interacting with it naturally,  natural light streaming in, shallow depth of field keeping the product in focus, warm inviting  mood, candid commercial photography, props and styling that suit the scene --ar 4:5
Example output
A ceramic pour-over coffee dripper sits on a sun-washed wooden kitchen counter as a pair of hands slowly pours from a gooseneck kettle. Late-morning light rakes across the steam; a linen napkin and a single mug sit softly out of focus behind. The product is the sharpest thing in frame, but the scene feels lived-in rather than staged.

TipLifestyle shots convert because they show use, not just the object. Name the setting, the time of day and one or two props — over-describing the background tends to push the product out of focus or make the scene look cluttered.

MidjourneyFLUXGPT Image

Flat-lay / knolling top-down arrangement

A neatly arranged overhead shot of related items for social or packaging.

The prompt 3 fields to fill
top-down flat-lay photograph of , knolling arrangement with everything aligned at right angles and evenly spaced, on a  surface, soft diffused overhead lighting with minimal shadows, consistent color palette of , organized and minimal, high detail --ar 1:1
Example output
A perfectly overhead shot of a traveller's desk kit — passport, brass compass, folded sunglasses, a notebook and a pen — each object squared to the grid and evenly spaced on a warm oak surface. Diffuse top light keeps shadows faint and even. The muted tan-and-brass palette ties the unrelated objects into one cohesive composition.

Tip"Knolling" is the keyword that triggers the precise right-angle alignment; without it you get a messy pile. Keep the item list to 5–9 things and lock a 2–3 colour palette so the arrangement looks curated rather than random.

MidjourneyFLUXSDXL

Sweeping landscape at golden hour

A wide, atmospheric nature scene with controllable place, weather and light.

The prompt 2 fields to fill
sweeping wide-angle landscape photograph of , , golden-hour light with long shadows and warm rim lighting on the terrain, layered foreground midground and background for depth, shot on 16-35mm lens, high dynamic range, crisp detail, natural color, photorealistic --ar 16:9
Example output
A wide vista over misty Scottish highlands just after sunrise: heather-covered foreground rocks lead into a fog-filled glen, with backlit ridgelines stacking into the distance. Low golden light rims the hilltops and stretches long shadows across the valley. The layered foreground-to-background staging gives the frame real depth, like a landscape-photography portfolio shot.

TipGolden-hour + a named location + "layered foreground/midground/background" is what produces depth instead of a flat postcard. For prints or desktop wallpaper keep 16:9; for phone wallpaper switch to `--ar 9:16` and the model will re-stage the composition vertically.

MidjourneyFLUXFirefly

Interior architecture / room render

A magazine-quality interior in a chosen style for mood boards or mockups.

The prompt 4 fields to fill
architectural interior photograph of a  in  style,  materials,  palette, large windows with soft natural daylight, considered furniture layout, realistic global illumination and soft shadows, wide architectural lens with corrected verticals, interior-design-magazine quality --ar 3:2
Example output
A Japandi living room: pale oak floors, a low linen sofa, a single arched floor lamp and a clay-toned rug. Floor-to-ceiling windows wash the space in soft daylight that bounces realistically off the matte walls. Vertical lines stay straight (no lens distortion), and the restrained beige-and-charcoal palette gives it the calm of an interiors-magazine spread.

TipName the design movement (Japandi, mid-century modern, brutalist, art deco) plus materials and palette — those three do most of the work. "Corrected verticals / architectural lens" stops the warped-wall look that instantly reads as a fake render.

MidjourneySDXLFLUX

Concept-art environment / matte painting

A cinematic world-building scene for games, film or storyboards.

The prompt 4 fields to fill
epic concept art environment of ,  with  atmosphere,  mood, dramatic cinematic lighting and god rays, sense of vast scale with a small figure for reference, painterly matte-painting style, intricate detail in the foreground, atmospheric depth haze, trending on ArtStation --ar 21:9
Example output
A colossal overgrown ruin half-swallowed by jungle at dawn: vines spill down weathered stone arches, mist pools between the pillars, and shafts of light cut through the canopy. A lone explorer at the base — tiny against the architecture — sells the scale. Foreground ferns are richly detailed while distance fades into blue atmospheric haze, the look of a film pre-production matte painting.

TipA small human or animal "for scale" is the single most effective trick for conveying epic size. The ultra-wide `--ar 21:9` reinforces the cinematic feel; "atmospheric depth haze" adds the layering that makes a matte painting feel deep rather than pasted.

SDXLMidjourneyFLUX

Anime-style character illustration

A clean cel-shaded character with controllable look, outfit and palette.

The prompt 6 fields to fill
anime-style character illustration of , wearing , , expressive  face, clean cel shading with crisp lineart, vibrant  palette, detailed eyes and hair highlights,  background, high-quality key visual, studio anime aesthetic --ar 2:3
Example output
A young swordswoman in a deep-blue haori mid-stride, sword drawn, hair caught in motion. Bold clean lineart and flat cel shading with sharp highlight bands; large, detailed eyes catch the light. A soft blurred cherry-blossom street sits behind her in muted complementary tones, framing the figure like an anime key visual.

TipFor consistent character art, lock the palette and hair/eye descriptors and reuse them across generations — they are the features the model drifts on most. SDXL with an anime-tuned checkpoint gives the cleanest cel shading; on Midjourney add a style reference image with `--sref` to pin a specific anime look.

MidjourneyGPT ImageFLUX

Cute 3D-render character (Pixar-style)

A glossy stylized 3D mascot or character for apps, stickers or branding.

The prompt 4 fields to fill
adorable stylized 3D character render of , big expressive eyes,  expression, soft rounded shapes, subsurface-scattering skin, smooth matte-and-glossy materials, soft studio lighting with gentle rim light,  palette, clean  background, Pixar / Blender Cycles style, high detail --ar 1:1
Example output
A chubby cartoon fox with oversized sparkling eyes and a shy grin, modeled in soft rounded forms with believable fluffy-fur shading. Gentle studio light plus a cool rim light separates it from the pastel-mint background. The matte body and tiny glossy nose read like a polished Pixar still — ideal as an app mascot or sticker.

TipWords like "subsurface scattering", "soft rim light" and "Blender Cycles" are what give the render that expensive studio-3D finish instead of a flat cartoon. Keep the background a single clean colour so the character cuts out cleanly for stickers or UI.

SDXLFLUXGPT Image

Watercolor illustration

A soft hand-painted watercolor for cards, editorial or children’s books.

The prompt 2 fields to fill
delicate watercolor illustration of , loose expressive brushstrokes with visible paper texture, soft bleeding washes of , gentle wet-on-wet edges, light pencil underdrawing showing through, airy negative space, hand-painted storybook feel, no harsh outlines --ar 4:5
Example output
A sprig of eucalyptus painted in loose sage-and-blush washes, the pigment blooming softly where the leaves meet. The watercolor paper's tooth shows through, faint pencil guidelines peek out at the stem, and the generous white space around it gives the airy, hand-made look of a greeting card or editorial spot illustration.

TipMentioning "paper texture", "wet-on-wet" and "no harsh outlines" keeps it from looking like a digital filter slapped over a photo. Watercolor loves breathing room — ask for "airy negative space" rather than filling the frame.

MidjourneySDXLFLUX

Cyberpunk neon street scene

A moody sci-fi cityscape with rain, neon and cinematic atmosphere.

The prompt 2 fields to fill
cyberpunk street scene,  in the foreground, rain-slicked neon-lit alley at night, glowing  signage and reflections on wet pavement, dense atmospheric fog and volumetric light, towering holographic billboards, cinematic anamorphic lens flares, moody high-contrast color grade, blade-runner aesthetic, highly detailed --ar 16:9
Example output
A lone figure in a translucent raincoat stands in a narrow alley drenched in magenta and cyan neon. Reflections smear across the wet asphalt, fog catches the volumetric glow, and a giant holographic ad flickers overhead. Anamorphic flares streak horizontally across the frame; the deep-shadow, high-saturation grade nails the Blade Runner mood.

TipWet pavement + fog + volumetric light is the combination that makes neon actually glow and reflect rather than just sit flat. Pick two dominant neon colours (e.g. magenta + cyan) instead of "rainbow" — restraint reads as cinematic, a full spectrum reads as noisy.

MidjourneyGPT ImageFLUX

App icon / glossy UI icon

A polished rounded-square app icon concept for a store listing mockup.

The prompt 4 fields to fill
modern mobile app icon for a  app, single bold  symbol centered on a  gradient, rounded-square format, soft long shadow, subtle depth and gloss, clean simple shapes, vibrant , iOS app-store icon style, no text --ar 1:1
Example output
A meditation-app icon: a simple white lotus silhouette centred on a smooth indigo-to-violet gradient rounded square. A soft long shadow gives gentle depth, the gloss is subtle (not skeuomorphic), and the single symbol stays legible even at thumbnail size — exactly how it would look in an App Store grid.

TipIcons must survive being shrunk to thumbnail size, so insist on a single bold symbol and no text. Generate on the rounded-square gradient, then drop it into a phone/store mockup to sanity-check legibility before committing.

GPT ImageMidjourneyFLUX

Overhead food photography (flat lay)

A top-down cookbook-style shot of a dish, with props and side light you control.

The prompt 4 fields to fill
overhead food photograph of  on a  surface, styled with , natural window light from the side, soft shadows, crumbs and texture details, editorial cookbook styling,  palette, shot on 50mm lens, top-down flat angle --ar 4:5
Example output
Tested in GPT Image (gpt-image-2) on 30 Sep 2026 with DISH = a cast-iron pan of shakshuka with crusty bread, SURFACE = weathered dark wood, PROPS = a linen napkin, a small bowl of fresh parsley and a vintage spoon, COLOR PALETTE = warm terracotta and olive green. It returned a portrait top-down shot: four eggs with glossy orange yolks set in a chunky tomato sauce, scattered with parsley and cracked pepper, the pan handle angled out to the lower right. Torn sourdough and a few crumbs sit top left, the parsley bowl top right, a tarnished spoon at the edge and an olive linen napkin folded along the bottom left. The light rakes in from one side, so the bread crust and the wood grain carry texture without hard shadows. Where it fell short: the "terracotta" in the palette shows up only in the sauce — the surface and props stay dark brown and olive — and the spoon is cut off by the right edge of the frame.

TipName two or three props and one surface — that is what makes it read as a styled editorial shot instead of a menu photo. "Crumbs and texture details" keeps the food looking real rather than plastic. In GPT Image or DALL·E, delete the --ar flag and ask for a portrait image instead.

GPT ImageMidjourneyFLUX

Children's picture-book illustration

A soft, storybook-style scene with room left for the words on the page.

The prompt 4 fields to fill
children's picture-book illustration of   in , soft gouache and colored-pencil texture, gentle rounded shapes, warm  palette, cozy storybook lighting, expressive friendly faces, plenty of white space around the scene for text, no text --ar 3:2
Example output
Tested in GPT Image (gpt-image-2) on 30 Sep 2026 with CHARACTER = a small fox wearing a yellow raincoat, ACTION = jumping over puddles, SETTING = a quiet autumn village lane, COLOR PALETTE = mustard, rust and sky-blue. The result is a landscape spread in a soft gouache-and-pencil texture: the fox mid-leap over a splashing puddle, grinning, in a yellow raincoat — and matching yellow boots it added on its own. Autumn trees and a wooden fence frame the left, a robin sits on the fence, and a lane of stone cottages with a church spire and a street lamp recedes to the right. The edges fade out to white paper, leaving open space at the top and in the corners for a line of text.

TipKeep "no text" and add the words yourself in a layout tool — image models still misspell. For a series, reuse the exact character line (e.g. "a small fox wearing a yellow raincoat") on every page so the character stays recognisable.

GPT ImageMidjourneyFirefly

Vintage travel poster (art deco)

A 1930s-style destination poster with a clear band left for your own title.

The prompt 2 fields to fill
vintage 1930s travel poster illustration of , art deco style, bold flat color shapes, strong geometric composition,  limited palette, subtle screen-print grain, dramatic sky, large empty band at the top reserved for a title, no text, no letters --ar 2:3
Example output
Tested in GPT Image (gpt-image-2) on 30 Sep 2026 with DESTINATION = the Amalfi Coast cliffs with a small sailboat, COLOR PALETTE = coral, deep navy, sand and mint. It produced a tall art-deco poster: coral-orange cliffs dropping into a navy sea, a cluster of pastel houses with a domed church above an arched viaduct, a white-sailed boat with its reflection, and stylised cream clouds cut by two sweeping sun rays. It added a branch of lemons and white blossoms in the foreground on its own. The top third is clean, flat navy sky — exactly the title band the prompt reserves — and there is no lettering anywhere.

TipAsk for the empty title band and "no letters", then set the destination name yourself in an art-deco typeface. Two to four colours plus "screen-print grain" is what sells the period look.

GPT ImageSDXLFLUX

Tattoo flash design

A stencil-ready tattoo design on plain white, in the style you name.

The prompt 3 fields to fill
tattoo flash design of  in  style, bold clean linework,  shading, isolated on a plain white background, symmetrical balanced composition, high contrast, ready to use as a stencil, no skin, no background scenery
Example output
Tested in GPT Image (gpt-image-2) on 30 Sep 2026 with SUBJECT = a snake coiled around a dagger with a rose, TATTOO STYLE = American traditional, SHADING = solid black and limited red. It returned a vertical flash piece on plain white: a downward-pointing dagger with a cross-hatched grip and red jewels, a black snake with red belly scales winding around the blade, its head at the top right with fangs and a forked red tongue, and a red rose with black leaves where the coils cross the blade. The outlines are heavy and even and the fills are solid black and flat red, with a little stipple texture on the rose petals. With no background at all, it can go straight onto a stencil. Where it fell short: the prompt asks for a symmetrical composition, but the snake's head and forked tongue break out to the upper right, so the design is visibly lopsided.

TipName a real tattoo style (American traditional, fine line, blackwork, neo-traditional) — it changes line weight and shading more than any adjective. Treat the result as a flash sketch: a tattoo artist should redraw it as a clean stencil before it goes on skin.

GPT ImageMidjourneyFLUX

Die-cut sticker design

A cute sticker with a thick white border, ready to print and cut.

The prompt 3 fields to fill
die-cut sticker design of ,  style, thick white border around the outline, bold outlines, flat vibrant colors, simple shading, centered on a plain  background, no text --ar 1:1
Example output
Tested in GPT Image (gpt-image-2) on 30 Sep 2026 with SUBJECT = a happy avocado riding a skateboard, ART STYLE = kawaii cartoon, BACKGROUND COLOR = light grey. It returned a halved avocado with the pit as its tummy, big glossy eyes, blush cheeks and an open smile, arms out for balance on a black skateboard with orange wheels — plus orange sneakers it added itself. A thick, even white border follows the whole outline with a faint drop shadow, set on flat light grey, so the cut path is obvious. Colours are flat with one level of simple shading inside a bold black outline, and there is no text.

TipThe thick white border is the cut line — keep the background plain and a different colour from the border so a cutting machine or print shop can trace it. Keep "no text"; add any lettering in a design tool.

GPT ImageSDXLMidjourney

Pixel-art game scene

A retro side-scroller background with a limited palette and crisp pixels.

The prompt 4 fields to fill
 pixel art of , retro video game style, limited -color palette, crisp hard-edged pixels with no anti-aliasing, side-scrolling view, parallax background layers,  lighting --ar 16:9
Example output
Tested in GPT Image (gpt-image-2) on 30 Sep 2026 with BIT DEPTH = 16-bit, SCENE = a forest village with a blacksmith's hut and a small waterfall, NUMBER = 32, TIME OF DAY = sunset. It produced a detailed 16-bit-style vista: a timber blacksmith's hut with a glowing forge, an anvil out front and smoke from the chimney, a wooden bridge over a river, a waterfall on the right, and a castle and a windmill on a cliff against an orange-to-violet sunset. The pixel look is convincing, but it reads as a scenic painting rather than a flat side-scrolling layer, and the sunset gradient clearly uses more than 32 colours — the model treated "limited palette" as a mood, not a rule.

TipImage models imitate pixel art at full resolution, so neither the grid nor the colour count is exact. Before using it in a game, downscale with nearest-neighbour to your sprite resolution, reduce the palette to your colour count in an editor (Aseprite, or indexed colour in Photoshop) and scale back up in whole multiples. Add "flat side view, single background layer" if you need a tileable level rather than a vista.

GPT ImageMidjourneyFLUX

Isometric 3D diorama room

A cut-away miniature room on a plain background — great for headers and explainers.

The prompt 3 fields to fill
isometric 3D diorama of a , cut-away cube floating on a plain  background, miniature detailed furniture and props, soft global illumination, clay-like matte materials,  colors, tilt-shift miniature look, 45-degree isometric camera --ar 1:1
Example output
Tested in GPT Image (gpt-image-2) on 30 Sep 2026 with ROOM TYPE = cozy home recording studio, BACKGROUND COLOR = pale peach, COLOR PALETTE = muted teal, cream and walnut brown. It returned a square, cut-away room floating on a flat peach background, its two front walls cut away so you look straight in: a walnut desk with a monitor, MIDI keyboard, two studio monitors and a microphone on a stand, acoustic panels on the teal walls, an acoustic guitar, an amp with a pedalboard, a teal sofa, a round coffee table on a rug, bookshelves and plants. Shadows are gentle and the cut-away reads as a tidy miniature. Where it fell short: two style words were mostly ignored — there is no tilt-shift blur (every shelf, cable and plant is in sharp focus), and the wood grain and sofa fabric look like real materials rather than clay.

TipKeep "plain background" and "cut-away cube" together — they stop the model from building a whole house around the room. Swap [ROOM TYPE] for a café, a bookshop or an office to make a matching set for a landing page.

GPT ImageMidjourneyFLUX

Renaissance pet portrait

Your pet as an old-master oil painting, in the costume and role you choose.

The prompt 3 fields to fill
classical Renaissance oil painting portrait of a  dressed as , wearing , seated on a velvet chair, dramatic chiaroscuro lighting, rich dark background, visible brushstrokes and craquelure, museum-quality old master style, three-quarter view --ar 4:5
Example output
Tested in GPT Image (gpt-image-2) on 30 Sep 2026 with PET = golden retriever, ROLE = a 17th-century admiral, COSTUME = a navy coat with gold epaulettes and a lace collar. It returned a tall three-quarter portrait: the retriever seated in a red velvet chair with a gilded arm, head turned slightly, in a dark navy coat with heavy gold epaulettes, gold buttons and braid, a white lace jabot and cuffs, and medals on the chest; one paw rests on the chair arm and a sword hilt shows at the lower right. The background is dark, with a red curtain at the upper left and, through a window on the right, a sailing ship on a stormy sea — a detail it added to fit the admiral role. Visible brushwork and a canvas-like crackle make it read as an aged oil painting.

TipTo paint your own pet, attach a clear photo as a reference image (GPT Image and Midjourney both accept one) and keep the breed and markings in [PET] — e.g. "golden retriever with a white blaze".

GPT ImageMidjourneyFLUX

Architectural exterior at blue hour

A real-estate-magazine exterior with glowing windows and straight verticals.

The prompt 3 fields to fill
architectural photograph of a  exterior at blue hour,  architecture, warm interior lights glowing through large windows,  in the foreground, two-point perspective with vertical lines kept straight, shot on a tilt-shift lens, real-estate magazine quality --ar 3:2
Example output
Tested in GPT Image (gpt-image-2) on 30 Sep 2026 with BUILDING TYPE = single-story family home, ARCHITECTURAL STYLE = mid-century modern, LANDSCAPING = native grasses and a stone path. It returned a landscape shot of a low, flat-roofed house with a wide overhang of warm wood soffit and recessed lights, a stacked-stone chimney and wall, and floor-to-ceiling glass showing a lit living room with a sofa, an indoor tree and a chandelier. Large concrete stepping stones cross a bed of gravel and tall ornamental grasses, with low path lights and lit steps leading to the entry. The sky is a deep evening blue, and the chimney and window frames stay upright rather than leaning — the straight verticals the prompt asks for. Where it fell short: the "stone path" came back as smooth concrete pavers set in gravel, not natural stone; name flagstone or irregular natural stone if that matters.

TipThe phrase "vertical lines kept straight" (with tilt-shift) is what makes it read as professional architecture photography rather than a phone snap. Use it for concept boards and mood images — not as a listing photo of a real property, which would misrepresent it.

GPT ImageSDXLFLUX

Coloring book page (line art)

Printable black-and-white line art with closed shapes, sized for a letter page.

The prompt 2 fields to fill
coloring book page of , clean black outline line art on pure white,  detail, closed shapes with no gaps, no shading, no gray tones, no color, no text, printable at letter size --ar 3:4
Example output
Tested in GPT Image (gpt-image-2) on 30 Sep 2026 with SUBJECT = a sea turtle swimming over a coral reef, DETAIL LEVEL = medium, suitable for ages 8 and up. It returned a tall page of clean black outlines on white: a large sea turtle gliding across the upper half, its shell split into big plates and its flippers into small scale shapes, a few striped fish and a school of tiny ones, rising bubbles, and a reef of branching coral, tube sponges and rocks along the bottom. There is no shading and no grey anywhere — the only solid black is the turtle's pupil — and the big shapes are closed, so fill tools stay inside the lines. The smallest scales and the distant fish are fine enough to suit the "8 and up" level rather than young children. Where it fell short: the file came back at 1024 × 1536 px (2:3) while US Letter is 8.5 × 11 in, so printed at letter size it leaves white side margins and works out to roughly 140 pixels per inch.

TipSay "closed shapes with no gaps" and "no gray tones" — otherwise crayons and fill tools leak. Check the lines at 100% before printing: if any are faint, regenerate rather than darkening them, which thickens the whole page.

Midjourney

Anime & manga art with Midjourney Niji

Manga/anime-style art using Midjourney’s Niji model for clean linework and screentones.

The prompt 5 fields to fill
, ,  expression,  background, dynamic manga composition, clean inked linework with screentone shading,  palette, detailed eyes and flowing hair, anime key-visual quality --niji 6 --ar 2:3 --style [expressive / cute / scenic]
Example output
A teenage duelist skids to a halt mid-fight on a rain-soaked rooftop, blade raised, jaw set in determination. Crisp inked outlines and halftone screentones give it a shonen-manga page feel; the stormy blue-grey palette and motion lines around the figure read like a key frame from an anime opening. --niji 6 pushes the whole render toward Japanese illustration instead of Midjourney’s default photoreal look.

TipThe `--niji 6` model is what turns Midjourney from photoreal into true anime/manga — pair it with `--style cute`, `--style expressive` or `--style scenic` to set the mood. Drop `--niji` and you fall back to the standard model and a more generic illustration.

Midjourney

Cinematic film still with Midjourney

A movie-frame look using Midjourney’s --style raw, --ar and --stylize flags.

The prompt 7 fields to fill
cinematic film still of  in , ,  with  lighting, anamorphic lens, shallow depth of field,  color grade, 35mm film grain, atmospheric haze, in the style of  --ar 21:9 --style raw --stylize 250
Example output
A lone detective stands under a flickering motel sign at 2am, rain streaking the neon, collar turned up. Anamorphic flares stretch across the ultra-wide frame; the teal-shadow / amber-highlight grade and fine film grain sell it as a frame pulled from a neo-noir. Naming a director (e.g. Villeneuve, Fincher) steers palette and framing far harder than the word “cinematic” alone, and --style raw stops Midjourney over-polishing it.

TipOn Midjourney, `--ar 21:9 --style raw` plus a director or film reference is the fastest route to a believable movie still. `--stylize` (0–1000) controls how strongly Midjourney’s house aesthetic overrides your prompt — keep it low (~150–250) when you want your reference to dominate, and add `--sref <image-url>` to lock a specific look across shots.

Image generation prompts with fill-in variables

These text-to-image prompts work in Midjourney, Stable Diffusion (SDXL), ChatGPT’s GPT Image (which replaced DALL·E), FLUX and Firefly. Each has fill-in variables for subject, style and lighting, plus an example to copy.

Midjourney and AI image prompt examples

Copy a prompt, swap in your subject and style, and treat the result as a first draft to iterate on. Midjourney flags like --ar are included; other tools set the aspect ratio in their own interface.

Frequently asked questions

What makes a good AI image prompt?

A strong prompt names the subject, a medium or lens (e.g. 85mm portrait, watercolor, 3D render), a lighting setup, and a colour or style direction — plus an aspect ratio. That structure is what turns a generic result into a deliberate one. Every prompt here follows it, with fill-in placeholders for the parts you customize.

Do these prompts work in Midjourney, Stable Diffusion and GPT Image?

Yes, with minor tweaks. Midjourney uses flags like --ar 16:9 and --style raw, which appear in the prompts. In Stable Diffusion / SDXL, FLUX, GPT Image or Firefly you set the aspect ratio in the interface and can delete the flags — the descriptive part of the prompt is the same. Each card notes which tools it suits best.

How do I fill in the variables?

The words in [BRACKETS] — like [SUBJECT], [STYLE] or [LIGHTING] — are editable right on the card. Type your details into them, then click Copy and the filled-in prompt goes to your clipboard, ready to paste into your image tool. Repeated placeholders update together.

Can I use AI-generated images commercially?

It depends on the tool and your plan — each generator (Midjourney, GPT Image, Firefly, Stable Diffusion) has its own licensing and commercial-use terms, and they change. Check the current terms of the service you use before using an image in paid work, and avoid prompting for real people’s likenesses or copyrighted characters.

Do these prompts work in ChatGPT (GPT Image)?

Yes. The ten newest prompts on this page were run in OpenAI’s gpt-image-2 — the model behind image generation in ChatGPT — on 30 September 2026, and each of those cards describes what it actually returned with the example values filled in. In ChatGPT, delete Midjourney flags such as --ar and ask for a portrait, landscape or square image instead; the descriptive part of the prompt stays the same.

Why won’t the logo prompt render readable text?

Diffusion models still struggle to spell reliably, so the logo and icon prompts ask for the symbol only, with no text. Use them as concept direction, then rebuild the mark as a true vector in a tool like Illustrator or Figma and set the typography there.

What are good Midjourney prompts?

Strong image prompts name the subject, a medium or lens, a lighting setup and a style, plus an aspect ratio. Every prompt here follows that structure with fill-in placeholders.

Which image models do these prompts work with?

Midjourney, Stable Diffusion / SDXL, GPT Image (ChatGPT), FLUX and Adobe Firefly. The descriptive part is the same; only flags like --ar differ, and each card notes which tools it suits best.