Copy-ready text-to-image prompts for Midjourney, Stable Diffusion (SDXL), DALL·E, 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 and lifestyle shots, sweeping landscapes and interiors, stylized anime and 3D characters, 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; 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.
15 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.
FLUXSDXLDALL·E
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.
MidjourneyFLUXDALL·E
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.
MidjourneyDALL·EFLUX
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.
SDXLFLUXDALL·E
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.
MidjourneyDALL·EFLUX
Minimalist vector logo concept
A clean, flat brand mark concept you can hand to a designer to refine.
The prompt 4 fields to fill
minimalist flat vector logo for , a brand, simple geometric mark, on a clean white background, balanced negative space, bold and memorable, no gradients, no text, no 3D, flat design, centered, crisp edges, suitable for a brand identity --ar 1:1
Example output
A single deep-green geometric mark for a plant-care brand: an abstract leaf formed from one continuous folded line, perfectly balanced with clever negative space inside it. Flat, two-dimensional, centred on pure white, with no gradients or shadows — a clean concept that would vectorize cleanly into an SVG.
TipDiffusion models cannot reliably render text or true vectors — ask for "no text", generate the symbol only, then rebuild it as a real vector in Illustrator/Figma. Use these outputs as direction and inspiration, not as the final deliverable.
MidjourneyDALL·EFLUX
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.
These text-to-image prompts work in Midjourney, Stable Diffusion (SDXL), 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 DALL·E?
Yes, with minor tweaks. Midjourney uses flags like --ar 16:9 and --style raw, which appear in the prompts. In Stable Diffusion / SDXL, FLUX, DALL·E 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, DALL·E, 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.
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, DALL·E, FLUX and Adobe Firefly. The descriptive part is the same; only flags like --ar differ, and each card notes which tools it suits best.