Periodic Table Wall Prompt for GPT-image-2.5
A GPT-image-2.5 prompt for rendering a full periodic table as a wall of transparent glass showcase boxes, each holding a physical sample of the element — plus the corrections chemists posted underneath.
IMGLAB / PROMPTS
Curated prompts for image, video and visual creation.
A GPT-image-2.5 prompt for rendering a full periodic table as a wall of transparent glass showcase boxes, each holding a physical sample of the element — plus the corrections chemists posted underneath.
A ChatGPT Image 2.5 prompt that turns an orange-and-white clay cat — pixel sunglasses, studded collar, cigarette in mouth — into a 24-frame stop-motion skateboard loop, delivered as a finished GIF in one shot.
A free gacha-style photo prompt for GPT image 2 that turns "what pose should I strike" into "what just happened": 18 unexpected-moment action cards, each draw rolling 3 sets with random outfit, camera and real-life scene, CCD direct-flash style.
A free image-to-image prompt that turns a photo into an impasto oil-painting art print: the subject stays faithful, the surroundings become a compact hand-painted summer world with palette-knife clouds on warm ivory paper.
A free video prompt that turns a three-panel triptych image into a cinematic anime autumn park clip: the same girl on a bench, walking a leaf-covered path, then holding a red maple leaf as the camera pushes in.
A free fill-in-the-blank prompt for GPT image 2 that renders any [STRUCTURE] as a minimal hand-drawn travel-journal artwork: ink sketch on warm ivory paper, tiny handwritten annotations, muted earthy washes and plenty of blank space.
A free image-to-image prompt that turns any landscape photo into a tiny minimalist watercolor-and-ink vignette: the artwork sits small and centered on warm ivory textured paper with generous negative space and a tiny handwritten caption — Japanese travel-sketch stationery aesthetic.
A short style formula rather than a runnable prompt: retro editorial still life built on low-saturation pastel, vintage grain and restrained negative space. Four reference images.
A free prompt for anime fashion-project posters: a Genshin character reinterpreted in a premium JK uniform, shot from an extreme low angle, under oversized editorial art typography. Written for Ganyu's BLUE HUSH and shown working across four characters.
A free GPT image 2 image-to-image prompt that turns any photo into a 3:4 editorial poster: the top half stays photorealistic, the bottom half becomes a tiny handmade mixed-media artwork on warm ivory.
A free photo-to-poster prompt that splits any picture into a vertical diptych: the untouched photo on top, and below it an extremely reduced hesitant-crayon line study on warm white paper, with at least 55% negative space and a short handwritten observation.
A free image-to-image prompt that flattens any photo into a mid-century modern editorial poster: vector-flat planar composition, 4-6 colour palette, screen-print sensibility, with explicit rules against depth, anime and mascot looks.
A free image-to-image prompt that rescues unflattering photos by repainting them as warm hand-pasted pastel portrait illustrations — identity, expression and open-mouth pose all preserved, on a flat powder-blue background with gouache, dry pastel and colored-pencil texture.
A free GPT image 2 prompt for a vertical full-body street-style portrait: a woman in a brown knit cardigan on a European boulevard, head tilted to the sunlight, eyes closed, with a full negative prompt.
A short outfit-and-palette formula rather than a runnable prompt: four autumn layering combinations for middle-aged men, held to a five-colour earth palette. Four reference images.
A reusable GPT image 2 template prompt: swap in any city or country and get a torn-paper travel scrapbook collage built from 5-7 recognizable local elements on warm ivory paper.
A free GPT image 2 prompt that turns a photo's subject into 4-6 hand-drawn frames — ingredients, preparation, texture, final form — styled as a page from an old culinary sketchbook.
A free 10-second video prompt for Gemini Flash: tiny explorers in khaki expedition gear trek across an oversized tropical island, from a low tracking shot in the jungle to a wide aerial reveal.
A free GPT image 2 prompt built on one rule — never pose the subject, give her an accident. Ships a pool of ten everyday mishap scenarios, an iPhone snapshot spec and a signature block.
A free GPT image 2 prompt for a photorealistic candid summer garden portrait: a woman in a plaid camisole and white skirt holding a woven basket of red tomatoes beside a backyard vegetable garden.
A free GPT image 2 prompt for a photorealistic nighttime street portrait: a woman in a cream textured jacket and pleated skirt on a lively city street, with warm streetlights, passing cars and slight motion blur.
A short style formula rather than a full prompt: Japanese minimalist lifestyle illustration built on low-saturation natural color, relaxed layered outfits and light watercolor linework, with four reference images.
A free 21-second vertical stop-motion video prompt for Seedance 2 on PixVerse: a tiny humanoid figure built from beach stones dances in a tidal pool, then collapses back into ordinary stones.
A free prompt for a highly realistic 4:5 editorial fashion photograph featuring a woman beside a child-sized hand-drawn illustrated counterpart wearing the exact same outfit.
A free close-up portrait prompt built on warm backlight: dark tousled hair lit from behind into a golden halo, deep emerald velvet with gold embroidery, on a dark moody background.
A free portrait prompt for a soft-glow CCD candid shot: a woman in a crowded Tokyo subway carriage at rush hour, framed behind blurred foreground passengers, 9:16 vertical.
A free, shot-by-shot video prompt for a photorealistic 9:16 macro clip: a miniature grey kitten no bigger than a fingertip is squeezed out of a tube onto the back of a hand and leaves a pink paw pad imprint behind.
A video prompt by Soaima for Seedance 2.0. Feed it a reference image of a glass snow globe holding a miniature McDonald's, ringed by pink, white and cream roses, and it produces a dreamy macro product clip - slow dolly push-in on the glass, falling petals, a soft breeze through the flowers, and elegant bokeh, in photorealistic 4K vertical 9:16.
A video prompt by Soaima for image-to-video models. Feed it three watercolor autumn reference images and it produces one seamless cinematic vertical clip - reaching for falling leaves, reading under the tree, riding a bicycle through the park - holding the same girl, outfit and style across all three scenes.
An image-to-image prompt by Soaima that converts an uploaded photo into a soft watercolor autumn illustration of a young woman in a cream sweater and blue jeans - resting under a maple tree, riding a bicycle with a flower basket, reading a book, or arranging fallen leaves into a heart. For Gemini, Grok or GPT Image 2.0, with an optional animation step for video.
A structured JSON prompt by @saniaspeaks_ for ChatGPT Image 2, a candid full-body outdoor smartphone portrait of a young woman on a quiet winter urban street in soft afternoon sunlight. Subject is playful and relaxed, with a long lavender-blue shirt, white lace top and tiered skirt, finished by a cream backpack and white sneakers.
A ChatGPT Image 2 candid lifestyle portrait prompt by Aqsa, a young woman in a cozy modern Korean-style kitchen wearing a black floral camisole and a blue pleated skirt, holding a strand of hair with a playful pout. Full English prompt ships in the tweet body.
An image-to-image prompt by SajidHassain for a photoreal miniature diorama of a tropical beach resort under construction, with a single oversized human hand working on tiny villas while full-size tools sit at model scale around the site. For Gemini, Grok or GPT Image 2.0.
A cinematic AI image concept by 0xKyne for a candid street portrait in Tokyo's Shibuya crossing on a rainy night. The prompt plays subject stillness against the chaos of rain, neon, taxi light trails and a motion-blurred crowd. Visual thesis: the more chaotic the city, the more striking the subject should look.
A detailed Seedance 2.5 prompt for a 30-second 1080p ultra-realistic early-2000s DV home video of a young Korean woman running relaxed Sunday errands in an older Seoul neighborhood. The prompt locks subject identity, scripts the trip beat by beat, and locks camera, audio, object continuity and a hard negative list so the model can't cheat its way through the shot.
A detailed prompt for a 24mm wide-angle full-body environmental portrait of an adult Chinese female model catching a travel moment at a seaside bus stop. It pins down the pose, the low angled candid camera position, the composition, the late-afternoon side light and the negative constraints, and ends with a request for a natural, non-staged snapshot rather than a runway look.
A short GPT-Image 2 demo that turns an ordinary portrait into a cinematic rainy-night coffee shop scene. Two samples are shown, one of the same woman seated holding a takeaway cup, one standing with a shoulder bag, both lit by warm streetlamps against a wet pavement and a coffee shopfront with hand-painted signs. The full prompt is referenced in the replies rather than embedded in the post, so this entry captures the visual recipe and the prompt's intent, not the prompt text itself.
A reverse-engineering prompt workflow for the viral AI subway outfit-change video format. Built with GPT-6 Astra and tuned for MiniMax H3 image-to-video mode, it turns a reference video into an H3-ready prompt in one pass, so the shopping-app-to-new-outfit transformation can be recreated without an expensive big-engine video model.
A detailed 15-second video prompt that animates a cartoon character climbing out of an X profile page avatar circle, peeling the page's text off into paper planes, sweeping the leftovers away with a broom, and writing two lines across the blank space with a marker. Built for GPT-6 Astra with MiniMax H3, it takes two reference images, one for character identity and one for page layout, and locks the camera for the entire shot.
A GPT Image 2 prompt by Soaima that blends two reference images into one magical 9:16 scene - a young woman sipping coffee on a giant dewy leaf beside a tiny butterfly creature in a sunlit forest, seamlessly transitioning into a nighttime miniature world where she sleeps in a matchbox bed labeled GOOD NIGHT on a warm wooden desk.
A video prompt by Soaima for Seedance 2.0. Turn an uploaded Vaseline Cocoa Glow product shot into a 10-second vertical skincare commercial in six timestamped scenes - unboxing, hands lifting the bottle, a hero shot with cocoa beans, a macro texture close-up, a rotating hand-held shot and a final push-in - while preserving the label and branding exactly.
A ChatGPT Image 2 prompt for a full-body mirror selfie of a stylish young woman seated cross-legged on a wooden workout bench inside a modern luxury gym. It pins down subject, outfit, props, environment, lighting and a 9:16 vertical composition with shallow depth of field and warm beige ambient light, and asks for natural skin texture rather than a smoothed beauty render.
A tight, ready-to-paste English prompt for a late-night smartphone-flash bedroom portrait of an adult East Asian woman. It pins down subject, outfit, pose, framing, camera, lighting, aesthetic flags and hard negatives, and is built around a casual late-night snapshot look rather than a studio setup.
A free GPT image 2 prompt for photorealistic 3D character portraits pairing a woman with a giant fluffy blue bird mascot in a 2:3 studio composition.
A prompt by Soaima that converts an uploaded character reference into a sophisticated hand-painted watercolor and ink fashion portrait. Three-quarter over-the-shoulder pose, deep blue and warm orange highlights in flowing dark hair, pearl earrings, artistic color bleeding on a mostly white background, shipped with a complete negative prompt.
A prompt for minimalist philosophical hand-drawn illustrations in magazine editorial style: black ink linework with light watercolor, muted beige, gray and brown palette, and generous negative space. It pairs a small human figure with an oversized symbolic object to create absurd contrast, expressing themes like desire, anxiety, vanity, loneliness, success, money and time.
No resources match these filters.