From Wikiprompt, the free prompt encyclopedia
Wikiprompt is a collaborative encyclopedia of AI prompts, featuring curated templates for various AI tools including ChatGPT, Midjourney, DALL-E, Claude, and more. It contains 3213 prompts by 225 community members.
All, Creative, Marketing, Business, Productivity, Coding, Education, Personal, Research, Other
All, GPT Image 2 (800), ChatGPT (298), Model-agnostic (247), Seedance 2.0 (242), Nano Banana Pro (226), Gemini Nano Banana (210), Gemini Nano Banana Pro (182), Grok Imagine (83), Claude (61), Gemini (44), Midjourney v7 (29), Nano Banana 2 (27), Veo 3 (25), Gemini Nano Banana 2 (24), GPT Image 1.5 (24), Midjourney (21), NotebookLM (20), Midjourney v8.1 (14), ChatGPT / Gemini (12), Kling AI 3.0 Turbo (12)
All, cinematic (198), photorealistic (115), editorial (106), portrait (96), commercial (39), fashion (38), minimalist (31), studio (31), luxury (30), product-photography (29), lifestyle (28), golden-hour (26), surreal (25), miniature (23), infographic (21), 3d-render (20), poster (20), candid (19), monochrome (19), macro (18)
All, Creative generation (2567), Template (321), One-shot (226), System prompt (50), Workflow (39), Persona (6), Agent (3)
67 prompts
Creates a minimalist seated-athlete editorial poster in a Portugal national kit, with a large translucent jersey number and clean studio-style FIFA World Cup 2026 branding. Via Kollab's World Cup 2026β¦

Produces a cinematic Match Day sports poster with a player walking away from camera, fist raised, giant bold typography, and official-style World Cup 2026 branding. Via Kollab's World Cup 2026 collectβ¦

A heartwarming Pixar-style 3D animation of a cat and mouse becoming friends in a sunlit kitchen, made with Seedance 2.0.

A four-photo editorial sequence of the same woman wandering a European city at golden hour, shot in a moody 1970s-90s 35mm film aesthetic. Made with GPT Image 2.

A detailed GPT Image 2 prompt that turns any film or story into a luxury layered pop-up storybook poster, with an open hardcover book blooming into a papercraft world and integrated title typography.

A meticulously timed single-take action prompt for Seedance 2.0 (1 face image + 1 prompt) staging a 15-second rooftop ambush, helicopter destruction and rooftop escape with second-by-second beats.

A long-form Seedance 2.0 (Higgsfield) prompt for a 4K identity-consistent lifestyle video following a woman through a calm morning routine, with detailed ambient-audio direction and no music.

A shot-by-shot, timeline-structured video prompt for generating a cozy 25-second cookie-baking clip with a recurring character, from ingredients to the melted-chocolate first bite.

A structured JSON prompt for GPT Image 2 (ChatGPT) that turns an uploaded reference photo into an ultra-realistic cinematic gym fitness editorial portrait with a katana.

A 15-second photorealistic dialogue scene for a first date at a garden cafe, with scripted lines and shot-by-shot cuts. Made with Nano Banana 2 plus Seedance 2.0.

Turns one reference portrait into a surreal aerial scene where the subject stands still while identical clones of her walk past. Built for GPT Image 2 on ChatGPT.

A 15-second cinematic video prompt with a full 5-beat timeline: an astronaut repairs an abandoned space station over Earth, with dialogue, physics and audio cues. Made with Kling AI 3.0 Turbo.

A photorealistic golden-hour meadow portrait prompt emphasizing windblown hair, freckled skin and shallow 85mm depth of field. Compared side-by-side on GPT Image 2 and Nano Banana 2.

A character-consistent 15-second fashion-commercial video prompt where the model travels through seven countries, each transition motivated by adjusting an outfit. Made with Seedance 2.0 from a characβ¦

A 15-second single-take cinematic WWII battlefield video prompt that uses a reference first frame and choreographs a soldier's charge to a fortress wall. Made with GPT Image 2 for the frame plus Seedaβ¦

A Seedance 2.0 recipe with a full 15-second, six-scene timeline: one reference influencer transformed through the couture of China, South Korea, Thailand, India, Japan and Saudi Arabia, each with its β¦

A GPT Image 2 recipe that drops a face-reference subject into a cinematic Avatar-style waterbending battle at night in an icy Water Tribe village - physical water ribbons, live-action realism, 4:5.

A Seedance 2.0 recipe for faux-documentary handheld DV-camcorder footage of the Great Pyramid's construction - worker gangs, ropes, dust, autofocus hunting and natural on-site sound.

A storyboard-to-motion recipe: build the frames in Seedream 5.0, animate in Seedance 2.0, for a 30-second GTA VI-style car-wash gameplay sequence with a HUD, ray tracing and water physics.

A GPT Image 2 recipe for a surreal editorial portrait: an aerial 45 degree shot of one sharp subject surrounded by motion-blurred identical clones in angled mirror panels, with a strong face-consistenβ¦
