Curated AI prompts for stunning image and video generation. Updated daily from top creators.
A simple image generation prompt for creating a cinematic still image of a man reading a book inside a New York coffee shop, rendered with the aesthetic qualities of Kodak Vision3 film stock. This prompt was used to test the model's ability to handle specific objects (a book) and film styles.
Prompt Preview
a cinematic still of a man holding a book in a New York coffee shop shot on Kodak Vision3.
A highly structured JSON prompt designed for generating a gritty, modern streetwear-style smartphone mirror selfie taken inside a metal elevator. It includes detailed parameters for image style, subject pose, clothing, accessories, environment, and explicitly requires 100% facial identity matching from a reference image.
Prompt Preview
{ "image_parameters": { "style": "Smartphone mirror selfie", "type": "Outfit check / POV", "quality": "Sharp digital noise, slightly desaturated", "tone": "Cool, edgy, modern, industrial", "lighting_and_atmosphere": "Overhead fluorescent elevator lighting, unflattering but gritty. Reflections on metallic walls." }, "subject": { "constraints": { "facial_identity": "Match reference image exactly 100%", "face_edits": "None allowed" }, "expression": [ "Cool/Neutral", "Looking at phone screen", "Obscured by phone", "Sassy tilt" ], "pose": { "body_position": "Standing casually, hip cocked to one side.", "action": "Holding phone up to mirror, maybe one hand in pocket or adjusting hair.", "details": "Full body or 3/4 shot." }, "clothing": { "style": "Streetwear or Night-out chic", "top": "Leather jacket or oversized blazer", "bottom": "Baggy cargo pants or mini skirt with patterned tights", "shoes": "Chunky platform boots or sneakers" }, "accessories": [ "Phone case with stickers", "Over-ear headphones around neck", "Beanie or cap" ] }, "environment": { "setting": "Inside a metal elevator", "background": [ "Reflective metal walls", "Elevator buttons panel", "Dirty mirror texture", "Infinite reflection if multiple mirrors" ] } }
An extremely detailed, structured JSON prompt designed to generate a hyper-realistic, edgy, late-night iPhone flash selfie of an alt-girl. It meticulously defines the style, age, subject's appearance (hair, face, expression, outfit), props, setting, lighting, technical camera details, and includes a comprehensive list of elements to avoid.
Prompt Preview
{ "style": "hyper-realistic iPhone flash selfie, late-night bedroom vibe", "age_range": "21–24 years old", "girl": { "hair": "jet-black straight hair with blunt bangs, shoulder-blade length, perfectly sleek and shiny", "face": "pale skin, sharp winged eyeliner, overdrawn matte nude lips, slight resting bitch face", "eyes": "fox-like upturned eyes, heavy lower lash line, staring straight into lens with zero emotion", "expression": "bored / unimpressed, tiny smirk at one corner of the mouth" }, "outfit": { "top": "oversized vintage band tee (faded black with cracked white print), slipping off one shoulder", "fit": "baggy on top, contrast against tiny waist" }, "props": { "phone": "iPhone 16 Pro Max held in portrait, flash ON and blasting", "hand_position": "lazy one-handed grip low near waist, arm relaxed" }, "setting": { "location": "messy bedroom corner", "walls": "dark gray walls covered in layered posters (mostly metal bands, horror movies, red LED bias lighting)", "lighting": "room almost completely dark except aggressive red LED strips behind posters + cold white phone flash" }, "camera_&_technical": { "perspective": "true first-person selfie POV", "lens": "24 mm smartphone equivalent", "flash": "harsh direct on-camera flash, strong raccoon-eye shadows, blown-out highlights on cheekbones and collarbone", "quality": "16K photorealistic, grainy sensor noise, high contrast", "framing": "mid-thigh up, phone low in frame to exaggerate legs and torso length" }, "mood": "edgy, 3 a.m. insomnia energy, alt-girl who doesn’t care if you like the photo or not", "avoid_list": [ "smiling", "soft lighting", "cute hair clips", "pastel colors", "clean background", "heavy jewelry", "anime/cartoon style", "smooth plastic skin" ] }
A detailed, structured prompt for generating a photorealistic, low-key portrait of a young woman using dramatic chiaroscuro lighting, mimicking a cinematic golden hour aesthetic. It specifies camera details (85mm/50mm prime lens, shallow depth of field) and focuses on high-contrast lighting that splits the face.
Prompt Preview
{ "type": "photorealistic image prompt", "description": "A close-up, low-key portrait of a young woman with long, straight, medium-brown hair and natural makeup. She is wearing a dark, simple top. She looks directly at the camera with a serious, intense, and self-assured expression.", "style": { "aesthetic": "Golden hour portraiture, cinematic, moody, high-contrast, chiaroscuro lighting.", "lighting": "Strong directional natural light (possibly golden hour) coming from the left, creating a dramatic, harsh shadow that splits the face and illuminates the hair and the left side of the face. The background wall is cast in deep shadow.", "camera_details": { "lens": "85mm or 50mm prime lens", "aperture": "f/1.8 to f/2.5 (shallow depth of field)", "film_type": "Digital, high-resolution", "composition": "Close-up headshot/bust shot, centered subject, eye-level angle." } }, "subject_details": { "person": "Young woman, appearing to be in her early 20s.", "hair": "Long, straight, rich medium-brown hair, styled with natural movement.", "expression": "Serious, steady, direct gaze, confident.", "attire": "Black or dark navy simple crewneck or t-shirt.", "skin_tone": "Warm, natural tone." }, "background": { "setting": "Plain, simple wall or indoor setting, strongly shadowed.", "color_palette": "Dominantly warm browns and creams on the illuminated side, contrasted with deep, dark shadows and blacks." } }
A detailed image generation prompt for creating an ultra-realistic, divine artwork depicting Lord Shiva and Goddess Parvati meditating back-to-back on a celestial cloud. The prompt specifies the appearance, attire, and divine attributes of both deities, along with technical details like 8K hyperrealistic rendering, dramatic lighting, and spiritual ambiance, following a mythological Indian art style.
Prompt Preview
Ultra-realistic divine artwork of Lord Shiva and Goddess Parvati sitting together in deep meditation, back-to-back on a glowing celestial cloud. Mahadev with blue skin, ash markings, long flowing hair, rudraksha mala, tiger-skin dhoti, serpent around his neck, peaceful closed eyes, calm expression, Trishul glowing behind him with divine aura. Parvati in a vibrant pink and gold saree, elegant jewelry, serene face, gentle smile, soft golden halo around her head, flowing hair, graceful feminine posture in meditation mudra. Heavenly light beams from above, cosmic particles in the background, soft smoke mist, spiritual ambiance, ultra-detailed textures, 8K hyperrealistic rendering, high dynamic range, dramatic lighting, mythological Indian art style, divine energy radiance.
A structured JSON prompt aimed at creating a cinematic street photography image paired with a specific, reflective caption, intended for use as the final slide in an Instagram carousel. It defines the objective, the caption text, the visual style (mood, lighting, texture), and relevant tags, emphasizing Midjourney-style realism and storytelling.
Prompt Preview
{ "Objective": "Create a cinematic street-photography inspired final slide caption paired with Midjourney-style realism and storytelling aesthetics.", "Caption": { "Primary_Text": "In a crowd full of motion, the ones who stand still make the loudest noise. 🎞✨", "Description": "Created in Midjourney — cinematic realism that feels alive, where every face becomes a story waiting to be told." }, "Visual_Style": { "Theme": "Cinematic street realism", "Mood": "Emotional, atmospheric, reflective", "Lighting": "Soft filmic contrast with vivid bokeh depth", "Aesthetic": "Traveler-inspired realism with expressive human storytelling", "Texture": "High clarity, realistic skin details, natural film-like grain", "Composition": "Moving urban crowd with a single still subject anchoring the scene" }, "Tags": [ "midjourney", "cinematic realism", "ai photography", "emotional street portrait", "traveler aesthetic", "urban crowd art", "bokeh depth shot", "storytelling image", "realistic ai portrait", "creative ai generation", "moody cinematic visual", "viral ai post", "travel inspired realism", "ai storytelling composition" ], "Output_Requirements": { "Use_Case": "Final slide in an Instagram carousel, cinematic AI-art caption, aesthetic storytelling post", "Format": "Caption with associated visual-style metadata", "Tone": "Poetic, cinematic, thought-provoking" } }
A simple prompt instructing the model to overlay an existing image (implied, as this is a modification prompt) with chaotic, handwritten elements like schizophrenic conspiracy scribbles, doodles, remarks, and comments using red ink.
Prompt Preview
overlay this with insane schizophrenic conspiracy scribbles, red ink, doodles, remarks, comments.
A prompt instructing the AI to generate an extremely detailed, messed up, and weird image of a 'crazy psycho' character, including a speech bubble that says 'heading out?'. It requires a reference photo for the character.
Prompt Preview
Create an image of a crazy psycho with speech bubble that says “heading out?” Make the entire image extremely detailed but make it really messed up and weird af.
A highly specific prompt for generating an ultra-realistic cinematic night street portrait. It requires 100% facial accuracy based on a reference image and features the man walking hand-in-hand with a glowing neon outline illustration of a girl holding red roses. The prompt details clothing, lighting, atmosphere, and technical requirements like shallow depth of field and crisp details.
Prompt Preview
Create an ultra-realistic cinematic night-street portrait featuring the young man from the reference image. His face must match the reference image with 100% accuracy — no changes at all to facial features, hairstyle, beard style, skin tone, expression or proportions. The man is walking on a dark empty road at night, wearing an all-black outfit with a black denim jacket, black t-shirt, black pants and white sneakers. Beside him, add a glowing neon outline illustration of a girl holding a bouquet of bright red roses. The neon girl should look exactly like a clean, smooth light-drawing silhouette — yellow neon body outline, soft glow, and the roses glowing in red neon. The man and the neon girl are walking hand-in-hand. Street bokeh lights in the background, shallow depth of field, dramatic lighting, moody cinematic atmosphere, crisp sharp details, full-body shot, realistic shadows on the road, perfect color grading. Maintain complete accuracy of the man’s face from the reference image — no changes at all.
No prompts found for the selected type.
Try adjusting your search or filters