Curated AI prompts for stunning image and video generation. Updated daily from top creators.
A description of a workflow where a story is built with GPTs, refined with GenSpark, and then a video from Kling is converted into a 4-panel manga using Nano Banana Pro.
Prompt Preview
From Kling video footage to 4-panel manga using Nano Banana Pro
A template for generating manga panels (ratio 2:3) in Nano Banana Pro, where the user inputs the desired content and the previously generated style tags (Style, Negative-Style, Color) to maintain a consistent aesthetic.
Prompt Preview
Manga Generation (Ratio: 2:3) Content: <{argument name="content" default="Insert content here"}> <{argument name="style tags" default="Insert style tags (Style, Negative-Style, Color) here"}>
An instruction for using Nano Banana to maintain facial and clothing consistency across multiple shots (jump cuts) by uploading source images for the face and the scene (like a staircase shot). This is a workflow instruction that functions as a prompt.
Prompt Preview
To maintain consistency in face and clothing, use Nano Banana to create additional jump cuts. Upload the source image of the face, and the {argument name="scene type" default="staircase shot"}:
A text prompt designed for an LLM or video generation model (like Seedance 2.0/Sora 2) to create a highly dramatic historical scene featuring intense dialogue, emotional conflict, and character revelation. The scene focuses on two characters, Xiao Jingheng and Shen Qingtang, discussing their shared history of reincarnation and failure.
Prompt Preview
Xiao Jingheng, his face covered in blood, draws his sword and points it at Shen Qingtang, shouting hysterically: "I have accompanied you through ninety-nine reincarnations, yet you still haven't defeated him! My intolerance for stupidity is about to flare up!" The woman in front of Xiao Jingheng, Shen Qingtang, sits on the ground, gently stroking Cheng Jingchuan, who is barely alive, in her arms. Upon hearing this, she suddenly looks up in surprise and says, "You, you are also a reincarnator?" Xiao Jingheng is instantly deflated by the shock. "Useless! You big idiot! I've accompanied you through ninety-nine reincarnations."
A two-step prompt sequence for Nano Banana Pro (Gemini 3 Pro Image) aimed at creating a 4-panel manga. The first instruction converts a specific scene (a Dragon Quest X monster zone special move) into a 4-panel format, and the second instruction adds speech bubbles and dialogue to the generated panels.
Prompt Preview
Turn this (the Dragon Quest X Superstar special move Monster Zone) into a 4-panel manga! Next Add speech bubbles and dialogue!
A structured prompt for generating a set of 12 emoji/sticker images in a 4:3 vertical format, where each panel depicts a different emotion or action (e.g., working hard, lying flat, working overtime) with corresponding large overlay text. The user needs to specify the main character/subject using the {argument name=\"subject\" default=\"protagonist\"} placeholder.
Prompt Preview
Generate 4 images based on the prompt, maintaining consistency in style with the original image. Each image should have 12 panels, and the prompt for each panel is as follows. Image aspect ratio: Vertical 4:3: 1 Full of energy Go! {argument name="subject" default="protagonist"} in a running and sprinting pose, limbs spread powerfully, speed lines behind, determined expression, large text "Go!" at the top of the screen. 2 Completely lying flat Lie Flat {argument name="subject" default="protagonist"} lying on their back with all four limbs up, eyes drawn as horizontal lines, soul floating out of the body, blank expression, large text "Lie Flat" at the top of the screen. 3 Received confirmation Okay! {argument name="subject" default="protagonist"} standing at attention and saluting, serious and solemn expression, straight body, large text "Okay!" at the top of the screen. 4 Slacking off Give up {argument name="subject" default="protagonist"} slumped on the sofa, holding snacks, vacant eyes, lazy posture, large text "Give up" at the top of the screen. 5 Super happy Yay! {argument name="subject" default="protagonist"} raising both fists in celebration, mouth wide open smiling, stars sparkling around, large text "Yay!" at the top of the screen. 6 Feeling wronged Sob {argument name="subject" default="protagonist"} eyes watery, mouth pouting, ears drooping, wronged expression, large text "Sob" at the top of the screen. 7 Smirking Hehe {argument name="subject" default="protagonist"} tilting head sideways, squinting and smirking, rubbing hands together, sly demeanor, large text "Hehe" at the top of the screen. 8 Work fatigue Overtime {argument name="subject" default="protagonist"} slumped over the computer, obvious eye bags, coffee cup nearby, tired expression, large text "Overtime" at the top of the screen. 9 Watching the drama Eating melon {argument name="subject" default="protagonist"} holding and eating a watermelon, eyes wide and curious, looking forward, large text "Eating melon" at the top of the screen. 10 Sudden wealth Rich! {argument name="subject" default="protagonist"} wearing sunglasses and a gold chain, banknotes and gold ingots floating around, smug expression, large text "Rich!" at the top of the screen. 11 Blushing Shy {argument name="subject" default="protagonist"} covering face with hands but peeking through fingers, cheeks blushing, shy expression, large text "Shy" at the top of the screen. 12 Good night Sleep {argument name="subject" default="protagonist"} curled up under a small blanket, eyes closed sleeping soundly, "zzz" symbol nearby, large text "Sleep" at the top of the screen.
A complex, multi-step prompt designed to generate a cinematic 3x2 storyboard grid (6 frames) from a single uploaded photograph (Jennifer Lawrence). It requires preserving the subject's identity and environment while varying the camera angles (Wide, Medium, Low-angle, Close-up, Dynamic, Final Shot) to create a narrative flow, emphasizing realism and cinematic consistency.
Prompt Preview
Use the uploaded photograph as the only visual reference. The person’s identity must be preserved with maximum accuracy: face, facial features, age, gender, body proportions, and overall appearance must remain unchanged. Do not invent or add anything that does not exist in the original image. Step 1: Detailed visual analysis of the source image First, perform a careful visual analysis of the uploaded image, including: Who is in the image (person, number of people, position in frame) Body pose and direction of gaze Facial expression and emotional mood Clothing and accessories Lighting conditions, time of day, color temperature Environment, background, and depth of space Overall emotional tone of the scene Step 2: Cinematic 3×2 storyboard grid After the analysis, create a cinematic 3×2 grid (6 frames) from the single image, as if it were a sequence of shots from a film. Global requirements for the entire grid: Format: one image containing a 3×2 grid All frames must be numbered 1–6, left to right, top to bottom Visual style: realistic, cinematic, non-illustrative One consistent character and environment with logical continuity Each frame must differ by pose, camera angle, or camera distance The sequence should feel like time is passing and the scene is developing No facial distortion, no change in identity or appearance Frame descriptions: Frame 1 (No. 1) Wide establishing shot. The camera is farthest from the subject, showing the full environment and context. The person feels like part of the surrounding space. Frame 2 (No. 2) Medium shot. The camera moves closer. The pose changes slightly, revealing inner emotion or state of mind. Frame 3 (No. 3) Low-angle or side-angle shot. Adds drama or tension, emphasizing body shape and perspective. Frame 4 (No. 4) Close-up or medium close-up. Focus on the face, eyes, and emotion. Fine details are clearly visible. Frame 5 (No. 5) Dynamic angle: diagonal composition or camera movement. The pose changes the most, creating a sense of action or momentum. Frame 6 (No. 6) Final shot. Calm, reflective, or emotionally resolved. The camera may be closer or farther, but the frame feels like a conclusion. Lighting & cinematic consistency: Lighting must remain logically consistent across all frames, as if filmed in one continuous scene. Depth of field, lighting, and color grading should reinforce a cinematic look. Final result: The output should resemble a professional cinematic storyboard, captured in a single take and location, with strong realism and narrative flow.
A complex, multi-part prompt written in Urdu/Hindi (Romanized) describing two separate superhero variants (Spider-Girl) resembling Ana de Armas and Sydney Sweeney, detailing their unique costumes, poses, and distinct New York City environments under golden hour or backlit conditions.
Prompt Preview
[ { "image_no": 1, "person_details": { "name": "{argument name="person 1 name" default="Ana de Armas (Likeness)"}", "pose": "Confident pose, sitting on a rooftop wall", "hair": "Brown, slightly wavy hair" }, "attire_and_appearance": { "title": "Spider-Girl Variant", "suit_color": "Deep orange and medium purple", "vibe": "Cinematic superhero suit", "shoes": "Heeled superhero boots that appear to be part of the suit" }, "background_environment": { "view": "New York Skyline", "prominent_building": "One World Trade Center (Freedom Tower)", "lighting": "Soft golden light of the evening (Golden hour lighting)", "weather": "Clear sky with light clouds" }, "items_and_objects": { "bag": "Large white leather tote bag", "clothing": "Yellow cardigan or scarf", "shoes": "Separate brown leather boots placed aside" } }, { "image_no": 2, "person_details": { "name": "{argument name="person 2 name" default="Sydney Sweeney (Likeness)"}", "pose": "Sitting on the ground, legs crossed", "hair": "Golden (Blonde) and loose" }, "attire_and_appearance": { "title": "Yellow Spider-Suit", "suit_color": "{argument name="suit color" default="Bright yellow (yellow)"} with black stripes", "design": "Large black spider mark on the chest", "lower_half": "Black bodysuit style" }, "background_environment": { "view": "Modern city buildings (Skyscrapers)", "sun": "Sun shining from behind the buildings (Backlit effect)", "setting": "Modern rooftop balcony with a glass railing" }, "items_and_objects": { "fabric": "Shiny electric blue fabric lying on the ground", "shoes": "Black pointed high heels taken off to the side", "feet": "Barefoot pose" } } ]
This tweet mentions using Nano Banana Pro in combination with Midjourney V5.2/V7 and a specific instruction to create a '1940s movie Still, resize 4:3', with the full original prompt located in the image's ALT text (not provided here).
Prompt Preview
1940s movie Still, resize 4:3
No prompts found for the selected type.
Try adjusting your search or filters