Text to Image
Annotated ChatGPT Multiple Image Outputs — AI Image Prompt
A screenshot-style composition showing a Japanese ChatGPT image generation request with n=10 highlighted and multiple generated anime background thumbnails. - AIPinMaker
Prompt
Goal: Create a realistic screenshot-style image of a ChatGPT image generation interface demonstrating multiple image outputs from one request.
Canvas: Landscape 16:9 screenshot crop, white background, resembling a mobile or narrow desktop chat interface. Keep the composition slightly zoomed in so the right edge of the image carousel is visible.
Layout: At the top right, place one rounded light-gray user message bubble containing Japanese text. Beneath it on the left, show the status line “Thought for 2m 7s ›” in light gray. Below that, show one large generated image preview with rounded corners, and a narrow strip of additional generated thumbnails on the right side.
Text content: The user bubble should read: “絵コンテを参考に今回のベた塗アニメMVで使用する背景イラストを被写体なしで10個作成してください。\nテイスト強めで汚らしっぷつぷ感はなくしてください。プロアニメーターとして画質はよくしてほしいです。\n16:9 n=10”. Highlight the “n=10” part as the key detail.
Generated image preview: The main preview is a pastel anime background illustration of an empty stylized street with no characters, inspired by a colorful East Asian shopping district. Use soft cel-shaded anime line art, bright pastel blue, pink, yellow, and mint tones, lanterns hanging from buildings, decorative circular signs, shopfronts on both sides, a centered vanishing point, and a decorative archway in the distance. The image should look like a professional anime MV background, 16:9, clean and polished.
Discrete visible elements to include: exactly 1 user message bubble; exactly 1 status line; exactly 1 large main generated image; exactly 3 narrow vertical thumbnails partially visible on the right, each showing a different pastel anime background; exactly 2 circular overlay buttons on the main preview, one dark “編集” edit button at bottom left and one white downward arrow download button near bottom right; exactly 1 small dark share/upload icon button at the lower-right corner of the main preview.
Annotation: Add thick hand-drawn yellow marker annotations over the screenshot: exactly 1 yellow circle around “n=10”, exactly 1 thick yellow arrow pointing from the circled “n=10” down toward the right-side thumbnail strip, and exactly 1 tall yellow bracket-like outline encircling the vertical thumbnail strip. The yellow marker should look casual and drawn by hand.
Style: Clean UI screenshot aesthetic with subtle antialiasing, light gray interface elements, Japanese text rendered legibly, and bright yellow annotation marks. Use {argument name="main annotation text" default="n=10"} as the highlighted parameter in the chat message. Keep the screenshot realistic, not a poster or infographic.39:Tb07,Goal: Create a realistic screenshot-style image of a ChatGPT image generation interface demonstrating multiple image outputs from one request.
Canvas: Landscape 16:9 screenshot crop, white background, resemblingPrompt breakdown
- Subject
- ChatGPT interface screenshot with Japanese user bubble requesting 10 anime backgrounds, status line reading Thought for 2m 7s, large main pastel street illustration and right-side thumbnail carousel
- Style
- Clean UI screenshot aesthetic with subtle antialiasing, legible Japanese text, rounded bubbles, and casual thick yellow hand-drawn marker annotations
- Composition
- Landscape 16:9 crop zoomed on white chat interface showing top-right user bubble, left status line, centered main image with edit and download buttons, plus three narrow vertical thumbnails on the right
- Mood
- Professional polished anime MV background feel with instructional yellow highlights drawing attention to the n=10 output request
Remix ideas
- Swap the main street scene for a rainy variant with reflective pavement while keeping the same pastel palette
- Add a fourth thumbnail and extend the yellow bracket to enclose all four
- Change the user message to request n=8 and update the yellow circle and arrow accordingly
Reference images
How to use this AI Image prompt template
1Copy the prompt — grab this template’s prompt and negative prompt. 
2Pick a model — choose a recommended AI model for the best match. 
3Generate — open the studio with one click and create your result.
Related templates
Cinematic Video Game Cutscene with Subtitles
Create a cinematic image of Cinematic Video Game Cutscene With Subtitles. Style: photorealistic. Composition: balanced and well-framed. Lighting: natural with cinematic mood. Category: cinematic-video. Reference: cinematic-video-game-cutscene-with-subtitles-13734.
Streetwear Motion Clone Editorial
Turn my photo (source) into a luxury cinematic streetwear editorial poster. Preserve my face, body, pose, outfit and original background so I'm still clearly recognizable, then upgrade the whole frame into a high-end fashion campaign look (style). Across the composition place 4 (count) realistic duplicate versions of me arranged like motion-captured steps of a walk sequence. Keep the central/front version the biggest, sharpest and most detailed, while the side clones are softly faded or motion blurred. Light it with dramatic top-down lighting, a subtle glow, deep shadows, long floor shadows, a cool-toned cinematic color grade, strong contrast, glossy highlights and a touch of fine film grain. Render outfit textures crisp and premium. In the top corner add bold oversized magazine-style typography with one powerful word tied to movement or style (e.g. MOTION, STATIC, RUSH, ECHO), plus smaller minimal text like a collection year, slogan, barcode or campaign details.
Early 2000s Digital Camera Snapshot Prompt - Nano Banana Pro AI Prompt for Social Media Post
{ "meta": { "aspect_ratio": "4:5", "quality": "ultra_photorealistic", "render_style": "raw digital snapshot realism", "grain": "authentic early-2000s compact camera noise", "no_ai_artifacts": true }, "camera": { "device": "compact Canon digital camera", "lens_equivalent": "28–35mm", "aperture": "f/2.8", "iso": 400, "shutter_speed": "1/60 with flash", "white_balance": "auto flash", "display_effect": "LCD screen glow with slight pixel texture" }, "composition": { "shot_type": "close-up", "framing": "subject centered within camera LCD screen", "outer_frame": "Canon camera body visible around screen", "details_visible": [ "FUNC/SET wheel", "DISP button", "textured plastic surface", "\"IMAGE STABILIZER\" label on side" ], "perspective": "viewer looking directly at the camera screen" }, "scene": { "location": "indoor kitchen", "time": "night", "background": { "elements": [ "cluttered countertop", "metallic kitchen appliances", "open shelves with random items" ], "focus": "softly blurred", "lighting": "dim ambient, overpowered by flash" }, "atmosphere": "candid, raw, nostalgic, early-2000s digital camera vibe" }, "lighting": { "type": "harsh direct built-in flash", "effect": [ "strong facial highlights", "hard shadow falloff", "slight shine on lips and hair", "flattened but intimate flash look" ], "contrast": "high", "color_temperature": "cool flash tones" }, "subject": { "identity": { "gender": "female", "age_vibe": "early 20s", "face_reference": "use facial structure, eye shape, nose proportion, and mouth softness from the attached photo", "body": "curvy, tight waist, round hips, full chest", "skin": "wet, glowing, subtle pink flush as if from cold night air", "hair": { "color": "dark brown", "state": "slightly wet", "behavior": "loose strands falling across face and collarbone" } }, "expression": { "eyes": "heavy-lidded bedroom eyes looking directly into lens", "mouth": "slightly parted lips, relaxed and soft", "overall": "warm, wine-softened, flirtatious confidence without posing" }, "pose": { "head": "slight tilt toward flash", "shoulders": "relaxed, close to frame edge", "energy": "caught-in-the-moment, not performing" } }, "color_grading": { "palette": "slightly muted", "undertones": "cool", "contrast": "strong flash contrast", "screen_effect": "subtle LCD pixel grain and glow" }, "restrictions": { "no_text_inside_photo": true, "no_logos_on_screen": true, "no_watermarks": true, "no_studio_lighting": true, "no_ai_symmetry": true } }3f
Candid High-Fashion Tennis-Core Spectator Shot - Nano Banana Pro AI Prompt for Social Media Post
{ "image_prompt_data": { "subjects": { "primary_subject_1": "A glamorous young woman with long platinum blonde hair styled half-up, wearing a vibrant red sleeveless mock-neck top and a matching red tweed mini skirt with black and white fringe trim. She is peering over the rim of slim black oval sunglasses, her hand adjusting the frame, wearing a gold watch on her left wrist.", "primary_subject_2": "A stylish young woman with wavy brunette hair, standing beside the first subject. She is wearing a red spaghetti-strap mini dress with a button-down front and ruffled hem. She wears dark angular sunglasses and small hoop earrings.", "pose_and_action": "Both subjects are standing side-by-side in a spectator box, leaning slightly against a blue railing. They are holding translucent cocktails with ice and melon ball garnishes (resembling Honey Deuce cocktails). They are looking off-camera to the left with a candid, focused expression." }, "environment": { "setting": "High-end outdoor sporting event stadium, likely a tennis match. Blue stadium seats and railings are visible. A 'RESERVED' sign is clearly printed on the blue railing in the foreground.", "background": "Blurred crowd in the background, creating a depth of field effect that isolates the subjects. The atmosphere is exclusive and energetic." }, "lighting_and_style": { "lighting": "Natural daylight, soft sun, even illumination, realistic skin textures, slight specular highlights on the sunglasses and drinks.", "style": "Paparazzi style, candid celebrity shot, fashion photography, tennis-core aesthetic, high fashion, sophisticated and chic." }, "technical_specifications": { "quality_tags": "Ultra realistic, HDR quality, UHD, 8k resolution, highly detailed, sharp focus, 85mm lens, f/1.8 aperture, cinematic color grading.", "aspect_ratio": "9:16 (Vertical/Long Image)", "resolution": "Highest possible" }, "compiled_prompt_string": "Two glamorous young women at a tennis match, US Open aesthetic. Subject 1: platinum blonde, red high-neck sleeveless top, red tweed skirt, looking over black sunglasses, gold watch. Subject 2: brunette, red spaghetti strap dress, sunglasses. Both holding Honey Deuce cocktails with melon balls. Leaning on blue railing with 'RESERVED' text. Candid paparazzi shot, ultra realistic, HDR, 8k resolution, highly detailed skin texture, depth of field, blurred stadium background, natural daylight, cinema quality, fashion photography, vertical aspect ratio --ar 9:16 --v 6.0 --style raw", "negative_prompt": "cartoon, illustration, 3d render, drawing, painting, bad anatomy, disfigured, blurry, low quality, pixelated, watermark, text overlay, distorted hands, extra fingers, bad eyes, grainy, noise, oversaturated." } }
Detailed JSON prompt for generating a viral athletic jump freeze photo - Nano Banana Pro AI Prompt for Social Media Post
{ "content_goal": "viral athletic jump freeze post (content goal)", "image_type": "jump freeze action photography", "visual_style": "cinematic sports editorial, high-impact, premium", "motion_concept": { "action_type": "jump freeze", "timing": "captured at peak height", "motion_state": "completely frozen mid-air", "energy": "explosive yet controlled" }, "pose_details": { "pose_name": "jump freeze flex pose", "body_position": "mid-air jump with legs extended or flexed symmetrically", "core_engagement": "tight core with visible strength", "arm_position": "balanced, expressive, athletic alignment", "freeze_quality": "sharp, suspended, gravity-defying" }, "subject": { "description": "athletic feminine body performing a powerful jump freeze", "physique": "lean, flexible, toned", "body_language": "confident, fearless, strong", "expression": "focused intensity with calm control" }, "facial_details": { "emotion": "determination mixed with ease", "micro_details": "relaxed face, steady eyes, natural expression" }, "wardrobe": { "clothing": "professional athletic performance wear", "fit": "body-contoured to emphasize motion lines", "fabric": "stretch performance fabric, non-reflective", "color_tones": "solid neutral or bold single color (wardrobe color)" }, "environment": { "location": "minimal studio or clean gym space", "background": "plain or gradient backdrop", "atmosphere": "focused, powerful, distraction-free" }, "lighting": { "type": "high-speed studio lighting", "quality": "crisp, clean, cinematic", "direction": "side and top lighting", "effect": "freeze motion sharply with defined muscle highlights" }, "camera_details": { "angle": "slightly low angle for power emphasis", "framing": "full body mid-air capture", "lens_feel": "sports editorial realism", "focus": "ultra-sharp subject with zero motion blur" }, "color_palette": { "primary_colors": ["neutral background", "natural skin tone"], "contrast_level": "high", "mood": "bold, energetic, inspiring" }, "emotional_impact": { "viewer_reaction": "scroll-stopping shock and admiration", "message": "power, balance, and control in one moment" }, "quality_control": { "realism": "ultra-realistic photography", "detail_level": "high-definition muscle and fabric texture", "ai_artifacts": "none", "professional_standard": "editorial-grade" }, "intended_use": { "primary": "viral jump freeze post on X", "secondary": "fitness branding, athletic inspiration" } }
Dreamy Y2K Soft Girl Magazine Grid
Create a creative image of Dreamy Y2k Soft Girl Magazine Grid. Style: photorealistic. Composition: balanced and well-framed. Lighting: natural with cinematic mood. Category: photography. Reference: dreamy-y2k-soft-girl-magazine-grid-18555.
Explore more prompts
Browse more AI image and video prompts by category.
FAQ
- What does the Japanese text in the user bubble specifically ask for?
- It requests ten character-free background illustrations in a strong anime taste for a beta-paint MV, with high professional quality and no messy texture, formatted 16:9 n=10.
- Why include the yellow hand-drawn annotations on the screenshot?
- They highlight the n=10 parameter, show its direct link to the generated thumbnail strip and emphasize how one prompt produces multiple distinct outputs.