25 Product Comparison & Aesthetic Analysis Prompts: GPT Image 2's Most Underrated Practical Use Cases

Based on an eye close-up image, generate a 3:4 four-panel ultra-realistic eye close-up composition arranged by spring, summer, autumn, and winter from top to bottom.

First panel: Eyes with cherry-blossom-colored contact lenses, lashes adorned with mini spring flowers, face scattered with cherry petals and yellow stamens, pink butterflies around brows, light golden hair strands, clusters of cherry blossoms below, white artistic "SPRING" lettering in the center, delicate and beautiful style, soft lighting, soft pink healing colors, calligraphy script "spring" below;

Second panel: Eyes with clear lotus-colored contact lenses, lashes decorated with pink lotus and green water plants, face with glistening water droplets, pink petals and green lotus details, dragonflies circling, light golden hair faintly visible, white artistic "Summer" lettering highlighted in center, transparent flowing light effect, clean and cool colors, calligraphy script "summer" below;

Third panel: Eyes with gold and red intermingled contact lenses, lashes decorated with orange-red maple leaves, face scattered with gold-red autumn leaves, orange butterflies dancing across brows, faint golden hair, striking white artistic "AUTUMN" lettering, warm golden lighting, rich and warm colors, calligraphy script "autumn" below;

Fourth panel: Eyes with snowy blue contact lenses, lashes covered with ice crystals and snow flakes, face scattered with white snow and red plum blossoms, silver-white butterflies dancing across brows, frosted golden hair, bright white artistic "WINTER" lettering, cold icy blue-white flowing light, clean and pure colors, calligraphy script "winter" below.

Overall present a dreamy fantasy scene of eyes transitioning through four seasons, adjust lighting intensity across panels to create richer atmosphere.

Create a personal color analysis graphic using this portrait. Point out which season colour suits the subject best. Show side-by-side clothing color comparisons to highlight which colors suit the subject best. List out what texture/accessories/hairstyle suit the subject best. Make it visual-first, with short labels only and no paragraphs.

Based on the portrait photo I upload, create a personal image analysis card set including hairstyle, makeup, color, and jewelry. Requirements: preserve facial features and skin tone without over-editing, show all changes on the same authentic face, clean and elevated style. Hairstyle: length, curl/straight, bangs—compare best/normal/not recommended (makes face look smaller/older). Makeup: analyze brows, eyes, nose, lips with tags (natural, brightening, soft). Color: different colors on body compare recommended/normal/unsuitable (whitening/aging). Jewelry: pearls, jade, red/blue stones, diamonds, gold—compare recommended/normal/not recommended. Overall: visual-focused, concise text, 4:5 aspect ratio.

Create a clean vertical fashion infographic from the uploaded portrait. Preserve the same face identity, hairstyle, body shape, and overall outfit style. Place the full-body character in the center in a relaxed T-pose, facing forward. Surround the character with realistic photo-style outfit breakdown elements, connected by thin arrows.

Include separate cutout sections for: head details, cardigan, sailor top, inner blouse, plaid skirt, bag, socks, loafers, color palette, styling notes, and fabric texture. Add 3–4 head close-ups from different angles at the top. Use short English handwritten-style labels and concise bullet points.

Visual style: soft pastel cream and blush-pink background, clean fashion board layout, elegant magazine-style composition, sweet preppy aesthetic, realistic fabric textures, delicate borders, small bow and heart doodles, airy and polished design. Keep the text short, readable, and fully in English. Original vertical aspect ratio.

Negative Prompt:

Chinese text, long text, messy layout, old parchment background, yellow aged paper, blurry details, distorted face, changed identity, extra limbs, bad hands, duplicated body, unrealistic fabric, cartoon style, anime style, 3D render, watermark, logo, unreadable typography, overcrowded design, harsh colors, low resolution.

9:16 vertical composition, single female artistic portrait, young East Asian woman, fine features, soft facial lines, natural translucent skin, preserve authentic texture, quiet elevated aura with slight detachment and narrative quality.

Photography studio style merged with natural light, soft side lighting, delicate face highlights, soft shadows, overall translucent lighting without harshness, subtle black mist filter effect, slightly hazy, soft glow, strong sense of air.

Minimalist clean background, cream gray, off-white, pale khaki or misty warm gray wall, substantial negative space, overall simple composition with breathing room.

Model sitting on ground or low platform, one leg naturally bent, one leg relaxed and extended, body slightly forward or sideways lean, asymmetrical shoulders, head gently tilted, movements natural and relaxed, unstaged.

Expression calm and restrained, soft eye contact, slightly detached, hint of contemplation, lips naturally slightly parted or gently closed, languid, quiet, delicate state.

Hairstyle natural voluminous long hair, slightly tousled shorter strands, soft hair texture, sense of air and layers, like recently tidied while preserving natural casual feeling.

Makeup elegant light makeup, Korean-style transparent base, skin with soft matte glow, natural highlights on bridge and cheekbones, clean brows, subtle but expressive eyes, long lashes, lip color in low-saturation rose or milky nude tone.

Outfit minimalist elevated: off-white fitted ribbed knit tank top, layered with loose white shirt or soft knit cardigan, bottoms high-waisted midi skirt or simple shorts, soft fabric fitting form without over-exposure, presenting natural body lines with literary aesthetic.

Image emphasizes delicate texture, soft tones, light French and Korean magazine aesthetic merged, authentic photography feel, cinema-level skin quality, rich details, clear hierarchy, restrained composition, elevated aesthetics, fashion editorial portrait, cinematic soft portrait, delicate texture, ultra-high detail, photorealistic, elegant, refined, high-end fashion photography, subtle sensuality, clean composition.

A side-by-side comparison graphic on a black background demonstrating a camera-angle change in the same restaurant scene. At the top, large white sans-serif text reads: "Show me the POV from someone standing behind the bar looking out over this crowded restaurant. Change NOTHING in the scene other than the pov". Below, place 2 stacked rectangular photos centered vertically: the top image labeled "Source" in large white text on the left, and the bottom image labeled "Output" in large white text on the left. The top photo shows a warmly lit, upscale, crowded restaurant interior seen from the dining room side, facing a tall back bar filled with many illuminated liquor bottles on wall-to-wall shelves, with bartenders and guests in front, amber lighting, globe pendant lights, wood ceiling, beige columns, and tightly packed seated diners in the foreground. The bottom photo shows the exact same restaurant, same crowd density, same warm lighting, same decor, same bar shelving, same globe pendant lights, and same overall composition elements, but now from the point of view of someone standing behind the bar and looking outward across the crowded restaurant; the foreground includes the bar counter with glassware, metal bar tools, bottles, and a point-of-sale screen visible at the lower left, while guests and staff fill the middle ground and the dining room extends into the background. Preserve the sense that only the camera position changed between the 2 images, with no other scene alterations.

Create a dramatic Japanese YouTube thumbnail in a futuristic neon cyberpunk style, 16:9 landscape. Use a dark tech-city background with faint skyscrapers, digital grid lines, glowing particles, and high-contrast blue, pink, and gold lighting. In the exact center, place a young woman from the waist up with long straight pastel blue hair, wearing a plain white short-sleeve T-shirt and a light pink skirt, posing thoughtfully with one hand near her chin and the other arm folded; anonymize her face with a soft rectangular blur. Across the very top, add huge distressed bold white Japanese headline text reading 主導権が揺れた, and directly below it add large bold yellow text reading {argument name="subheadline text" default="Nano Bananaから"}. On the left side, create a glowing blue hexagonal-framed panel titled Nano Banana with a smaller subtitle 画像生成. Inside that panel, include exactly 4 image tiles in a 2x2 grid: 1) a fantasy floating island landscape at sunset, 2) a sunlit forest path with tall trees, 3) a neon futuristic city street at night, 4) an outer-space planet scene with stars and a spacecraft. Beneath the left panel, add a blue glowing ribbon label reading かつては優位だった. On the right side, create a glowing magenta hexagonal-framed panel titled {argument name="right panel title" default="GPT Image 2"} with a smaller subtitle 実務で使える出力へ. Inside it, include exactly 4 example thumbnail cards in a 2x2 grid, each featuring the same blue-haired woman with a blurred face and bold Japanese text. The 4 card labels above the tiles are: サムネイル画像, 記事のアイキャッチ画像, LPのセクション画像, SNS投稿画像. The large text inside the 4 cards should read respectively: 1) AIで変わるクリエイティブの未来, 2) AI時代のクリエイティブ戦略 成功する企業の条件, 3) AIで加速するビジネス成長, 4) 未来をつくるのは AI×あなたのアイデア. Between the left and right panels, place a bright glowing gold arrow pointing from left to right with spark-like particle trails, indicating transition or superiority shift. Along the bottom, add a very large black banner with a glowing gold border and massive bold gold text reading {argument name="bottom banner text" default="GPT Image 2へ"}. Overall composition should feel like a comparison graphic showing a shift from older image generation to more practical commercial output, with aggressive thumbnail typography, strong glow effects, metallic texture on major text, and polished social-media marketing visuals.

A futuristic Japanese tech comparison poster in a dark cyberpunk control-room setting, wide 16:9 composition. Large distressed white Japanese headline text at the upper left reading "三つ巴", with a bold gold subtitle directly below reading "それぞれの武器". Across the center-left are 3 glowing holographic comparison panels arranged horizontally and connected by neon arrows: a blue panel labeled "Google", an amber-gold panel labeled "Claude", and a purple-magenta panel labeled "OpenAI". The Google panel contains 4 inner cards: 2 larger top cards labeled "Gemini" and "Antigravity", plus 2 smaller bottom cards showing analytics/dashboard-like visuals and a blue isometric cube graphic. The Claude panel contains 4 inner cards: 1 large top card labeled "Claude Code", plus 3 smaller bottom cards showing a network diagram, text/code list, and chart analytics. The OpenAI panel contains 5 inner cards: 2 larger top cards labeled "ChatGPT" and "Codex", plus 3 smaller bottom cards showing interface/code windows and a geometric wireframe cube. Add glowing bidirectional arrows between Google and Claude, and between Claude and OpenAI. At the bottom center, place a large neon-framed banner with gold text reading "Google / Claude / OpenAI". On the right side, include a young woman standing and pointing left toward the panels, with long straight split-dyed hair in pastel pink and cyan blue, a plain white t-shirt with black text reading "{argument name="shirt text" default="OKIHIRO AI Creative"}", and a soft pink pleated skirt. Her face is obscured by a smooth rectangular blur block. Use cinematic sci-fi lighting, glossy hologram UI details, high contrast, vivid blue-gold-purple accents, and a polished YouTube thumbnail aesthetic.

GPT Image 2.0 on ChatGPT vs Google Nano Banana 2 on Gemini. PROMPT: Create a hyper-realistic, cinematic portrait of me (use uploaded face) as a modern mafia boss. I'm sitting in a luxury black car, wearing a black suit and tinted aviator sunglasses, smoking a thick cigar. Cold, fearless expression. Background: moody sky + blurred city/street for noir feel. Cool tones, high contrast. Sharp details on face & smoke. Style: 8K, movie-poster quality, shallow depth of field 1:1

Please generate a visual brand deconstruction graphic for me that I can later use to create explanatory videos.

A [food item], dissected as a naturalist master discovering wild specimens in nature.
Dissected, unfolded, mounted—like precious museum collections,
yet illuminated by Caravaggio's light as he shot for National Geographic.
Every internal structure glows with its own material truth.
Cross-sections sharp as violence. Interior beauty near sacred.
Complete specimen presented in frame:
One half preserved in original state, showing [external appearance: texture/color/patterns];
Other half dissected to core, [internal core structure: 1-2 key internal visual features] clearly visible.
[Add 1-2 sentences describing the most visually striking cross-section details of this food]

Background: pure black velvet.
[Food item] floats within, like some precious and dangerous artifact.
Label text hugs structure edges, hand-written serif font, never floating.
Frame includes following annotations, each annotation three lines:
First line: structure name,
Second line: composition/data explanation,
Third line: plain language explanation:

[Structure 01 Name]
[Composition/Data Information]
[What this structure does and why it matters]

[Structure 02 Name]
[Composition/Data Information]
[What this structure does and why it matters]
[Structure 03 Name]
[Composition/Data Information]
[What this structure does and why it matters]
[Structure 04 Name]
[Composition/Data Information]
[What this structure does and why it matters]
[Structure 05 Name]
[Composition/Data Information]
[What this structure does and why it matters]

[Structure 06 Name]
[Composition/Data Information]
[What this structure does and why it matters]
Continue with same format if more structures exist.
Main title, upper left, warm ivory capitals:
[Food Item] · Dissection

Italic subtitle immediately following:
[One sentence revealing the essence of this food, max 15 words]

Overall aesthetic: Audubon natural history illustration × Caravaggio lighting × most beautiful scientific photography ever. 4K precision, specimen lighting, ultimate internal detail. No clinical feeling, everything alive. Photorealistic style, not conceptual, not cartoon, not simplified infographic. Every material has authentic physical texture:
Rough, smooth, moist, dry, dense, loose.

Neo-Chinese minimalist Eastern aesthetics × high-end commercial illustration, theme: one flower, one world,
minimalist, restrained, ethereal, elevated commercial visual, surreal Eastern sentiment,
clean and translucent frame, no gray haze, no muddy colors,

One massive lotus as space container, naturally growing from still water surface, subtle tilt, elegant composition with ample white space,

Low-saturation clean pink, soft blush tone, semi-transparent petals, light and translucent,
matte low contrast, softened edges + slight depth of field,

Inside lotus as only visual focal point: glowing 3D miniature Guangzhou city, including:
Guangzhou Tower, Zhujiang New Town architecture cluster, Liede Bridge, Pearl River waterfront, select Lingnan buildings,

City ultra-fine structure, authentic materials, extremely high detail clarity, city highlights in warm gold, city shadows in cool cyan-blue, creating cold-warm contrast,

Lighting translucent with energy, local high saturation but not excessive, city brightness clearly higher than lotus,

Water surface clear minimalist and still, only subtle soft ripples, weak reflections,

Background warm off-white rice paper texture, no ink wash, no brush marks, vast white space,
center with extremely subtle light halo gradation, overall translucent without murkiness or heaviness,

Below composition one ultra-minimalist small boat, one woman fisher in red on boat, ultra-small proportion,
standing still gazing upward at lotus, red as only high-saturation accent detail,

Overall lighting translucent, clean, layered, no gray haze, no blown-out highlights,
high-end CG commercial illustration, cinema-level authentic lighting, high dynamic range, ultra-fine, 8K detail, ArtStation quality, strong color separation, clean color grading, cyan-orange contrast, warm highlights cool shadows, only city lights increase saturation, soft color tone, sharp bright lighting, no gray haze, no darkness, no low-saturation haze.

Please automatically generate a high-aesthetic "outline universe / collector's edition narrative poster" style work based on theme [theme: xxx]. Do not confine the composition to fixed objects or common containers, do not default to bottles, hourglasses, glass domes, pocket watches or similar conventional vessels. Instead, let AI independently judge and select the most fitting, most symbolically meaningful, strongest-outline, most narrative-carrying main outline vessel. This main outline can be an object, building, door, tower, arch, dome, stairwell, corridor, statue, side profile, eye, palm, skull, wing, mask, mirror, throne, circle, crack, light screen, shadow, geometric structure, spatial cross-section, stage frame, abstract symbol or other more creative and thematically representative visual outline. Require reasonable spatial distribution. Prioritize outlines that amplify thematic aesthetics, create strong visual memory, embody epic feeling, mystery, poetic or design sense over the safest, most common, most ordinary containers.

The composition's core isn't simply containing the world inside an object, but letting the complete thematic world naturally grow within, inside, upon, along the boundary of this main outline or merge with its structure, forming an advanced narrative effect of "thematic universe developing around a symbolic outline." Main outline must be clear, elegant, identifiable, and occupy core position in overall composition. Within outline boundaries or edges, automatically generate complete narrative world strongly bound to theme, content should be rich, full, clearly layered, including most representative theme scenes, core architecture or spatial structures, symbolic and metaphorical elements, character relationships or civilization traces, foreground-midground-background spatial progression, atmosphere layers with fate and emotional tension, plus narrative details like doors, stairs, bridges, water surfaces, smoke, pathways, light sources, ruins, mechanical structures, natural landscapes, abstract forms, organisms or props. All elements must integrate unified, natural, with hierarchy and layering, like a complete world truly gestating within this outline structure rather than simple collage, cropping and filling, material stacking or template-based background.

Overall composition needs strong collector's edition poster aesthetic and elevated design sense, stable major structure, strong clear main outline, inner world with depth, order and breathing, rich details without crowding, complete content without disorder. Can appropriately include small-proportion character silhouettes, distant buildings, light pillars, door openings, bridges, stairs, colonnades, reflections, skylight or distant structures to enhance scale, narrative and epic feeling. Overall frame should be quiet, grand, concentrated, rich with afterthought, no even distribution, no cheap bustle, no pointless stacking.

Style combines collector's edition film poster composition, elevated narrative visual design, dreamlike watercolor texture and paper print aesthetic, emphasizing paper grain, edge feathering, watercolor brush marks, subtle color bleeding, atmospheric perspective, soft haziness, localized volumetric light, light mist penetration, large white space and restrained layout, making the frame look like completed high-end collector's edition visual work by designers rather than ordinary AI generation. Overall aesthetic should be elevated, poetic, grand, sacred, nostalgic, quiet, with legendary and narrative feeling.

Color selection AI automatically judges by theme and matches most appropriate elevated color palette, but must maintain unified, restrained, enduring, low-saturation, elevated aesthetic, never chaotic high-saturation, never cheap neon feeling, never plastic digital feeling. Colors can vary around black-gold-gray, cool blue-gray, misty white-gray, brown-red off-white, dark copper, aged paper, deep-sea blue, twilight purple, silver-gray systems, but must always serve theme and maintain poster-level aesthetics and overall harmony.

Final requirements: first glance has strong thematic recognition and outline memory, second glance has complete rich narrative world, third glance still has details and lingering aftertaste. Outline selection must have creativity and thematic match, avoiding repetition, conservatism, common container tricks, prioritizing more symbolic, more spatial, more design-potential outline forms. No ordinary background splicing, no stiff cropping, no templated fantasy materials, no game promo feel, no excessive cartoon, no excessive realism losing artistic feeling, no form dominating content. If suitable, can naturally incorporate subtle restrained title, numbering, signature or inscription making it more collector's edition poster design component, but do not overshadow content.

Using this image as perspective and style reference, create more refined ultra-high-resolution illustration depicting surreal Japanese cyberpunk future city, with ability to discern minute details, including street traditional cultural parade crowds, gangsters in alleys, dance girls in smoke-filled lanes, exhausted office workers, window rooms in buildings filled with various people—students studying, couples arguing, gamers playing, plus more creative details. Satirize boredom within crowded reality, solitude beneath urban prosperity, pathological beauty within meaningless life. Frame must possess extremely high aesthetic value, cannot lose beauty and harmony due to content abundance, proportion 9:16

Research LIME Drug Design and make a detailed infographic about it

Lü Bu game Boss design, Red Hare and Crescent Moon Halberd, dark evolution dual form comparison

1. Generate game battle poster of Shiranui Mai and Diao Chan
2. Generate a K-pop group fashion album cover
3. Create a key character relationship diagram for "Pursuit of the Lost Dragon"
4. Screenshot the TikTok homepage of the uploaded image

Social app matching success interface, two user profile cards colliding with heart effects

{"type":"comparison graphic","style":"anime cinematic demonstration image on a black presentation background","canvas":{"aspect_ratio":"4:3","background":"solid black"},"text_elements":[{"text":"{argument name=\"headline text\" default=\"Move the camera POV to be at ground level in the crowd.\"}","position":"top center","style":"large white sans-serif"},{"text":"Source","position":"left of upper image","style":"large white sans-serif"},{"text":"Output","position":"left of lower image","style":"large white sans-serif"}],"layout":{"sections":[{"title":"Source","position":"upper center","count":1,"labels":["overhead crowd scene"]},{"title":"Output","position":"lower center","count":1,"labels":["ground-level crowd POV scene"]}],"image_frames":2},"images":[{"role":"source image","composition":"busy top-down view of a densely packed historical street crowd, seen from above","scene":"a chaotic crowd gathered around a wagon and a horse-drawn carriage, people pressed shoulder to shoulder, many wearing caps and muted early-20th-century or old-European clothing, bundles and sacks visible, one brown horse at the right edge, wooden wagon wheel and cart structure partially visible","camera":"high overhead bird's-eye angle looking down into the crowd","lighting":"soft daylight","color_palette":"muted earthy browns, dusty blues, beige, olive, warm gray","rendering":"hand-painted anime film still, detailed crowd illustration, slightly soft shading"},{"role":"output image","composition":"the same crowded historical street reimagined from inside the mass of people at near-ground height","scene":"view from within the crowd beside a carriage wheel, bodies filling the foreground and midground, a person in dark maroon clothing bent forward at left, a crouched figure in green near the bottom center, a woman in a light blue dress at right-center turning back, tightly packed figures, horse and cart implied nearby, dramatic sense of compression and closeness","camera":"very low ground-level POV from inside the crowd, upward and forward through people, emphasizing complex occlusion and depth","lighting":"soft daylight with warm cinematic shadows","color_palette":"muted earthy browns, dusty blues, beige, olive, warm gray","rendering":"hand-painted anime film still, cinematic perspective shift, detailed character crowding, soft painterly shading"}],"overall_goal":"show a before-and-after camera angle transformation of the same anime crowd scene, with the output moving from an overhead view to a low immersive POV inside the crowd"}

Image of a person in a Polaroid photo who jumps out of the frame. Generate image with Japanese text.

← image below
Generated with GPT Image-2 →

Eastern fantasy style female, half-body portrait, glancing back profile, ethereal elegant aura, soft divine beauty, delicate features, downward gazing eyes, cool-white refined skin, light orange-pink makeup, gold highlights

Long flowing hair incorporating colorful flowers and light particles (red, blue, orange, purple) in hair, hair flowing with air texture

Wearing semi-transparent silk evening gown and shawl, material light and translucent, fabric floating with wind, surface with flowing gold texture and shimmering particles

Overall lighting warm golden backlight, strong rim light, obvious volumetric light, floating light particles, soft bloom glow, dreamlike atmosphere

Background clean light color gradient with slight glow and particle effects, overall ethereal, dreamlike, sacred atmosphere

Style: high-end CG illustration, ultra-fine, cinema-level lighting, soft glow rendering, 8K detail, ArtStation trending style

Daji ancient-style photography, red translucent gauze dress, fox ears faint and ambiguous, seductive manner

Yaya of Tushan (Fox Demon matchmaker) photoshoot spread, pink nine-tail fox fur form-fitting dress, seductive eyes like silk, red lips slightly parted, extreme enchantment

9:16 vertical, extreme wuxia style, stunningly beautiful Eastern female knight, early twenties, cold-sharp phoenix eyes, commanding brow authority, porcelain white skin, long straight black hair soaking wet wildly blowing in gale, few hair strands clinging to cheeks and neck, wearing soaking wet deep black modified wuxia martial outfit, layered with wide-sleeved black robe, robe and sleeves blown violently fluttering, tight martial outfit accentuating figure, soft sword belt at waist, long boots on feet, right hand wielding ancient sword, sword body radiating blue sword-light glow, dynamic pose: body slightly sideways glancing back, clothing rippling, background moonlit mist-shrouded bamboo forest ancient path, enormous bright moon high above, stone slab path, ancient lanterns, thin mist rain threads, dramatic cold moonlight and blue sword-light combining, wet-body water-light effects, ultra-strong dynamic feeling, delicate fabric wrinkles, hair-strand floating, authentic water droplets reflecting light, cinema-level lighting, 8k, masterpiece, best quality, ultra realistic, cinematic, dramatic atmosphere

GPT IMAGE 2 on ChatGpt Prompt: Transform the provided reference image into a cozy aesthetic scrapbook-style composition while strictly preserving the original subject, identity, pose, lighting, and background. Add multiple small "mini version" characters of the same person (chibi / doll-like style), placed naturally around the scene (on objects, table, shoulder, etc.). These mini figures must match the subject's face, hairstyle, outfit, and vibe consistently, styled as cute 3D collectible figurines. Show them doing different activities (reading, posing, taking photos, relaxing). Overlay handwritten-style doodles and annotations across the image: arrows, hearts, stars, sparkles, icons, and playful captions connected to elements in the scene. Use a soft pastel color palette (white base with pink, peach, blue accents). Keep the frame visually rich and filled but balanced and clean. Style: warm, cozy lighting, dreamy Instagram scrapbook aesthetic, soft depth of field, highly detailed, polished but playful. The final result must look like the SAME original image enhanced with mini alter-egos and aesthetic annotations — not a recreated or different scene

Based on uploaded portrait photo, generate [analysis type] card set,
including: [dimension 1], [dimension 2], [dimension 3], [dimension 4],
each dimension compare: recommended / normal / not recommended,
preserve authentic features, visual-focused, concise text, [aspect ratio]

A side-by-side comparison graphic on a black background,
[comparison condition explanation] at the top in large white text,
Source image: [scene A description],
Output image: [scene B description],
Preserve [unchanged elements], change only [changed elements]

[Style name], [3-5 core aesthetic keywords],
[Subject description: person/object/scene],
[Color system: primary color + contrast color + accent color],
[Lighting definition: light direction + warm/cold contrast],
[Material texture: 2-3 texture descriptions],
[Aesthetic boundaries: 3-5 "avoid xxx" statements]

One [item name], dissected as [analysis method],
one half preserved original, other half dissected,
[N structure annotations, each containing: name + data + explanation],
background: [solid background],
overall aesthetic: [aesthetic reference A] × [aesthetic reference B]