Sketch / Line Art

Convert a user's short image request, attached image, or combination of text and images into one finished prompt for GPT Image Gen V2 or Nano Banana Pro. Apply the Redphase Survey visual system defined below. Do not explain the system, show analysis, or add commentary. Return only the finished image prompt in the selected model's format. Use the model named by the user or supplied by the host application. If neither names one, use GPT Image Gen V2. For GPT Image Gen V2, return natural language prose only. For Nano Banana Pro, return one valid JSON object only. When both are explicitly requested, return the GPT prompt first under the line "GPT IMAGE GEN V2", then the JSON under the line "NANO BANANA PRO". Add no other text. Write prompt content in the user's language unless another language is requested. Keep Nano Banana Pro keys in English. Preserve exact in-image text in its required script. CORE LOGIC Every image contains two simultaneous records. The survey record describes what occupies the scene. It uses observed geometry, dry line, hatching, reserved paper, and a restricted set of local colors. The red phase describes what is active through the scene. It uses one red spectral range, deep black, limited bloom, rapid falloff, and selective loss of ordinary color and detail. The survey record answers: What is present? The red phase answers: What is acting, passing, gathering, or changing? Do not average the two records into red-tinted illustration. Give each record a separate job. Before writing the final prompt, silently determine: 1. The literal subject and setting. 2. The stable material structure that belongs to the survey record. 3. One active condition that belongs to the red phase. 4. The source of that condition. 5. The path or relation through which it travels. 6. The receiving subject, object, region, or surface. 7. The visible consequence. 8. Two or three transition sites where the records meet. Choose the active condition from the user's request. It may be physical, social, temporal, or perceptual. Valid causes include heat, movement, wind, electric current, pressure, recent touch, reflected light, sound, gaze, attention, occupancy, growth, chemical change, distance, or another condition that can be shown through visible evidence. If the request names no active condition, use the strongest existing process already implied by the subject or action. Do not invent danger, desire, trauma, memory, menace, or supernatural activity without evidence. Red is a measurement channel, not a mood label. Do not equate red with violence, horror, romance, or urgency unless the user's content establishes that meaning. The active condition must have one source, one route or relation, and one consequence. Do not scatter red accents without a causal structure. CONTENT CONTROL Preserve the user's explicit subject, count, identity requirements, action or state, setting, era, clothing, objects,

Create a landscape clean monochrome 2D storyboard line-sketch sheet of a mechanoid

Goal: Create a clean illustrated Chinese self-improvement infographic titled 三步拥有幸福人生, presenting happiness as three executable small steps like an instruction manual. Canvas: Wide horizontal 16:9 white background, airy margins, minimalist editorial poster layout. Use a hand-drawn red-orange marker style for all illustrations and large step numbers, with black Chinese body text. Overall feeling: warm, encouraging, simple, practical, like a WeChat article cover illustration. Header: Center a large rough handwritten red-orange headline at the top: 「三步拥有幸福人生」, with small decorative red strokes on both sides. Under it, add a small black subtitle: 「像说明书一样，把幸福拆成可执行的小步骤」. Layout: Three equal columns across the lower two-thirds of the canvas, connected visually by red-orange dotted arrows moving left to right. Each column has one doodle illustration above, a thin red divider line, then a step label, huge red step number, bold black title, and three short black lines of explanatory text. Use exactly 3 steps. Step 1 column, left: Section label 「准备」. Huge red number 「01」 followed by bold title 「先照顾自己」. Body text has exactly 3 lines: 「睡够一点」, 「吃好一点，动一动」, 「把身体和情绪放回正位」. Illustration: a simple smiling person sitting on the floor beside a pillow or bed, holding a steaming mug; include a small smiling sun doodle, a heart speech bubble, and cozy rest/self-care feeling. Step 2 column, center: Section label 「操作」. Huge red number 「02」 followed by bold title 「认真投入」. Body text has exactly 3 lines: 「每天做好一件重要的小事」, 「专注、练习、持续积累」, 「让生活慢慢长出方向感」. Illustration: a person writing in a notebook, another person reading an open book, a small child watering a potted plant with a heart on the pot; include a checklist clipboard, a clock, books, dotted motion arrows, growth arrows, and a tall sprouting plant to symbolize progress. Step 3 column, right: Section label 「完成」. Huge red number 「03」 followed by bold title 「分享与感恩」. Body text has exactly 3 lines: 「和喜欢的人保持连接」, 「表达感谢，也庆祝小成就」, 「幸福会在分享中放大」. Illustration: two simple smiling people clinking mugs or cups, a basket of apples with a heart, a smiling sun, a heart speech bubble, and a small award ribbon with a check mark. Visual style: Red-orange sketch lines should look slightly imperfect and textured, as if drawn with a wax crayon or marker. Text should be crisp and readable, using bold sans-serif Chinese for headings and smaller black sans-serif for descriptions. Keep the design uncluttered, balanced, friendly, and high contrast. Constraints: Include exactly 3 columns and exactly 3 numbered steps: 01, 02, 03. Preserve the visible Chinese text exactly as specified. Do not add extra panels, photos, gradients, shadows, watermarks, logos, or additional explanatory paragraphs.

Create a vertical 2:3 dark gothic anime illustration in a monochrome black, white, and muted silver palette. In a dense, dreamlike forest, show a pale young man with messy blond hair tied in a loose low ponytail, wearing a black formal suit and white shirt, kneeling or bending forward at the lower right. His head is bowed in sorrow and tenderness as he extends one human hand to gently touch one skeletal hand reaching in from the lower left, making exactly two central hands: one living hand and one exposed bone hand. Surround them with thick shadowed foliage, mist, tiny white blossoms, and several large white lilies in the foreground, with a soft vignette and painterly bokeh blur around the edges. Behind them, place tall vertical black-and-white tree trunks like solemn pillars, with cold backlight filtering through fog. Add a single narrow vertical Japanese inscription near the upper center on a dark trunk reading 死は優しく手を引く——. The mood should be elegiac, poetic, and quiet, like a funeral garden at night; use fine ink-like linework, delicate floral detail, high contrast chiaroscuro lighting, subtle film grain, and no modern objects, no extra characters, no watermark.

I want to create an emotional design with handwritten characters. Beautiful and cute flowing characters drawn by a young woman. It has a scribbled diagonal accent but the cuteness wins out. Use only a white background as it will be used as a material. No decoration, the beauty of the characters stands out. The text is: please enter the text you want to express here

Create a [YEAR] aesthetic illustrated calendar poster featuring the same mature [WOMAN/MAN/PERSON] (uploaded photo reference face 100%) across all 12 popular and tourist locations of [LOCATION] in different outfits and moods. The artwork should be in a soft watercolor + ink sketch style with clean hand-drawn linework and light textured shading. 🎨✨ The character has an expressive face.

Create a 16:9 monochrome storyboard line-sketch sheet for a swordswoman filming monsters; preserve a fixed frame and do not render

Goal: Create a square retro poster-style social media header/brand visual for a personal creative account themed around collecting everyday senses, writing what resonates, and sharing inspiration. Canvas: 1:1 square image, warm risograph print texture, slightly faded paper grain, bold graphic composition. Use a coral-pink background with oversized cream typography filling almost the entire image. Layout: Place enormous condensed block letters reading “MORE” across the top half and “SENSE” across the middle, cropped by the canvas edges so the letters feel poster-sized and architectural. In the lower center, draw a small line-art scene of a person seated at a desk. Add a tilted ticket-shaped label in the upper right. Add a small handwritten Japanese tagline near the lower right. Along the bottom, add a thin horizontal line and exactly 3 navigation words with small yellow dots between them. Main illustration: A simple teal-blue line drawing with cream fills and coral accents. Show chi.okey as a short-haired person with a bob haircut, seen from behind/side, sitting on a chair at a rectangular desk. The person wears a loose sweater, skirt or shorts, socks, and sneakers, and is writing in an open notebook. On the desk include exactly 5 visible objects: 1 open notebook, 1 small potted plant, 1 yellow mug, 1 smartphone or small card, and 1 small rectangular item. Beside the desk on the right, include exactly 1 fluffy sheep mascot with a cream wool body, dark face, and small legs. Add a dark teal cast shadow under the chair and table. Ticket label: In the upper right, draw a cream admission-ticket style sticker with teal outline, perforation details, and small decorative marks. Text on the ticket should read “chi.okey” in bold, “SENSE COLLECTOR” below it, and Japanese copy: “面白い！珍しい！心が動くモノだけ。” Bottom text: Create exactly 3 bottom menu items in blue uppercase with smaller lowercase captions: 1) “COLLECT” with “what moves me”, 2) “WRITE” with “what stays”, 3) “SHARE” with “what inspires”. Put exactly 2 small yellow circular dots between the three items. Additional text: Near the lower right, add handwritten Japanese text “好きが、いちばんのセンス。” with a short yellow underline stroke. Visual style: Minimal Japanese zine aesthetic, retro risograph, clean vector linework, teal outlines, cream typography, coral-pink background, yellow accent dots and mug. Slight ink misregistration, subtle paper speckles, playful but calm brand identity. Constraints: Keep the composition uncluttered, preserve the oversized cropped “MORE SENSE” lettering, include exactly 1 sheep mascot, no photorealism, no extra characters, no watermark.

A cute little child in a comfy taxi-yellow hoodie, denim shorts and white sneakers standing on a Brooklyn cobblestone street, looking up at the Brooklyn Bridge, minimalist children's drawing style, thick white lines, glowing contours. At the top of the poster, the city name "NEW YORK" hand-lettered in a cute rounded playful children's font, slightly wobbly like a child's handwriting, with thick glowing white strokes. The bridge's gothic arches and the Manhattan skyline drawn as simple, naive childlike shapes with luminous white outlines. The background is softly blurred with steel-blue and warm brick-red splashes, no architectural detail, only color patches. Floating elements like tiny yellow taxis, drifting pigeons, and small glowing stars add a whimsical touch. Full-body view, warm and simple aesthetic, vertical 3:4 poster.

Treat the uploaded image as composition and color reference only. Recreate it as an original minimalist vector doodle illustration. Use thick monoline cobalt-blue outlines with intentionally uneven hand-drawn strokes. Fill every object with completely flat solid colors sampled from the reference. No gradients, no realistic shading, no marker texture, no pencil texture, no cross-hatching, no painterly effects, no photorealism. Simplify facial features into cartoon shapes with round eyes, tiny nose, simple mouth, and minimal details while keeping the pose instantly recognizable. Use a clean off-white paper background with lots of negative space. The overall style should match a modern editorial doodle illustration, similar to hand-drawn vector artwork created with Procreate or Adobe Fresco, playful, bold, flat, minimal, and graphic Do not create a marker sketch. Do not create a realistic illustration. Create a flat vector doodle with bold blue outlines exactly in the same visual language as the reference.

Goal: Create a square Chinese dark newspaper-style story poster about 代付链接, using a restrained, emotional, old-magazine collage aesthetic. Canvas: 1:1 square poster, black worn paper background with heavy grain, scratched edges, dust, scuffs, faded ink, photocopy texture, and uneven white distressing. Overall monochrome black, gray, and off-white only. Layout: Irregular two-column editorial layout beneath one huge distressed headline. The headline occupies the top third, aligned slightly left, in oversized rough white Chinese brush/newspaper type reading 代付链接. Below it, arrange exactly 11 discrete text blocks: 6 blocks in the left column and 5 blocks in the right column. Use a mix of plain paragraph blocks, thin hand-drawn rectangular outlines, torn-paper strips, and large quoted pull-quotes. Keep margins tight and imperfect, like an underground zine or old crime newspaper clipping. Text blocks, counted exactly: 1. Left upper plain paragraph: “第一次加上她微信，\n是我姐的邻居牵的线。\n\n邻居是女孩的姑姑，说女孩二十五六岁，\n在老家市里卖车险，人长得漂亮，性格也不差，\n平时接触的人少，所以想找个靠谱的对象。” 2. Left outlined box paragraph: “我对“靠谱”这两个字没抱太大希望。\n相亲见得多了，介绍人口中的“性格好”，\n有时候只是“不爱发脾气”；“工作稳定”，\n可能只是暂时没辞职；“长得显小”，\n多半意味着照片拍得不错。” 3. Left bold intro paragraph: “但她的照片确实好看。\n脸小，皮肤白，笑起来显得很年轻，\n乍一看比实际年龄小好几岁。\n我们刚开始聊得也还算顺畅。\n她会问我工作，也会主动发些日常，\n偶尔说一句俏皮话。” 4. Left torn-paper strip: “我那时候觉得，也许这次能正常一点。” 5. Left large outlined pull-quote: ““又是一个代付链接。”” 6. Left lower plain paragraph: “我把钱付了。\n然后告诉自己，也许只是她性格大大咧咧，\n也许只是试探，也许现在年轻人相亲就这样。” 7. Right upper small lead-in plus torn-paper quote: “没过几天，她忽然发来一句：” followed by a torn strip reading ““请我吃个早饭呗。”” 8. Right upper paragraph: “我以为她是在开玩笑，或者想让我\n给她点份外卖，于是刚准备问她想吃什么，\n一个代付链接已经甩了过来。\n干脆、直接，没有铺垫。\n我盯着那个链接看了几秒，\n心里某个地方轻轻往下一沉。” 9. Right middle torn-paper quote: ““我们还没见过面。”” 10. Right middle paragraph with outlined lower portion: “甚至连彼此说话的语气都没完全熟悉，\n她已经很自然地让我替她付款。\n金额不大，几十块钱。\n可让人不舒服的，\n从来不是那几十块，而是那种理所当然。\n\n我没有立刻发作。\n说到底，还是因为她长得漂亮。\n人有时候很诚实，也挺没出息。\n要是换成一个完全不符合自己审美的人，\n可能当场就不想聊了。可面对一个漂亮女孩，\n很多原则都会先被自己往后挪一点。” 11. Right lower closing paragraph plus torn-paper emphasis: “过了一两天，聊到晚上，她忽然又说想吃牛排。\n紧接着，又是一个代付链接。\n这一次，我连替她找理由的力气都没有了。” followed by a gray torn-paper block reading “我没付。\n她也没生气，只是发了个表情，\n好像这件事本来就无关紧要。\n可我心里已经把她划掉了。” Typography and style: Use bold, rough, distressed Chinese fonts with chipped edges. Main headline should look hand-painted and eroded. Body text should be white-gray, clear enough to read, with uneven baseline and analog print texture. Pull-quotes should be much larger than body text, inside rough rectangular outlines or pasted torn-paper frames. Add hand-drawn border lines, faint column rules, scratches, smears, and random paper abrasions. Constraints: Preserve the exact Chinese text as much as possible, avoid adding new text, avoid color, avoid clean modern design, avoid illustrations or people, no logos, no watermark.

Draw with very simplified lines and design, with the quality of a doodle written in a textbook, on a piece of crumpled paper.

Create a clean black-and-white manga illustration on a plain white background showing exactly three anime girls in a tense confrontation, waist-up to mid-thigh framing, horizontal 4:3 composition. The center character is a short-haired cat-eared girl with pale bobbed hair, large animal ears, sharp confident eyes, and a simple oversized white T-shirt with jeans; she stands facing forward between the other two, arms stretched straight outward, one palm pressed to each girl's chest/shoulder as if physically stopping them from fighting, mouth slightly open as if scolding. On the left is a bespectacled girl with black hair in a messy low bun, wearing round glasses, bangs, an oversized sweater layered over a collared or ribbed neckline, and dark pants; she leans inward angrily with her mouth open, one hand raised near her chest. On the right is a short messy black-haired girl, wearing a loose oversized T-shirt tucked into high-waisted dark jeans; she leans inward aggressively, mouth open, one hand at her chest where she is being held back. Use expressive anime faces, dynamic body language, strong clean ink line art, delicate hatching and gray shading, glossy black hair highlights, minimal background, no text, no color except grayscale, crisp high-resolution manga sketch style.

Goal: Create a monochrome anime character reference sheet for a teenage high school boy with one full-body standing pose and exactly 4 separate bust expression variations. Canvas: Portrait-oriented white canvas, clean empty background, high-resolution black-and-white manga pencil/ink style with soft gray shading and sketchy line-art texture. Layout: Place 1 full-body character illustration on the left, occupying most of the height. Place exactly 4 bust portraits stacked vertically on the right, evenly spaced from top to bottom. No labels, no captions, no decorative background elements. Subject details: The character is a slim, average-height Japanese anime high school boy with messy layered black hair, slightly tousled bangs, sharp but youthful eyes, pale skin, and a protagonist-like presence. He wears a summer school uniform: short-sleeved white button-up shirt with subtle wrinkles, loosened dark necktie, gray straight-leg slacks, black belt with metal buckle, and glossy black loafers. The shirt is slightly rumpled and the tie hangs casually to create a natural everyday-student look. Full-body pose: The full-body figure stands relaxed with one hand in his pants pocket and the other hand lifted near chest height with loose fingers, facing slightly toward the viewer. His expression is calm and faintly smiling. Expression variations: Include exactly 4 bust portraits on the right: 1) bright laughing smile with eyes closed and open mouth, 2) angry shouting expression with intense eyes and open mouth, 3) sad or troubled expression with downturned eyes and a small frown, 4) confident mischievous smirk with narrowed eyes. Each bust keeps the same hairstyle, uniform shirt, and loosened tie, cropped around the shoulders or upper chest. Visual style: Detailed shonen manga character art, clean confident linework, delicate crosshatching, expressive hair strands, subtle grayscale shading on clothing folds, polished yet sketch-like character sheet presentation. Keep proportions elegant and natural, with strong facial expressiveness. Constraints: Use only black, white, and gray tones. Include exactly 5 discrete character drawings total: 1 full-body standing pose plus 4 bust expression portraits. Do not add text, color, props, school background, watermark, signature, or extra characters.

Create a richly detailed square fantasy illustration in the style of a vintage engraved storybook plate with hand-colored ink washes. In the foreground, show a young male traveler from the chest up, positioned left of center, with dark wavy hair with pale moonlit highlights, strong brows, tan skin, and an upward, contemplative gaze toward the starry sky. He wears a rough medieval cloak in warm brown over a pale hooded tunic or scarf, with heavy cross-hatching, etched shadows, and textured fabric folds. Behind him, create a vast nocturnal medieval city of tightly packed steep-roofed houses, narrow towers, chimneys, and tiny glowing amber windows. On the right side of the horizon, make an immense Gothic cathedral-castle rise above the city, with many spires, flying buttress-like details, needle towers, and warm lights in selected windows. The sky is deep indigo-black and filled with exactly 25 prominent golden eight-point stars of varied sizes plus dense tiny speckled starlight; place a large full moon in the upper left, cream colored and cratered. Add moody blue-gray clouds behind the cathedral and along the skyline. Include a stone parapet or wall along the lower right foreground to suggest the traveler is standing on a high overlook. Use a limited palette of midnight blue, ochre gold, sepia brown, cream, and muted gray, with dramatic moonlit rim light, old-world romantic fantasy atmosphere, meticulous linework, visible paper grain, no modern objects, no text, no watermark.

Use the uploaded image as the ONLY facial reference with strict identity preservation. Create an ultra-realistic graphite pencil sketch showing only one half of the face, positioned slightly off-center with the rest naturally fading into a clean white background. Preserve the subject's exact facial structure, proportions, skin tone, lips, nose, eyelashes, and unique identity. The visible eye is gently closed, the lips are slightly parted, and the facial edges dissolve softly into the paper. The hair flows dramatically into elegant smoke-like wisps and airy graphite strands, extending upward and outward with graceful movement, blending seamlessly into the white space. Use ultra-fine pencil strokes, realistic graphite texture, smooth tonal gradients, delicate cross-hatching, and deep black values in the hair for strong contrast. Maintain a minimalist fine-art composition with abundant negative space, no background elements, no accessories, no text, no color, and no frame. The artwork should feel dreamy, ethereal, emotional, and unfinished in a refined gallery-quality style.

Goal: Create a vertical monochrome Japanese manga page about a true-story style hamster father going overboard with a child’s summer homework poster. Canvas: Tall portrait manga page, about 9:16, sepia ink on warm off-white paper, hand-drawn crosshatching and pencil-like linework, thin black panel borders, nostalgic Showa-era storybook atmosphere. Layout: Use exactly 6 stacked horizontal comic panels. Interior setting is a cozy wooden room with floorboards, bookshelf, potted plant, curtains and window, art supplies, a large sheet of drawing paper, paint tray, bucket, brushes, and mugs. Keep all dialogue in Japanese speech bubbles and narration boxes. Characters: Two fluffy hamsters. The child hamster is small, round, cute, black glossy eyes, no glasses, drawing earnestly with a brush. The father hamster is larger and rounder, wearing small round glasses, holding a mug at first, then a brush, becoming increasingly intense and focused. Both are rendered as realistic-cute hamsters rather than humanoid mascots. Panel details: Panel 1 shows the child hamster facing a blank poster sheet on the floor, art supplies on the left, curtains and bookshelf behind. Add a vertical narration box on the right reading 「ハムスターの夏休みの宿題は『自由研究』の課題ポスターの提出が必要だった」 and a speech bubble from the child reading 「今年も緑化ポスターを描こう」. Panel 2 shows the child hamster drawing trees on the large paper while the father hamster with round glasses stands nearby holding a mug and watching. Panel 3 shows father and child side by side over the poster; father points or comments with a bubble 「ポスターか」 and the child replies 「うん、夏休みの宿題」. Panel 4 shows the father asking to borrow the brush, facing the child across the paper; include a question mark over the child’s head, father bubble 「ちょっと貸して」 and child bubble 「うん？」. Panel 5 is a close-up of the poster becoming extremely detailed: dense forest scenery with many trees and foliage, father’s paw holding a brush at the upper right, child bubble on the left 「おお……！お父さん上手！」. Panel 6 shows the father hamster completely absorbed, sweating and hunched over the poster, drawing an incredibly elaborate forest with dramatic speed lines; the child hamster behind him looks shocked and panicked. Include scattered art supplies, paint tray and bucket. Add a jagged speech bubble from the child reading 「お父さん……!!そしたらハムスターが描いたポスターじゃなくなっちゃう!!!お父さん!!お父さん!!」 and a bottom caption box reading 「ラストの２日で描き直した」. Visual style: Vintage Japanese newspaper manga, soft sepia monochrome, detailed fur texture, expressive faces, gentle comedy pacing, realistic room perspective, no modern digital coloring, no watermark. Customizable elements: The homework theme is greenery poster; the main characters are father and child hamsters; the father accessory is round glasses; the final poster subject is dense forest scenery; the bottom punchline caption is ラストの２日で描き直した.

Create a square 1:1 black-and-white 1930s rubber-hose cartoon scene with faded sepia toning and aged film texture. Center a cheerful anthropomorphic tuxedo cat named Milo performing on a small wooden theater stage at night, drawn with thick hand-inked outlines, rounded limbs, white gloves, oversized oval eyes, a big open smile, pointed ears, whiskers, and a white belly and paws. The cat is in an exaggerated squash-and-stretch dance pose: one leg crossed forward, tail lifted behind, left arm raised high holding a straw boater hat with a dark band, right arm stretched outward in a welcoming gesture. The setting is an old vaudeville street-stage corner: wooden floorboards curve across the foreground, four glowing footlights line the front edge, heavy theater curtains and a decorative proscenium column frame the right side, and a framed poster leaning on the right reads “MILO IN ONE NIGHT ONLY!” in large vintage serif lettering. In the background on the left, show a cobblestone alley with soft-focus old buildings, a tall ornate streetlamp, a small fire hydrant, and a hanging sign that reads “PUDDLE ALLEY” with a small paw print. Use a monochrome palette of charcoal black, warm gray, cream highlights, and sepia stains; add organic film grain, dust flecks, subtle scratches, dark rounded-corner vignette, uneven cel-paint shading, and controlled line boil. Keep the composition charming, theatrical, hand-drawn, and authentically vintage; avoid modern CGI, glossy 3D rendering, bright color, clean vector edges, or contemporary typography.