App / Web Design

2D flat vector fashion illustration, unveiled Middle Eastern woman, full body, wearing wide-leg trousers in mustard yellow with geometric print, embroidered cream blouse with floral motifs, minimal shadows, clean bold outlines, soft beige background, editorial fashion pose, 3:4

Modern fashion line art illustration, unveiled Middle Eastern woman, single-weight black linework, flat color blocks in ochre and sage green, wide-leg patterned trousers, embroidered off-shoulder blouse, negative space composition, soft cream background, walking pose, 3:4

Provide 5 layout ideas for this living room. Output one image for each with different variations.

Goal: Create a dark-mode desktop web app screenshot for HeliosGen, an AI image/video generation dashboard, shown in a wide 16:9 browser-like canvas. Canvas: 1200×675 style screenshot, very dark navy/black interface with subtle dotted grid texture across the main workspace. Use a clean modern SaaS UI aesthetic, thin dividers, small muted gray text, and teal accents. Layout: A narrow left sidebar occupies about 10% of the width, with the main workspace filling the rest. At the top of the main workspace, show two small tabs: “Generated” selected and “Uploaded” inactive. Beneath the tabs, display exactly 5 generated image thumbnails in one horizontal row, aligned along the top, each separated by thin borders. Sidebar details: Top-left logo text reads “HeliosGen” with a small teal emblem. Include exactly 6 primary navigation items with icons: 1) Image selected, 2) Video, 3) Workflow, 4) Assets, 5) Chat, 6) Settings. Below that, show a small “Folders” section with exactly 1 folder row labeled “All works,” then an empty-state area reading “No chats yet.” At the bottom-left, add two tiny stats/icons resembling “1.8k” and “220.” Thumbnail row: Show exactly 5 thumbnails from left to right: 1) an ornate amber luxury perfume bottle on a dark rock in a golden desert at sunset, 2) a rounded amber perfume bottle with ornate gold cap on a stone slab in desert dunes at sunset, 3) a square amber perfume bottle with a crescent-shaped cap on a black rock in desert dunes at sunset, 4) a single red apple centered on an off-white studio background, 5) a smaller red apple sitting on a white table in a minimal white studio scene. The first three thumbnails should feel cinematic and warm; the last two should be minimal product-photo tests. Bottom prompt panel: Near the bottom center of the workspace, include a floating generation control panel with rounded corners. On the left of the panel, show a small square preview tile labeled “IMAGE 1:1.” In the main text area, include the prompt: “Luxury Saudi perfume bottle on black stone, desert dunes in the background at sunset, premium commercial product”. Along the bottom of the panel, show compact controls reading approximately “Nano Banana Pro,” “2K,” “1:1,” “1/4,” “Multi,” and “JSON (4.14k),” plus a teal send/generate button at the right. Visual style: Crisp UI screenshot, high contrast, minimal glow, fine dotted background, realistic generated-image thumbnails, no browser chrome, no extra popups, no people, no watermark.

Please turn each uploaded travel photo into a separate 3:4 vertical "Retro Pixel Industrial Travel Archive" editorial poster. Each photo is output individually, without multi-photo collages. This style is not about directly pixelating the entire photo, nor is it about putting a generic computer frame on the photo. You must first extract 3 to 7 real objects that define the scene's identity from the original photo, then transform them into pixel sprites, local previews, data indices, and structural slices, and reassemble them into a fully functioning old computer software interface. The top portion, about 30% to 38% of the screen, retains the clearly recognizable original photo. Accurately maintain the identity of the subject, architectural structure, quantity, observation angle, spatial relationship, real texture, natural light and shadow, and local colors. Only apply slight artistic publication color grading and thin film grain treatment; do not illustrate, reconstruct, or change the original photo. Below the photo, maintain a 7% to 10% charcoal black or dark olive "breathing zone", in which a readable pixel title of 1 to 4 English words is added. The title should come from the actual structure or theme of the photo, for example: HEAVEN AXIS ROOF SYSTEM LAKE PAVILION CANAL OBJECTS The lower part, about 50% to 60% of the screen, constructs a complete late 1980s to early 1990s graphic workstation software interface. The primary background color must be a visible deep forest green, dark cyan-green, or faded olive green, not pure black. The computer area must simultaneously feature: 1. A complete main application window occupying the primary area below; 2. A narrow frame in old ivory or tobacco gold; 3. A system menu bar spanning the top of the entire application; 4. Menu text used verbatim: FILE EDIT VIEW DATA TOOLS WINDOW HELP 5. At least one selected menu; 6. An expanded drop-down menu directly connected to the selected menu; 7. Drop-down menu options can include: IMPORT… EXPORT… LAYERS… FILTER… COLOR MAP STATISTICS… PRINT… 8. At least three overlapping functional sub-windows; 9. Each sub-window has a title bar, close button, and specific function; 10. At least one window has clear scroll bars, arrow buttons, and sliders; 11. At least one object index, color palette, histogram, or status window. Analyze the photo first and list objects that can be separated. For example: Traditional architecture photos: Main roof, secondary roof, dougong color bands, gable walls, steps, railings, red walls. Garden photos: Pavilions, rocks, lake shores, cruise boats, branches, roof fragments. Water town photos: Stone bridges, wooden houses by the water, balconies, tiled roofs, water surface, reflections, shorelines. People or transportation photos: People, vehicles, roads, building facades, landmarks, and direction of action. Convert these real elements into low-resolution pixel sprites or structural modules. Retain the silhouette, direction, quantity, and signature colors of the objects, but remove tiny textures. Re-adjust the size and position of the objects in the central workspace: the main object can be enlarged to become a visual anchor, and other objects are arranged around it like movable layers. Do not follow the original...

Glass studio, holographic canvas, mixed tungsten and cyan light.

Goal: Create a clean screenshot-style composition showing an AI image-editing conversation about refining a simple mascot bear drawing. Canvas: Wide horizontal canvas, about 1200×960 px, with a very pale gray-white background and lots of empty space. The layout should feel like a cropped social-media or image-generation interface screenshot, not a polished poster. Layout: Include exactly 2 white rounded image cards containing the same minimalist bear character: 1 smaller card in the upper-right area and 1 larger card in the lower-left/center area. Place exactly 1 light-blue rounded chat bubble beneath the small upper-right card, horizontally centered under it. Add exactly 2 semi-transparent circular interface buttons over the bottom of the large card: 1 gray button at bottom-left labeled in Japanese and 1 small gray share/upload icon button at bottom-right. Text content: The single chat bubble should read 頬の横から首にかけてのあたりを、もっと細くしてください。. The bottom-left overlay button should read 「編集」. Do not add any other text. Subject details: The bear is a cute, simple, hand-drawn white bear mascot with a slightly awkward neutral expression. It stands upright facing forward with a thick black sketchy outline, rounded ears, small inner-ear marks, wide circular eyes with black pupils, a large black oval nose, a tiny straight mouth, pink circular blush cheeks, short arms hanging down, stubby legs, and small toe lines. The fur should be off-white with subtle paper-like texture and light gray shading along the right side. The larger lower bear should have a narrower neck and upper torso from cheek level down toward the shoulders, while still looking a little chunky and handmade. The smaller upper-right bear should appear as a prior version, slightly more compact and with a narrower body. Visual style: Minimal Japanese UI screenshot aesthetic, soft rounded corners, flat light-gray background, simple black marker line art, warm off-white paper texture inside the bear cards, no strong shadows except very subtle card separation. Keep the image sparse and asymmetrical, with the upper card far to the right and the larger card lower and more central-left. Constraints: Use exactly 2 bear drawings, exactly 1 chat bubble, and exactly 2 overlay buttons. Preserve the Japanese text exactly where specified. Avoid extra icons, watermarks, browser chrome, usernames, timestamps, or decorative elements.

Create a wide cropped comparison graphic showing two side-by-side image-generation quality results on a plain white background. The canvas is an ultra-wide horizontal strip, about 5:1 aspect ratio, cropped tightly so only the top portion of each result is visible. At the top left above the first crop place the bold black uppercase label “MEDIUM”; near the upper center above the second crop place the bold black uppercase label “HIGH”. Each of the 2 comparison panels shows the same fitness-class style tiled layout: a photographic band at the top with gym equipment and dark exercise machines, underneath a deep teal rectangular title bar with large bold white Japanese text 有酸素. Use thick white borders and sharp diagonal white dividers between tiles, giving the layout a dynamic slanted collage look. Count exactly 2 main visible teal title tiles with the full text “有酸素”, one in each panel, plus exactly 2 partially visible neighboring teal tiles at the right edge showing only the first character or fragment ス. A thin lower white divider and the top edge of another teal row are barely visible along the bottom, cropped off. Emphasize the artifact being compared: around the white Japanese letters on the solid teal backgrounds, include subtle uneven brightness and saturation patches, faint haloing, and mottled texture, with the “HIGH” panel slightly cleaner but still showing visible nonuniformity. Keep the composition as a technical screenshot/comparison crop, not a polished poster. Use crisp sans-serif typography, high contrast, no extra captions, no watermark.

Goal: Create a character design variation sheet for a cute white polar bear mascot, showing exactly 16 discrete bear designs arranged in a clean 4-by-4 grid. Canvas: Square image on a plain white background, like a screenshot of an image-generation variation gallery. Use faint tile divisions between the 16 panels, with soft off-white spacing and no decorative border. Layout: Four rows and four columns, each tile containing one full-body or cropped white bear character centered in its panel. Keep the bears similar but not identical, varying the body silhouette, snout shape, ear placement, cheek marks, posture, and line wobble. Include a small translucent interface overlay on the second bear in the first row with three stacked labels: “Vary Subtle”, “Vary Strong”, and “Animate”. Subject details: The character is a hand-drawn, childlike white polar bear mascot with a simple upright stance, round staring eyes, small rounded ears with pink inner ears, a tan or peach muzzle, black nose, tiny paws, and occasional pink cheeks. The body should be slightly tubby and rectangular-to-pear-shaped, with short arms hanging down and small feet. Use black uneven marker-like outlines, simple flat coloring, and sparse pale beige fur strokes on some bears. Count and visible variations: Show exactly 16 bears total. Row 1: 1) tall rectangular bear with pink inner ears and long peach muzzle, 2) similar bear with blush cheeks and UI overlay across the legs, 3) shaggy narrow bear with oversized sideways salmon muzzle, 4) clean rounded bear with tall vertical tan muzzle. Row 2: 5) stocky bear with tiny side tail and gray-black nose patch, 6) taller bear with blush cheeks and drooping black nose, 7) smaller furry bear with round red cheeks and horizontal snout, 8) rounded bear with open smiling black mouth inside tan muzzle. Row 3: 9) simplified smooth bear with large side-pointing black nose, 10) upright bear with red cheeks and dark oval nose, 11) slim bear with tiny muzzle and blush cheeks, 12) pear-shaped bear with side-facing snout and one arm visible. Row 4: 13) cropped upper body bear with long oval muzzle, 14) cropped upper body bear with pointed tan muzzle and red cheeks, 15) cropped upper body bear with tilted oval muzzle and light fur marks, 16) cropped upper body bear with curled ears, red cheeks, and small dark nose. Visual style: Cute naive doodle illustration, loose black ink contour lines, minimal shading, warm off-white fur, soft pink accents, playful imperfect proportions, whimsical mascot exploration sheet. The art should feel like an iterative concept sheet moving toward a charming polar bear character. Constraints: Do not add scenery, props, logos, or extra characters. Keep the background white and the grid clean. Preserve the exact 16-panel count and the three overlay labels on the first-row second panel. Avoid realistic fur, 3D rendering, or polished vector smoothness.

Elegant editorial illustration of a [SUBJECT], combining delicate contour drawing with one or two bold solid-color shapes, selective areas intentionally unfinished, refined balance of detail and emptiness, plain white background, contemporary art-magazine aesthetic.

Goal: Create a tall, narrow black portfolio case-study preview strip showing three vertically stacked AI-generated mockup thumbnails, each with a small white label above it. Canvas: Very tall vertical canvas, approximately 207 × 975 px, with a solid near-black background and generous black margins. Minimal editorial/portfolio styling, like a website column of project thumbnails. Layout: Stack exactly 3 project entries from top to bottom, aligned slightly left of center with consistent left margin. Each entry has one small white text label above a rectangular image thumbnail. Use large vertical gaps between entries. The thumbnail widths are similar, but their heights vary slightly; all images are portrait-oriented. Project entries: 1) Label: “1inch-01”. Thumbnail: a moody product-style photo of a small beige cardboard cube or box sitting on dark asphalt in strong sunlight, casting a long hard shadow. A wooden structure or pallet edge appears along the upper left side. The box top has delicate printed line-art graphics and small text, viewed from above at an angle. 2) Label: “mrNick-01”. Thumbnail: a clean studio render of a translucent electric-blue human figure/mannequin wearing an oversized T-shirt and pants, standing against a light gray background. The figure holds a white shopping bag in the left hand. The shirt has vertical white branding text reading “mrNick” along the right side. 3) Label: “GLAZURE_GLASS-01”. Thumbnail: a bright candy-colored product poster dominated by hot pink. A glossy pink-red donut-shaped glaze ring sits on a pink product box, covered with colorful sprinkles. More sprinkles scatter across the surface. Large bold white Cyrillic-style lettering appears near the bottom of the box/poster. Typography: Labels are small, plain sans-serif, white or light gray, left-aligned above each thumbnail. Preserve the exact visible labels. No additional captions, navigation, icons, borders, or interface elements. Visual style: High-contrast black gallery background, polished website mockup feel, sharp realistic thumbnails, clean spacing, premium design case-study presentation. Constraints: Include exactly 3 labeled thumbnails; do not add extra projects, buttons, browser chrome, watermark, or decorative elements.

Please transform each photo I upload into an individual high-end design poster, outputting each photo separately without stitching multiple images. The overall composition uses a 3:4 vertical format, with the top and bottom sections strictly 1:1 in height, each occupying 50% of the screen. The upper part retains the original photo, maintaining the subject's identity, structure, posture, realistic texture, natural light and shadow, and original color atmosphere, with only slight professional color grading to give it the texture of an art magazine, independent publication, or exhibition image. The environment background can be naturally extended to fit the frame, but the subject must not be stretched, distorted, or changed. The lower part extracts the most recognizable subjects, local elements, action clues, object details, and narrative relationships from the photo, reconstructing them into a visual system of 3x3 modular icon grid + naive hand-drawn doodle illustrations + crayon/colored pencil grainy texture + handwritten text. Do not trace the original image completely or create realistic illustrations; instead, compress complex information into 9 visual units most worth remembering: these can be the subject itself, local features, personal belongings, plants, food, modes of transport, gestures, emotional symbols, or small memory points in the scene. Each unit should be a semantic extension of the same image above, making people feel at a glance that they belong to the same photo's 'memory checklist'. The composition uses an implicit 3x3 loose grid. The nine-square grid serves only as the underlying order and does not need to be drawn too neatly; the position, size, angle, and placement of each icon can be slightly shifted, creating a sense of loose grid / organic grid that is orderly but not mechanical. A short handwritten title can be added at the top, along with a few relaxed wavy lines, stars, or symbols; a tiny handwritten caption can be added at the bottom, making the whole thing look like a page from a private notebook, visual diary, or collection sheet. White space must be sufficient, and the layout should be relaxed, cute, restrained, and not cluttered. The art style uses Naïve Hand-drawn Doodle Illustration: simple forms, a bit naive, with slightly shaky outlines of uneven thickness that are not completely closed, retaining intentional imperfections. The coloring should not be filled too full, allowing paper texture, white particles, and rough edges to be seen. A mixture of thin black outlines, colored pencil/crayon filling, and small local color blocks can be used, not relying on realistic light and shadow but establishing graphic relationships through flat color / spot color. If grid auxiliary lines appear, they should be extremely faint, like pencil drafts lightly drawn, rather than computer-drawn regular tables. The color scheme uses a low-saturation retro candy palette, with warm off-white coarse-textured paper as the base, keeping colors soft, light, friendly, and high-end. It can refine and translate colors from the original image into comprehensive color relationships like sage green, mint green, pastel blue, cobalt blue, cream yellow, dusty pink, strawberry pink, and coral orange: usually with blue-green as the primary color, yellow-pink for object filling, and orange-red for very little emphasis. The overall control is a large area of off-white background, moderate blue-green primary color, small areas of yellow-pink secondary colors, and minimal orange-red accents, making the picture rich but not messy. Add a layer of minimal hand-drawn red annotation elements, such as circles, arrows, hearts, starbursts, small crosses, wavy lines, or emphasis marks, transforming the work from a regular icon page into a more editorial and personal visual diary. However, these annotations must be few and precise, serving only as a second touch, not overpowering the main subjects. The text content and language are not restricted; a few truly meaningful words should be freely generated based on the photo's theme, mood, location, action, or sense of life. Use a light, loose, handwritten font with slight writing pauses and spacing shifts for titles and descriptive text, making the writing look like casual notes naturally written on paper rather than commercial typography titles. The overall text remains sparse, small, with ample white space, forming a natural text-image mix with icons and annotations. The overall presentation gives a visual temperament of being naive, relaxed, retro, healing, light, friendly, and having a sense of editorial design, like a seriously collected private notebook, happiness list, or life observation page. Avoid clean vector feelings, realistic light and shadow, complex textures, heavy shadows, overly neat UI icon feelings, commercial template feelings, and children's cartoonization.

Elegant abstract illustration of [attached image] constructed from a single flowing ribbon-like form, continuous curves suggesting movement and volume, subtle dimensional shading, restrained [color choice here] palette, graceful negative space, premium brand-art aesthetic, sophisticated simplicity, centered composition.” 9:16

Generate a bifold poster with mature editorial design and exhibition visual quality. Instead of simply cutting the frame into two columns, let the left and right visual areas express different states of the same theme, and let the "middle boundary" be where the change actually happens. The left and right areas use an unequal layout (40:60, 45:55, 55:45) based on the weight of the subject, rather than a mechanical 50:50. The left side is responsible for establishing the starting point or original state, and the right side is responsible for showing the transformed result, for example: Front of a work → structural and production path behind it; Design sketch → real space after completion; Sound source subject → vibration and sound field diffusing outward; Real entity → rubbings, traces, or images on paper. The most important part is the central axis translation. Do not use an obvious vertical line, but choose a core element to pass through the left and right areas and undergo continuous changes as it crosses the axis. For example: petals gradually turning into stitches and threads; architectural line drawings gradually turning into real walls; object vibrations gradually diffusing into voiceprints; stone carvings gradually flattened into black ink rubbings. This change must be continuous and natural, allowing viewers to immediately understand the causal, process, or translation relationship between the two sides, rather than two unrelated images spliced together. Typography also participates in the left-right relationship, but all text must belong to the work itself. Use real titles, subtitles, short sentences, and exhibition info; avoid template placeholder text like "left-right composition" or "design case." Reduce info on the visually heavier side; the emptier side can carry more titles and text, achieving visual balance through font size, density, and position. Control colors within 2–4 main palettes. The two sides can have distinct brightness, temperature, or material differences, but at least one color, texture, or visual element must cross the axis to ensure unity. Reading order: first see the two visually distinct states; second, discover the connection and change at the axis; third, understand "why the left becomes the right"; finally, read the title and information. Overall requirements: two visual domains with their own roles, a clear translation process in the middle, visually balanced despite being unequal, with both content logic and a sense of a mature work.

Goal: Create a cinematic horizontal website/social banner about AI image generation and accurate text rendering, with a moody studio atmosphere and clear Portuguese typography. Canvas: Wide 2:1 banner, approximately 1200×600 px. Dark, soft-focus photographic background with strong depth of field. Leave the left half for text and the right half for the visual metaphor. Background and subject: A dim artist studio with cool gray-blue lighting, a blurred window on the far left, concrete wall, soft shadows on the floor, and an easel on the right holding a blank white canvas. In the upper center-right, show a delicate mechanical drawing arm or robotic brush holder reaching toward the canvas, holding a thin brush that has a single dark blue paint droplet at its tip. The canvas should be bright white and mostly empty, slightly angled, with a subtle shadow. Use realistic lighting, shallow depth of field, and a premium editorial tech aesthetic. Layout: Place all main text on the left side over a dark translucent gradient overlay for legibility. Use exactly 3 small rounded pill tags above the headline, aligned horizontally: “IA”, “MUSE IMAGE”, and “NOVIDADE”. Below them, place a large bold headline in two lines: “A IA aprendeu a pensar” on the first line and “antes de desenhar” on the second line. Highlight only the word “pensar” with a vivid purple rectangular label behind the word, white text on purple. Under the headline, add one smaller italic subtitle: “O texto deixou de ser o calcanhar de Aquiles. Falta todo o resto.” Add a small website URL in the bottom-right corner: “www.macareno.net”. Text content: Use A IA aprendeu a pensar antes de desenhar, with the word pensar highlighted in purple. Use O texto deixou de ser o calcanhar de Aquiles. Falta todo o resto.. Use IA, MUSE IMAGE, NOVIDADE. Use www.macareno.net. Visual style: Minimal, polished, cinematic, realistic, high contrast between white typography and dark background, with a modern tech-news landing-page feel. Typography should be clean sans serif; headline extra bold, subtitle light italic, tags uppercase with letter spacing. Keep text sharp and perfectly spelled. Constraints: Include exactly 3 pill tags, exactly 1 highlighted word, exactly 1 subtitle line, exactly 1 URL, exactly 1 easel canvas, exactly 1 robotic drawing arm, exactly 1 brush, and exactly 1 visible paint droplet. Do not add extra logos, people, icons, or additional text.

Create a realistic architectural visualization comparing two 3D-generated ottoman stools in an interior showroom scene. Canvas: wide landscape 16:9 render, camera at low eye level looking slightly downward. Scene: two small Barcelona-style footstools placed side by side on a dark charcoal tiled floor, in front of a tall glossy stone wall with dramatic brown, cream, rust, and gold onyx/marble veining; a narrow strip of green-tinted glass or window appears at the far right edge, with pale exterior floor tiles visible beyond. Subjects: exactly 2 footstools: left stool is the HD version, slightly smaller and lower, with a white tufted square cushion divided into a 4-by-4 grid, rounded soft edges, light gray leather straps underneath, and reflective polished metal X-shaped legs; right stool is the Smart Mesh version, slightly larger and cleaner, with a thicker smooth white cushion, parallel white underside straps, and gray polished X-shaped metal legs. Add thin black 3D viewport guide lines or wireframe axis lines crossing through and around both stools, including vertical and horizontal alignment lines, as if shown in a 3D modeling comparison viewport. Materials: white leather cushions with subtle seams and soft highlights, chrome legs with reflections, dark matte floor tiles with faint grout lines, glossy veined stone wall. Lighting: soft indoor studio lighting, moderate shadows, realistic but slightly CGI-rendered look. Composition: left stool around one-third of the frame, right stool around two-thirds, both facing forward at a slight angle, enough floor visible in front, marble wall filling the background. No people, no labels, no UI panels, no watermark.

Create a centered, high-end 3D render of a single translucent glass orb on a pure white studio background. The orb is a perfectly smooth sphere made of thick glossy crystal, with a dark smoky interior and layered, flowing ribbon-like waves suspended inside it. The internal ribbons curve horizontally in elegant S-shaped bands: electric cyan and deep blue across the upper half, molten gold and orange through the middle, hot magenta and violet through the lower half. Add bright neon light streaks, tiny star-like glints, and caustic refractions following the curves, as if glowing energy is trapped inside the glass. Use transparent glossy crystal glass, electric blue, cyan, gold, orange, magenta, violet, and pure white. Include large soft white specular highlights near the upper left and upper right of the sphere, a crisp luminous rim around the edge, subtle internal reflections, and a soft blurred colored shadow underneath in blue, purple, and pink. The composition should be minimal and product-shot-like, with the sphere occupying most of the square frame, no text, no logos, no extra objects, ultra-detailed, polished, futuristic, luminous, photorealistic, octane-render style.

Goal: Create a realistic vertical smartphone screenshot of a Telegram chat showing an AI bot successfully generating an image, with the generated image embedded in the conversation. Canvas: Tall mobile screenshot, 9:16 aspect ratio, approximately 576 × 1024 pixels. Dark mode Telegram interface with black doodle-pattern wallpaper. The screenshot should look like it was captured on an iPhone. Top status and header: At the very top show the iOS status bar with time “6:50” on the left, a blue “TELEGRAM” pill centered near the top, and cellular/Wi‑Fi/battery icons on the right. Below it, show the Telegram chat header with a circular back button on the left, the chat title “Arcturus Alpha” in white, the subtitle “bot” underneath, and a small circular avatar on the right showing a golden bull or constellation-like emblem on a dark blue background. Conversation layout: Use exactly 3 visible chat messages: 1. A large dark purple rounded text bubble at the top, partially cropped at the very top, containing white text: “four, coming up — same minimal test as last time so we're changing exactly one variable:]]” then a blank line, then “Remark: Attempt four — same test, now with the missing await in place...” with timestamp “6:48 PM” in small gray text at the lower right of the bubble. 2. A media message beneath it with a rounded rectangular image preview and a caption bubble below. The image preview shows a luminous golden constellation ox/bull drawn with thin glowing lines and star points, standing in profile against a deep navy starfield with faint Milky Way texture. The bull has long curved horns, a lowered head, one front leg raised, and connected constellation nodes across its body. Below the image, include the caption text: “gpt-image-2 smoke test — the constellation ox, back in business.” with timestamp “6:49 PM” at the lower right. The message bubble is dark purple with rounded corners. 3. A bottom incoming message bubble partially covered by the input bar, containing: “[[Private: 🤍 Arcturus> 🎉 It worked! That missing await was the culprit — image generated, file” with the rest cut off by the bottom UI. Make “worked!” bold-looking if possible. Bottom UI: Show Telegram’s message composer overlay at the bottom. Include a blue rounded “Menu” button on the left with a hamburger icon, a paperclip attachment icon, a dark rounded input field labeled “Message”, a small circular icon inside the field near the right, and a microphone button on the far right. Add a floating circular down-arrow button near the lower right of the conversation, just above the input area. Visual style: Photorealistic app screenshot, crisp Telegram dark mode UI, white text, muted gray timestamps, dark translucent purple message bubbles, high contrast. Wallpaper should include faint doodles such as rockets, planets, stars, pizza, animals, and other Telegram-style line icons. Constraints: Keep all visible text exactly as specified. Use exactly one generated image preview inside the chat. The constellation ox image should be square-ish and occupy the center-left width of the chat. Do not add extra messages, reactions, usernames, watermarks, or unrelated UI panels.