Try it Now ：ride.youware.app

PROMPT： Build a browser experience in Three.js called STILLWATER. Tone: a moonlit swamp you get lost in. Not a game with enemies. Not photoreal Unreal. A quiet, expensive-looking web world where the water reflections are the feature. People should stare at the water for an unhealthy amount of time. SETTING - Location title: THE DEEP SWAMP - Time on the HUD: 19:26 - First named place: Heron bend - Tagline under the place name: "Leave a little room for the wild." - Discovery toast when you arrive: "Discovered: Heron bend" WORLD A flooded cypress swamp at moonrise / late dusk. - Tall knobby-kneed trees standing in black-green water - Spanish moss hanging in long strands - Lily pads clustered along the banks - Narrow winding channel that opens into a wider bend - Thick volumetric fog, teal-green distance, purple-pink cloudy sky - A bright moon with a long broken reflection path on the water - A few birds crossing the sky - Warm cabin light from the boat punching through the gloom WATER (do not cheap out) This is the hero. - Real-time reflections of trees, moon, fog and boat lights - Gentle swell, not ocean waves - Lily pads that sit on the surface and bob - Shoreline foam / dark tannin water near roots - Screen-space or planar reflections good enough that the moon path feels cinematic - Keep 60fps. LOD the trees, instanced foliage. BOAT A small weathered cabin skiff / workboat. - Hull number 86 on the stern - White cabin, dark blue hull, warm interior lamps - Idle drift through the channel, optional slow guided tour - HUD speed around 15.9 KNOTS - Mode label: GUIDED DRIFT Player can look around. Boat can be followed from a cinematic chase / side orbit. CAMERA - Start on a three-quarter of the boat in the trees - Drift behind the stern down the moonlit lane - Occasional side slide past a foreground trunk - Drag to look - Optional PHOTO MODE Feel like a nature documentary, not an FPS. UI — editorial, not gamey Top-left: small mark + STILLWATER Top-center: THE DEEP SWAMP / 19:26, a compass heading (e.g. 314°) Top-right: quiet utility icons Bottom-left: EXPLORING STILLWATER Heron bend Leave a little room for the wild. 15.9 KNOTS GUIDED DRIFT Bottom-right: PHOTO MODE, fps, Pause Center-bottom: small toast "Discovered: Heron bend" Tiny hint row: shaders / water / drag to look / photos / wildlife Look: dark filmic grade, muted greens, magenta clouds, one moon highlight. Taste over realism. No bloated debug GUI. TECH Three.js in the browser. Procedural / instanced nature. Custom water shader. Fog. Soft shadows or baked-looking dusk lighting. No asset-store swamp pack if you can author it. DO NOT add combat, inventory, jump scares, or a treasure hunt. Something can lurk underwater later — not now.

1、Try it now ： youware.com/app?utm_medium=x… 2、Full Prompt: [Objective] Redraw the person/character in the image provided by the user as a minimalist 2D robot avatar with black capsule-shaped eyes. Extract the appearance features needed to identify the person from the original image; the facial structure, eyes, expression, composition, and coloring follow the specifications below. The Grok robot avatar in this document refers to this visual specification. [Extract Information from the Original Image] Confirm the skin tone/facial base color, hair color, and hair silhouette of the subject to be converted. Hair length, parting, curliness, signature bangs, and tied-up hairstyles should follow the original image. From the signature ears, hats, glasses, beards, accessories, and mechanical parts, select the elements essential for identifying the subject. Keep the base colors, and streamline the core features whose forms need to be preserved to a maximum of 3 items. Prioritize preserving large silhouettes and discard small details. Do not force skin tone and hair into fixed uniform colors. If the hair is missing/obscured, keep it as is; do not add bangs, accessories, or mechanical parts that do not exist in the original image. Do not replicate the original image's facial expression or realistic facial structure. For complex clothing and equipment, retain only the parts essential for identification. Even if there are additional style reference images, the character's appearance information can only be taken from the original image to be converted; you must not copy the skin tone, hair color, hairstyle, or accessories from the style reference images. 【Face】 Combine the simplified hair and recognizable features onto the large, round robot face. The cuteness should not rely on facial expression decorations, but rather be conveyed through rounded proportions + a tilted composition. The face is based on the original image's skin tone/base color, rendered as large, smooth color blocks. The cheeks and chin blend softly, avoiding a pointed/angular chin, and no realistic bone structure is depicted. Do not draw a mouth or nose. Do not add a smiling mouth, dot mouth, or cat mouth. Add small, low-saturation light oval blush on both cheeks that matches the skin tone. Draw the blush as flat color blocks with no outlines and no highlights. Leave ample blank facial space around the eyes and blush. If glasses or a beard are core identifying features, they may be kept in their simplest form; glasses must not cover the eyes, and a beard must not be used to depict a mouth or realistic facial structure. [Eyes] The eyes are precisely drawn as two nearly pure-black monochrome capsule shapes. When the face is upright, they are vertical elongated bars with rounded ends. The vertical length is approximately 2.5 to 3 times the horizontal width, and the two eyes are identical in size and parallel to each other. The long axis of each eye is perpendicular to the line connecting the centers of both eyes. Maintain this arrangement while tilting the head and both eyes together according to the direction and angle specified in [Composition]. Do not draw horizontal lying bars or closed-eye styles. Each capsule is completely filled with a solid color. The shape itself is the eye; do not draw a separate eyeball or pupil inside it. Do not draw irises, eye whites, reflections, highlights, gradients, eyelashes, eyelids, eyebrows, or border decorations. Do not draw lines resembling the numeral "1" with a hook/base. Compared to the eye shape and color in the original image, this specification takes higher priority. 【Composition】 1:1 square canvas, place one character. Greatly enlarge the face and hair/head outline, occupying most of the frame. Composition: The character tilts their head in the lower-left corner of the frame, looking at the camera. The head is rotated clockwise by about 15–20 degrees, making the eye on the left side of the frame appear slightly higher than the right eye. The face, both eyes, hair, and attached accessories all maintain the same tilt angle. The left side of the head and the lower edge are naturally cropped by the frame boundary. The chin is close to the bottom edge of the frame, with part of it cut off; the upper-right corner of the frame retains dark background negative space. Both eyes must be fully visible and must not be obscured by bangs or accessories. Do not use a reduced-head, centered ID-photo-style composition, and do not use a left-right symmetrical composition. Do not draw the torso or hands. Only when identification requires it, retain a small section of neck or collar at the bottom of the frame. Enlarging the face + edge cropping is an intentional design. [Hair · Accessories · Coloring] Hair does not need fine strands; simplify it into a few large, smooth color blocks. Preserve the bangs direction, length feel, and overall silhouette of the original image. Adopt a minimalist 2D style with almost no outer contour lines, relying mainly on color blocks. Do not distinguish forms with thick black outlines; instead, rely on color differences between adjacent blocks. Use the representative colors from the original image for flat, soft coloring. Apply only one layer of broad, weak shadow over the base color; if the hair needs highlights, add at most 1–2 large highlight blocks. For accessories and mechanical parts, keep only the outlines and main connecting structures. Omit tiny screws, wiring, circuit boards, dense panel lines, and complex patterns. When scaled down to a small avatar, the two black capsule-shaped eyes and the core silhouette of the original image are still recognizable at a glance. [Background and Prohibited Elements] The background uses a nearly pure black dark charcoal solid color that fills the entire canvas. Do not add background objects or patterns. Prohibited: circular frames, badge borders, text, numbers, logos, watermarks, speech bubbles, exclamation symbols, sparkles, particles, halos, lens flares. Avoid: real-life photos, 3D rendering, oil painting texture, rough sketch lines, excessive reflections, complex light and shadow, detailed hair strand rendering, overly dense accessories. [Conflict Handling Rules] When specifications conflict, execute according to the following priority: 1. Two black capsule eyes without decoration 2. A rounded robot face without a mouth or nose 3. A tilted close-up composition with both eyes fully visible 4. The base colors and core identifying features of the original image 5. All other details If the bangs cover the eyes, adjust the length, width, and position of the bangs while preserving the overall direction. If the core accessory is cropped and completely disappears, fine-tune its size and position to ensure it remains recognizable; this process must not add features that do not exist in the original image. [Execution and Follow-up Modifications] When the user requests generation/conversion, directly output the finished avatar without adding extra explanatory text. If only one image to be converted is uploaded with no additional questions, handle it as a basic conversion. If the image to be converted cannot be read, request that the user upload an image. If there are multiple people in the image and no conversion target is specified, confirm which person needs to be converted. If the request is only to modify the prompt, explain specifications, analyze results, or ask about usage, reply in text without generating a new image. Production specifications are provided only when the user requests them, and specification text must not be placed inside the image. For subsequent modifications, change only the parts specified by the user; style specifications and character features for which no modification request has been made remain unchanged. Do not falsely claim that the image has been generated or verified unless it has actually been generated and verified.

Try it Free : youware.com/app?utm_medium=x…

Try it: youware.com/app?utm_medium=x…