Make Up

Cup Dreams

"Vertical premium sports memorial montage poster, 8K ultra HD, professional portrait photography and commercial digital art style with cinematic Rembrandt lighting. Dark navy blue/sky blue gradient background (#0A1A2F/#1E90FF) with thick matte base, fine blue brush splatter texture, rain particles, mist, stage light beams, lens flare and subtle film grain, simulating physical printed poster texture. Cool premium tone, no stray colors or template feel. 【Mandatory Subject Rule】 All figures in the frame must strictly follow the facial features and appearance of the female character in your reference image, 100% unchanged, no modification, deviation or replacement; all clips/afterimages are the same subject with 100% identical facial features, hairstyle, expressions and demeanor. Uniformly wear classic blue-and-white striped No.10 soccer jersey with high-simulation heavy knitted fabric, three-dimensional clear texture and natural hanging folds. Complete forward prints of minimalist ""VICTORY"" emblem and No.10 number. Matched with same-color shorts, light blue socks and professional soccer cleats, all clothing details are intact. 【Composition & Layers (Enhance virtual-real fusion, no stiffness or duplication)】 Four strict layers with unchangeable order: Bottom layer: #0A1A2F/#1E90FF gradient background + hazy rainy night stadium, starry smoke, stage light beams, rain particles, lens flare and film grain for full atmosphere; Middle layer afterimage 1: Cool semi-transparent emotional close-up (excited roaring celebration expression, low-saturation blue tone treatment, ink-wash/misty feathered edges, fixed 40% transparency, 15% reduced brightness, forming an emotional/light contrast with the foreground); Middle layer afterimages 2&3: Colorful shallow depth of field blur + slight motion blur victory pose clips (front finger-pointing celebration, back arms-spread celebration, full color retained, 30% reduced sharpness, brush/misty feathered edges, 10% reduced brightness, 1/3 size of the main portrait, distributed on the right side of the main portrait and slightly covered by the foreground, forming a triple contrast of virtual-real/light/sharpness with the main portrait); Foreground layer: Oversized main portrait on the left (highest sharpness in the frame, occupying 65% horizontal width on the left, absolute visual core with high saturation and contrast, side light shaping three-dimensionality, vivid color, forming a clear level distinction with the rear afterimages, no duplication); Clear occlusion between foreground and middle layers, strong primary-secondary contrast. 【Character Clip Details (Enhanced texture and tension)】 Foreground Main Portrait (Core vision, 65% width on left): Profile close-up with calm and confident expression. Extremely realistic human skin with full micro-details: distinct pores, fine lines and natural facial texture. Delicate light and shadow transition on skin surface, fully restore real portrait photography effect, no over-smoothing, no plastic or fake skin feeling. Rembrandt side light shapes facial outline. Low-density blue brush splatter and particles around the outline to enhance design sense. Vivid color with normal saturation to separate from the background. Background Afterimage 1 (Emotional close-up): The same character with excited roaring celebration expression and clenched fist posture, forming a contrast with the main portrait's demeanor. Cool semi-transparent effect with blue cold tone, integrated into background mist, no stiff black-and-white/gray tone effect. Skin texture consistent with the main portrait, soft lighting. Background Afterimage 2 (Front celebration pose): The same character adopts a standard handsome victory celebration pose, one finger pointing to the sky, chest out and head up, confident gaze, expression consistent with the main portrait. Shallow depth of field blur + slight motion blur effect with full color retained, integrated into background atmosphere. Clear soccer/jersey details, dark blurred rainy night stadium in background, weak stage light illuminating the subject, medium-density brush splatter and particle effects around the body to enhance dynamism. Background Afterimage 3 (Back celebration pose): The same character celebrates with arms spread, back to the camera, No.10 number on the back of the jersey is clear, relaxed and confident posture. Shallow depth of field blur + slight motion blur effect with full color retained, brush-feathered edges integrated into the background atmosphere. Soft lighting, forming a contrast with the main portrait. 【Text & Emblem Layout (Enhance premium texture, clear hierarchy)】 All texts and emblems adopt matte gold foil/ice blue embossed texture, commercial sans-serif font, no stroke, glow or gradient, visual effect equals physical printing. Position, size and character spacing strictly follow high-end sports poster design: Top left corner: Round golden ""VICTORY"" emblem with matte metallic texture, fixed size. Bottom main title: Brush art font with ice blue light effect and splatter texture, VICTORY-themed main title, secondary title with matte white/gold small description text, three levels of text with clear hierarchy, layout embedded in the frame texture with soft edges, not stiffly pasted on the frame. No redundant text obscuring the subject. 【Lighting, Effects & Atmosphere (Enhance cinematic feel, avoid cheapness)】 Unified stage top and side light dual light source for the whole frame. The foreground main portrait uses warm hard light with high-contrast light and shadow and saturated color; the rear afterimages use cool soft light with low-contrast light and shadow, 10%-15% reduced brightness to form a strong light and shadow contrast. Brush splatter is matte paint splatter effect, realistic rain, mist and lens flare with subtle film grain, only attach to character outlines without diffusion. Clear texture distinction among jersey fabric, human skin and soccer ball, unified overall atmosphere with no flat light or template feel."

AI Retouch

Retouch this photo. Keep the background, clothing, pose, framing, and head-to-body proportions exactly identical. Do not crop or change the layout. Skin: healthy radiant glow, smooth matte. PRESERVE freckles. Do NOT whiten skin. Remove blemishes only, keep natural texture. Body: toned and fit, subtle hourglass [female] / athletic V-taper [male].  Hair: keep style, add shine, reduce flyaways. Color: increase contrast, vibrant and clean. NO warm or golden filters. Same person, same face, same scene, same resolution. Do not upscale, sharpen, or add detail not in the original.

Tender Shine

Thief Cat

The real-life footage of this news scene is extremely realistic, featuring some close-up shots that captured the image of the pet in the uploaded picture (the pet's features and species remained unchanged). The pet was sitting in an open and messy refrigerator, located in the center of the frame, occupying 80% of it. Its face was smeared with some cat food, and its paws were holding a half-eaten tuna can. Its eyes were wide open, looking very innocent, as if nothing had happened. The refrigerator was in a messy state, with cat food scattered everywhere, along with spilled wet food and overturned yogurt cups. The background of the kitchen was somewhat blurry, and the indoor light was warm. Above it was a prominent large red and white news headline: BREAKING NEWS. In the following picture, there was a news headline: LIVE BROADCAST, 8:23 PM, Watch: This pet was discovered stealing and robbing during the midnight snack search operation with red-claw's assistance.

Pet for You

Pet Caixa

Parisian Muse

Elevator Couple

Lift off

Food Filter

Sky Paraglide

Sticker Star

" Image-to-image, fully retain the original pet's appearance, fur, facial features and core characteristics from the uploaded photo, hyper-realistic photographic quality, truly reproducing the texture and sheen of the pet's fur. The frame adopts a 2×2 four-grid sticker layout, overall 1:1 square composition, pure transparent background, with rounded white borders on each sticker, perfectly adapted for WhatsApp and social media platforms. The overall style is grounded Brazilian street vibe, focusing on the rough yet cute charm of Rio de Janeiro's favelas, rejecting overly polished aesthetics, and conveying the Brazilian spirit of ""tough yet cute, surviving and thriving"". Four sticker expressions and elements: Top Left: Shocked & Crushed Face: The pet has wide eyes and an open mouth, showing a dumbfounded and devastated look after life's blows, paired with a green-yellow explosion speech bubble (Brazilian national flag colors) with the Portuguese phrase「NÃO!」, enhancing the ""miserable yet cute"" vibe; Top Right: Joyful & Content Face: The pet squints, licks its lips and smiles, showing a grounded happiness of ""being satisfied with a cheap snack"", decorated with green-yellow hearts and a Brazilian pão de queijo silhouette, highlighting optimistic resilience; Bottom Left: Tired & Disgusted Face: The pet tilts its head, squints and purses its mouth, showing a ""meh, whatever"" laid-back attitude, paired with a street-graffiti-style speech bubble with the Portuguese phrase「Tá tudo mais ou menos」, down-to-earth and playful; Bottom Right: Tearful but Stubborn Face: The pet has teary eyes but purses its mouth tightly, showing the stubborn grievance of ""I'll cry and keep going"", decorated with a green-yellow broken heart and a small sun silhouette, emphasizing the resilient core. Even and soft lighting, no extra clutter, all emotional elements are grounded Brazilian street-style, bright colors, hyper-realistic texture, perfectly restoring the rough yet cute charm of real pets, fitting the Brazilian street atmosphere."

Milk Splash

"Use the uploaded pet image as the exact identity reference. Preserve the animal's species, breed, coat colour and markings, ear shape, muzzle/face structure, eye colour and tail, keeping it instantly recognisable as the same pet; change only the style, not its identity. Create a vertical 3:4 image with this exact effect: surreal cinematic city scene, the uploaded pet becomes a huge kaiju-sized animal crouched between skyscrapers and pouring or splashing milk into the street below. Dramatic but cute, realistic fur, miniature cars and buildings for scale, golden evening light, high-detail photo-composite. Keep it playful, not scary; no text. The generated image must strongly match the gameplay composition and texture described above. Keep the pet angle and amount of face/body visible faithful to the described style. If the style is hand-drawn, manga, watercolor, plush, sticker, toy, surreal photo-composite, or realistic meme photo, reproduce that material and texture clearly. No logos, no watermark, no Doubao AI text."

Caramelo Stamp

"Image-to-image, fully retain the original appearance, fur and caramel-colored texture of the dog, hyper-realistic printing texture that restores the paper, ink and cutting details of physical commemorative stamps. Multiple stamps are stacked in a staggered and tilted layout with rich layers and flexible design. The central C-position stamp is the visual focus with clear and sharp details. The surrounding stamps have different styles and color schemes, blurred and indistinct due to shallow depth of field, forming distinct primary and secondary layers. All stamps are equipped with standard serrated perforated borders, restoring the appearance of real stamps. The whole picture is dominated by Brazilian green and yellow, decorated with retro patterns such as palm leaves and folk lines. The caramel dog on the C-position stamp turns its side face towards the camera, with exaggerated, funny and dramatic facial expressions and vivid comical effect. The Portuguese text Caramelo do Brasil is printed on the stamp in retro postal font, arranged properly without covering the main subject. Made of matte vintage stamp paper with subtle fiber texture and slight natural aging traces, simulating the real state of collected stamps. The light is soft and even, highlighting the three-dimensional sense of stacked stamps. The overall atmosphere is joyful, interesting, realistic and natural."

Ganesha Blessing

Cool Dance

"System Role: You are an expert AI Image Editing Assistant. Your task is to view the input image and generate a single, precise text instruction to edit the image. Logic Requirements: Analyze Identity: Identify the main subject. You must explicitly mention their specific visual traits (species/breed for animals; age, hair color, facial features for humans) in the output to preserve their identity. Determine Posture: If Animal: The instruction must make the animal stand in an anthropomorphic posture, standing fully upright on its hind legs with a vertical torso and forelimbs hanging naturally at its sides. If Human: The instruction must make the human stand naturally, with arms hanging naturally at their sides. Apply Scene & Costume: Wearing a light brown straw wide-brimmed hat, paired with blue round sunglasses, wearing a light blue short-sleeved T-shirt (with cute bone pattern prints), a cute khaki work pants (with dog head embroidery patterns on the front), the scene is on a city rooftop (with blurry tall buildings in the background), clear blue sky with a few white clouds, and the ground has a rough cement texture. Style: Ultra-realistic, high-definition details, natural light and shadow (sunlight creates clear shadows); atmosphere: casual, cool and handsome, cute street style"

3D Spin

Christmas Gift

Great Wall Selfie

Create a close wide-angle travel selfie at the Great Wall, matching the reference. The uploaded pet's face fills the lower-right foreground, wearing oversized orange sunglasses; the stone wall and watchtowers curve into green mountains behind. Bright clear daylight, raised-camera tourist perspective, playful confident expression. The subject remains an animal throughout. No people or human hands. No real brands, logos, watermarks or readable text. Accurately preserve the uploaded pet's species, breed, coat color and markings, ear shape, muzzle and face structure, eye color and body proportions. Keep it instantly recognisable as the same animal; change only pose, scene, clothing and accessories. Vertical 3:4, photorealistic, crisp detail, with the pet as the unmistakable main subject.

Headphone Treasure

Photograph the uploaded pet as a joyful studio DJ-style pet portrait on a solid pastel pink background: the pet faces camera with a happy open-mouth expression, wearing oversized cream heart-shaped sunglasses and a dark navy floral bandana or scarf around the neck. Add over-ear headphones as a playful music accessory if they fit the pose, keeping the sunglasses and bandana clearly visible. Bright commercial pet photography, crisp fur, clean shadows. No real brand names, no logos, no readable text, no watermarks, no human hands and no people. while accurately preserving the uploaded pet's species, breed, coat color and markings, ear shape, muzzle and face structure, eye color, body proportions and tail; keep it instantly recognisable as the same pet, changing only the pose, scene, accessories and styling. Vertical 3:4 composition; pet is the clear main subject, centered, with the key props fully visible and the background subordinate.

AI Enhance

Retouch this image. Remove visible water spots, dust specks, smudges, and blurry dirty spots on reflective surfaces such as mirrors or glass, while keeping the actual reflection, subject, clothing, hair, and all real objects exactly the same. After cleaning surface artifacts, enhance overall image quality to 2K: reduce noise, sharpen edges, repair compression artifacts, and reconstruct natural fine details such as hair strands, skin texture, fabric texture, and small object details. Do not change the person's appearance, expression, identity, or pose. Do not add, remove, or alter any real objects. Do not change the overall colors, lighting style, or atmosphere. Only clean surface artifacts and improve clarity, sharpness, and detail while preserving the original look.

3D Cartoon

"Use the uploaded image as the only reference. Strictly preserve the original subject, identity, facial features, hairstyle, expression, clothing, pose, background, scene layout, and overall composition of the uploaded image. Do not add or remove major elements. Only transform the visual style into a polished stylized 3D cartoon illustration. Style: animated movie character aesthetic, soft 3D rendering, smooth shading, expressive eyes, clean details, warm cinematic lighting, appealing stylized proportions, and a refined CG cartoon finish. Use a softer and more natural color treatment: slightly muted colors, lower saturation, gentle contrast, balanced tones, and a warm but not overly vivid palette. Avoid overly bright, oversaturated, or neon-like colors. The final image should look like a faithful 3D cartoon version of the uploaded image, changing only the artistic style while keeping the original content recognizable, with a more subtle, elegant, and cinematic color mood."

City Nap

"Use the uploaded pet image as the exact identity reference. Preserve the animal's species, breed, coat colour and markings, ear shape, muzzle/face structure, eye colour and tail, keeping it instantly recognisable as the same pet; change only the style, not its identity. Create a vertical 3:4 image with this exact effect: dreamy surreal city photo-composite, the uploaded pet as a gigantic sleepy animal resting over a downtown street canyon between tall buildings. Eyes closed, paws relaxed, soft clouds and bright blue sky, tiny cars and pedestrians below for scale, cozy peaceful giant-pet mood, realistic fur and sunlight. The generated image must strongly match the gameplay composition and texture described above. Keep the pet angle and amount of face/body visible faithful to the described style. If the style is hand-drawn, manga, watercolor, plush, sticker, toy, surreal photo-composite, or realistic meme photo, reproduce that material and texture clearly. No logos, no watermark, no Doubao AI text."