Caramel Mutt

Crocodile Voyage

"[Strictly preserve the exact same subjects, same species, same faces, original appearance features, and the full style of clothing and costume details from the reference images unchanged;] photorealistic photograph, the subject from the reference image is straddling and riding on the back of a massive, realistic saltwater crocodile floating in crystal clear tropical turquoise sea water, legs naturally parted to sit across the crocodile body, and waving cheerfully at the camera. If the figure is female, she must wear long-sleeve top, long trousers and white sneakers. The background is a bright blue sky with soft white clouds, a distant lush tropical island shrouded in light mist, bright natural sunlight, sharp focus, ultra-detailed crocodile scales, realistic water reflections, 4K resolution, cinematic lighting, no deformities, consistent lighting on the subject matching the environment."

Flower Pet

A photorealistic portrait of the uploaded pet sitting calmly upright, gently holding a small bouquet of soft pink tulips in its mouth, stems resting naturally at the side of the muzzle. Soft pastel pink seamless background. Soft even studio lighting with gentle catchlights in the eyes, shallow depth of field, crisp fur detail, high-resolution. Sweet innocent expression, direct eye contact with the camera. while accurately preserving the animal's species, breed, coat colour and markings, ear shape, muzzle/face structure, eye colour and tail — keep it instantly recognisable as the same pet; change only the style, not its identity. The pet occupies 60–75% of the frame height, centered, head and full body clearly visible; background subordinate and not obstructing the pet.

Dance Softly

Strictly lock the subject identity from the reference image: preserve the original species, original identity, original face/facial structure, fur color or skin tone, markings/patterns, body proportions, age impression, gender vibe, eye color, ear/nose/mouth details, hairstyle or fur length and texture, and all unique recognizable traits. The generated result must remain instantly recognizable as the exact same subject from the reference image. Do not change the species, do not replace the subject with another person or another animal, do not lose likeness, do not replace the face. Only transform pose, clothing, accessories, environment, and cinematic presentation. Transform the subject into a full-body standing pose on top of a modern desktop, facing the camera, centered in frame, standing upright on both feet or hind legs, with both arms/front limbs slightly raised in a cute dancing, playful bouncing, or charming interactive pose. The expression should be soft, adorable, natural, and camera-facing. The overall mood should be cute, polished, healing, stylish, lightly anthropomorphic in pose only, while fully preserving the original species and recognizable appearance. Clothing rule must be strict: If the reference subject is a pet, animal, bird, or non-human creature, it must wear a cute full top and small pants/shorts/overalls/full little outfit. The outfit should be adorable, clean, stylish, modest, and properly fitted to the subject’s body. No nudity, no exposed private areas, no bare body presentation, no “only accessories without clothing.” Prefer soft colors such as cream, blush pink, light gray, beige. Keep the outfit simple and refined, and do not hide the subject’s key facial features or recognizable traits. If the reference subject is a human, keep them in a tasteful, cute, clean, stylish full outfit that matches the same adorable desk-setup aesthetic, with no revealing clothing and no identity distortion. Add a pair of soft pink glowing cat-ear over-ear headphones. The headphones should feel premium, dreamy, cute, slightly futuristic, and fashionable, with subtle clean glow accents. Do not let the headphones cover the eyes, face, or key recognizable features. Environment: place the subject in a premium modern computer desk setup scene. The subject stands on the center of the desk, with a large monitor behind them showing a dark or black screen. Add a clean keyboard, elegant small tech accessories, optional crystal or glass decorative objects, and a tidy minimalist desktop environment. The overall atmosphere should be clean, stylish, luxurious, soft, cozy, social-media-friendly, streamer/gaming desk aesthetic. Use a palette of cream white, soft gray, blush pink, and silver, with a gentle feminine tech vibe and minimalist premium styling. Composition: vertical 9:16, full-body visible, no cropping of feet, head, ears, or limbs, subject centered, slightly low-angle or subtly upward eye-level perspective to enhance the cute standing pose. Use shallow depth of field, with the subject sharp and crisp, and the background softly blurred while still readable as a premium desk setup. Lighting and rendering: use soft studio lighting, clear facial illumination, refined body contour light, highly realistic fur/skin/clothing/material textures. The overall style should be ultra detailed, photorealistic, cinematic, high-end commercial quality, cute but realistic. Quality tags: ultra detailed, photorealistic, realistic fur or skin texture, detailed clothing fabric, premium accessories, soft studio lighting, soft shadows, cinematic realism, adorable aesthetic, high-end commercial render, clean luxury desk setup. Style emphasis keywords: same subject, same species, identity preserved, original appearance locked, cute standing pose, playful dance pose, pink glowing cat-ear headphones, pets wearing a cute top and small pants, full outfit, premium computer desk setup, monitor background, minimalist luxury desktop, soft studio lighting, realistic kawaii aesthetic, healing and polished visual style. English Negative Prompt: do not change species, do not replace the subject with another person or another animal, no face replacement, no identity loss, no lost markings, no wrong fur color, no wrong skin tone, no extra limbs, no extra heads, no deformed anatomy, no fused limbs, no asymmetrical eyes, no distorted ears, no face collapse, no blur, no low resolution, no body crop, no messy background, no dirty desk, no horror, no uncanny expression, no excessive cartoon style, no nudity, no exposed private areas, no bare pet body, no accessories-only styling, no overly short clothes, no visible sensitive parts, do not let the headphones block the eyes or key facial features, no watermark, no text, no logo, no overexposure, no underexposure.

Angel Caramelo

"Image-to-image, 100% accurately retain the fur texture, facial outline and original posture of the caramel dog, top-tier hyper-realistic photographic quality. The fur is fluffy and three-dimensional with clear details, matched with master-level layered warm cinematic light and soft color palette. The caramel dog turns into a tender little angel and squats firmly on thick full warm cotton-like clouds. It tilts its head naturally to one side and squints its eyes comfortably, with soft facial lines and lovely coquettish look. One front paw is lifted lightly with a playful curve to act cute towards the camera. The limbs connect naturally with the body, and the whole body is neat and fully covered without any exposed areas. A pearlescent translucent circular halo hovers above its head, with gradual flowing white and golden soft light along the edge, delicate and layered. A pair of layered realistic white feather wings spread on its back, with distinct and staggered feather textures. The wings stretch slightly and glow with faint elegant pearlescent luster. The whole scene adopts a unified warm color system. The sky and clouds are mainly warm off-white, light apricot and soft golden yellow with moderate saturation and mellow tones. The color transition is smooth and natural, without abrupt visual contrast, and echoes harmoniously with the dog's caramel-brown fur. Large areas of gradual white and golden diffused halos surround the body, with delicate light and shadow transition. The background is a three-dimensional layered warm cloud scene: thick fluffy warm clouds form the ground in the foreground, and thin flowing light apricot clouds stretch in the distance. The clouds are scattered at different heights with strong spatial depth. Tiny stardust and floating light particles drift slowly in the air, creating a cozy, romantic and wonderful atmosphere. The dog has a sweet and lovely expression with lazy and charming eyes and a reserved soft smile without showing teeth, full of cute coquettish charm. The overall mood is positive and healing with no sad tones at all. The unified warm tone and soft transparent light and shadow bring top-tier hyper-realistic texture, making it an excellent template for high-definition memorial works, exclusive avatars and warm social pictures."

Hairstyle

Noir Gaze

"Use the exact same facial features, gender, and age as the character in the uploaded image. Photorealistic dramatic portrait, shot from a low-angle perspective with a wide-angle lens, creating a sense of grandeur and intimacy. Dark, slightly messy, textured hair with strands catching the light.The figure stands facing the camera, head tilted slightly upward, with a serious, smoldering expression.The right hand is extended forward, palm up, reaching directly toward the viewer, creating a compelling focal point and sense of immediacy.Wearing a sleek, black mandarin-collar jacket with a minimalist, formal design, which contrasts with the dark, cavernous, textured background.The lighting is dramatic and high-contrast, with a single, strong key light from above, creating a sharp highlight on the hair and face, while deep, moody shadows fill the background and sculpt the contours of the body.The overall mood is intense, mysterious, and cinematic.High detail skin texture, cinematic lighting, shallow depth of field, 8K, ultra-realistic, no text or watermarks."

Fur Crystals

Recreate the luxury editorial portrait. The uploaded pet is shown from chest up in three-quarter view wearing a voluminous blush-pink faux-fur stole and multiple oversized clear crystal necklaces stacked around the neck. Dark gray studio background, cool glamorous light, elegant alert gaze, detailed sparkling gems and fluffy fur. 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.

National Wind

Drunk Cat

"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 cute top, with the background being the scenery of an amusement park. Style: High-definition realistic, cinematic texture，high-end photography style, the aesthetic charm of fashion photography."

Sobbing Dance

The pet in the picture is depicted in an anthropomorphic standing posture (with its front two legs raised and the hind legs on the ground; there should be no additional legs). The scene and background remain unchanged. It is a black knitted short top in the Chanel style, with a pearl-embroidered collar. It is paired with a black pleated mini skirt, black satin gloves, and the cuffs of the gloves are decorated with pearls. There is a small, cute black satin bow decoration on the pet's head.

Elan Step

photo of the exact same subject from the reference image, 100% preserve the original species, identical face, exact facial features, same fur texture, same natural appearance, NO alterations to the subject’s face, identity, or core physical traits, stylized realistic chibi proportions, compact streamlined small body, balanced head-to-body ratio for a cool yet lifelike effect, full-body shot, standard upright standing pose, facing the camera, wearing iconic stage costume: tailored black leather jacket, single white sequined glove on one hand, black fedora hat, slim-fit black trousers, white mid-calf socks, polished black leather shoes, background is out-of-focus blurred American city street with neon light bokeh effect, cinematic cool-toned street lighting, photorealistic, ultra-detailed leather sheen, lifelike fur texture, high contrast color grading, high resolution, 8K, sharp focus, professional commercial photography, natural expression (cool aloof expression / subtle closed-mouth smile)

Baby Mode

Expressionist Bridge Pet

Recreate the expressionist bridge painting with the uploaded pet centered close to camera, mouth open in an exaggerated surprised cry and front paws held near the chest. Wavy orange-red sky, dark blue water and sharply receding bridge rails behind, thick swirling brushwork and distressed emotional color. The subject remains an animal throughout. No people or human hands. No real character names, celebrity names, 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, body proportions and tail. Keep it instantly recognisable as the same animal; change only pose, scene, costume and art treatment. Match the reference composition closely. Vertical 3:4, crisp detail, the pet is the unmistakable main subject.

Quiet Night

Groom Style

Pirate Pet

Farm Warm Us

Five-grid collage, realistic portrait of pregnant couple on American ranch, strictly follow the layout, proportion, character poses and props of the reference image. All characters wear fixed unified outfits, overall low saturation natural warm tone. The facial features, face shape, hair color and hairstyle of the man and woman fully match the reference portraits provided by the user. shtur horizontal panorama: A young pregnant woman and a man stand in front of wooden ranch fence. The pregnant woman wears a loose black draping shirt worn open to fully show her pregnant belly and off-white wide-leg trousers, holding her belly gently with both hands. The man wears a fitted black short-sleeve T-shirt and blue washed jeans, holding horse reins beside a spotted horse. Background: vast grassland and old wooden barn, soft warm light at golden hour dusk. 2.Middle left vertical half-body shot: The pregnant woman leans alone on the wooden fence, wearing an off-white wide-brim cowboy hat and the same loose black shirt worn open to expose her belly. One arm rests on the fence, one hand lies gently on her belly with relaxed posture. Background: open autumn grassland, soft dusk light. 3.Middle right vertical half-body shot: Pregnant woman in the front, man standing right behind her. The pregnant woman wears the same black shirt open to expose her belly with one hand on her abdomen. The man wears the same black short-sleeve T-shirt and holds a clear prenatal B-ultrasound photo. Background: ranch grassland, soft side light at dusk. 4.Bottom left vertical full-body back shot: The couple hold hands on the grassland, facing the setting sun. The pregnant woman wears the same black shirt and off-white wide-leg trousers. The man wears the same black short-sleeve T-shirt and blue jeans. Background: low saturation warm tone dusk sky, hazy grassland. 5.Bottom right vertical close-up: Close-up of the pregnant woman’s belly. She wears the same loose black shirt open to expose her full pregnant belly, making a heart shape with both hands on her belly. Background: blurred ranch fence and grassland, shallow depth of field. Realistic portrait photography, natural and lifelike light and shadow, delicate and transparent skin texture, overall low saturation, soft and natural colors, 8K high definition, rich details. Negative prompt: Messed up five-grid layout, wrong division proportion, inconsistent character poses, missing props; inconsistent outfits, multiple different clothes, wrong color and fabric; facial distortion, mismatched facial features and hairstyle; high saturation gaudy colors, dazzling tone, inconsistent hue; pregnant belly covered by clothes, deformed horse, blurred B-ultrasound photo; overexposure, crushed shadows, color distortion; blurry image, excessive noise, watermarks, text, logo, messy borders, deformed limbs, abnormal fingers.

Cake and Wine

Pet for You

Flower Vogue

Recreate the reference as a warm VOGUE botanical fashion cover. The uploaded cat sits three-quarter/front-facing in a cream knitted sweater and flowing ivory cape or shawl, one flower stem with an orange blossom held near the chest, regal calm expression. Soft golden studio lighting, cream curtain background, large black 'VOGUE' masthead at the top and tiny text 'x botanika.' near upper right. Dreamy editorial print texture, warm beige palette. Preserve the uploaded pet's actual species, breed, coat color, markings, ear shape, eye color, muzzle and facial structure. Do not assume a fixed breed, color, or species from the reference image; adapt the exact gameplay to the uploaded pet. Actively change pose, facial expression, gaze direction, camera angle, wardrobe and styling to match the gameplay reference. Match the gameplay reference very closely in composition, crop, texture, lighting, visible pet angle, props, background, graphic layout and image quality. Vertical 3:4. Keep only the text explicitly requested in the prompt; do not add unrelated logos, watermarks or random words.

Lucky Charm

"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: glossy 3D soft charm icon on a warm orange rounded-square background, the uploaded pet as a lucky-cat-style kawaii mascot sitting upright and holding a tiny striped candy or ball. Smooth inflated vinyl texture, rounded paws, tiny bell collar, soft highlights, cute product-icon framing. No brand marks or readable 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."

Poolside Vibe

Jewel Glasses

Recreate the quirky blue studio portrait. The uploaded pet faces forward wearing enormous round silver rhinestone sunglasses with blue mirrored lenses and a chunky sky-blue knitted turtleneck sweater with large dark buttons. Solid cyan background, close chest-up crop, humorous high-fashion expression, crisp knit and gem texture. 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.