Free Manipulation Images & AI Prompts

Create ↗

Use the uploaded character reference image as the strict identity and outfit reference. Preserve the reference subject’s facial identity, facial proportions, eye shape, nose, lips, skin tone, hairstyle, hair color, visible accessories, recognizable vibe, outfit, and styling. Infer all identity, hairstyle, accessory, and clothing details directly from the uploaded reference; do not invent specific traits that are not visible. Create a polished mixed-media vertical portrait featuring: (1) one realistic full-body or nearly full-body version of the uploaded character/person, and (2) one black hand-drawn doodle-shadow version of the same character/person drawn directly on the wall beside them. The real person and doodle-shadow are performing the same general playful, mischievous pose idea, but the doodle-shadow is much more exaggerated, chaotic, silly, and cartoonish. The real person should look cute, stylish, photogenic, slightly confused, mildly embarrassed, and playfully reluctant, as if thinking: “Why am I doing this with my shadow?” The real person must remain realistic, actively participate in the pose, and wear the same outfit style and key visible details shown in the reference. Do not replace the reference styling with unrelated fashion. Avoid a stiff stance. The doodle-shadow must be black sketch line art only: not a realistic second person, normal physical shadow, reflection, full-color anime character, or solid black monster. It should resemble the person through the hairstyle silhouette, accessories, outfit silhouette, and pose structure. Make it more energetic and mischievous, with optional manga-like motion lines, hearts, stars, sparkles, and comic marks. Invent a fresh playful mischievous pose for each generation rather than fixing one pose. Do not repeatedly use pointing, finger-gun, mirrored, or identical standing poses. The pose may suggest a silly dance, playful idol gesture, cheeky wink, cute teasing, mock surprise, tiptoe sneak, peekaboo, dramatic overreaction, goofy victory, playful balance, or another original pose, but these are loose inspiration only. The real person should perform a natural realistic version while the doodle-shadow looks like it is having far too much fun. Composition: vertical 2:3 portrait; place the real person on one side of the frame and the black doodle-shadow on a clean wall beside them. Show the full pose clearly, with enough surrounding space for both figures. The doodle-shadow should be approximately the same height or slightly taller, and the connection between the person and doodle-shadow should be immediately clear. Set the scene in a simple, clean indoor studio or minimal room corner with a white, cream, or pale gray wall and clean floor. A soft natural sunlight patch or gentle wall shadow is allowed, but keep the background uncluttered. Use soft natural studio lighting with a bright, clean, polished, playful mood; keep the real person’s face clearly visible. Use realistic human photography combined with precise black hand-drawn doodle line art on the wall, faithful identity and outfit resemblance, a clean composition, and a social-media-friendly mixed-media portrait. Negative prompt: unrelated outfit changes, realistic second person, normal reflection, normal shadow only, solid black monster shadow, horror shadow, creepy shadow, full-color illustration, cartoon human, anime human, weak resemblance, unrelated sketch character, messy wall, cluttered background, repeated pointing pose, repeated finger-gun pose, same pose every time, fixed pose, boring mirrored pose, stiff pose, identical pose repetition, real person not matching the shadow’s general pose idea, text, watermark, logo, distorted body, extra limbs, extra fingers, bad hands, obvious AI artifacts.

Copy

Create ↗

Use the uploaded image strictly as the only face and identity reference. Preserve her identity without beautification or identity drift. Create an ultra-realistic, vibrant cinematic tiny-planet portrait using a stereographic projection. A cheerful woman stands at the center of a miniature spherical world, looking directly at the camera with a genuine, confident smile. Her expression is lively, friendly, and energetic rather than posed or artificial. She has naturally long, voluminous, wavy brunette hair. She wears a casual modern outfit: a blue denim jacket over a plain white crew-neck T-shirt, fitted blue jeans with slight distressing on one knee, clean white sneakers, and visible brown leather backpack straps over her shoulders. In her right hand, she holds a white disposable coffee cup with a lid and sleeve, with subtle steam rising. In her left hand, she holds a smartphone angled toward the camera, displaying a colorful abstract map or navigation interface with no readable text. Use an extreme wide-angle fisheye and 360-degree stereographic tiny-planet perspective. Position the camera slightly above eye level and angle it downward. The woman should dominate the foreground, occupying approximately 70–80% of the frame, while the spherical world wraps visibly around and beneath her feet. Keep the entire tiny planet uncropped and emphasize strong depth and curvature. The miniature spherical ground is covered in vibrant green grass with tiny white details such as flowers or path markers. Around the sphere’s edge, seamlessly integrate a circular panorama of global landmarks: the Eiffel Tower, Burj Al Arab, Big Ben (Elizabeth Tower), Taipei 101, and St. Basil’s Cathedral, along with subtle European-style domes and towers. Use bright cinematic daylight with a soft HDR balance. Place the primary light source at the top left with a subtle sun flare. Add soft, diffused shadows on the right side of her face and clothing, with even exposure across highlights and shadows and no harsh clipping. Use a highly saturated, vibrant color palette with rich greens, deep sky blues, warm natural skin tones, and clearly visible denim texture. The result should be hyper-realistic with a slightly polished AI-rendered aesthetic, smooth but natural skin, refined detail, clean edges, and sharpness throughout the frame. Keep all elements physically stylized yet visually believable. No text, watermark, or branding.

Copy