Chibi Character Peeking into a Deep Cardboard Box

Format

Markdown Parameterized

Inputs

character_reference (image) · Required cardboard_reference (image) · Required

Outputs

Generated_image (image)

Replace the ${…} placeholders with your values before using this prompt. See parameters and defaults below.

Create a high-quality 3D CGI chibi figure image in a vertical 3:4 composition. Use ${character-reference} as the sole reference for the character’s appearance, and use ${cardboard-reference} as the reference for the cardboard box opening. Preserve the character’s identity and recognizable features; change only the character, not the scene, camera position, box structure, pose, or composition.

CHARACTER
Transform the referenced character into a polished, adorable 3D chibi figure with an approximately 2.5-head-tall body. Enlarge the head to about 1.3–1.5 times its original visual proportion. Give the face rounded, full cheeks, a short chin, and a head visibly wider than the shoulders. Keep the body small, with short arms and appropriately small hands. Connect the head and body naturally, without an overly long neck or implausible joints.

Preserve the reference character’s face shape, facial features, eye color, hairstyle and silhouette, hair color, bangs, hair direction, braids, glasses, bows, hair accessories, clothing, colors, materials, and other identifying details. Retain any glasses, braids, bows, or distinctive headwear in their original shape, color, and position. Give the eyes bright, clear, dimensional highlights. Use detailed skin and natural-looking hair strands. Show the complete head, hairstyle, bangs, ears, and important accessories without cropping. The head, including the hairstyle, should occupy about 35–45% of the image height, adjusted naturally for the hairstyle and accessories. Keep the face near the upper center of the box opening, with room at both sides. Show the head, shoulders, hands, and only a small part of the upper body; the rest of the body is hidden behind the box. The result must clearly show an oversized head, small body, rounded face, and cute expression—not merely a close-up portrait.

CAMERA AND VIEWPOINT
Place the camera at the very bottom center inside a large, deep cardboard box, aimed upward at the opening. Use an extreme low-angle, wide-angle worm’s-eye view, as if the viewer were at the bottom of a deep well looking up. The character stands outside the box, bends over the opening, and looks directly down into the camera. Make it unmistakable that the viewer is inside the box and the character is above it. Do not place the camera at the rim or outside the box. Do not shoot from above, use an ordinary eye-level portrait angle, or show the whole box from outside.

Use strong near-to-far perspective: the nearby front wall should appear broad, while the side walls rise and converge toward the distant opening. Keep the camera approximately vertical, with a wide-angle effect comparable to an 18–20 mm lens, while avoiding unnatural barrel distortion. The box must have clear front-to-back, side-to-side, and vertical depth; it must not look like a shallow box, flat backdrop, fence, or depthless rectangular frame.

BOX STRUCTURE AND MATERIAL
Use a large, clean, unprinted, dark-brown corrugated cardboard box with a slightly warm tone. All four top flaps are folded outward, forming a clear, naturally irregular quadrilateral opening through which the character peeks. Follow the box-opening shape in ${cardboard-reference}. The flaps must be actual parts of the box, not floating boards, a transparent frame, or decorative borders.

The upper flap extends diagonally from the upper left toward the upper right and remains visible as a substantial overhanging panel. The left flap opens outward toward the upper left and continues along the left side as a thick, angled frame. The right flap opens outward toward the upper right and forms a matching angled frame; the two sides may have naturally different angles. The front rim runs across the middle-to-lower portion of the image. The character’s hands grip its left and right sides. Below it, the front wall extends toward the bottom edge and fills much of the lower image. Show realistic flap thickness, corrugated cut edges, fibers, folds, creases, seams, natural dents, and subtle irregular surface texture. Make the box interior darken with depth, with the opening brighter than the bottom. The cardboard interior should occupy approximately 55–65% of the lower image.

POSE AND HANDS
The character stands outside the box, bends forward over the opening, and naturally extends the head toward its center, looking down at the camera with a sweet, curious expression and a gentle smile. Both hands clearly grip the left and right sides of the front rim. Fingers bend naturally around the cardboard edge; hands and contact points must be clearly visible and anatomically plausible. Show the palms in contact with the cardboard. Avoid incorrect finger counts, extra fingers, fused hands, extra arms, or hands passing through the box. Keep the shoulders and a small portion of the upper body above the rim, with the rest naturally hidden behind the walls. The character must not appear to be inside or sitting in the box, looking down from outside without leaning over, or shown full-body.

SETTING AND LIGHTING
Outside the opening, show a warm, bright, cinematic library. A softly blurred background may include wooden bookshelves, books, warm pendant lights, and golden ambient light. Keep the background naturally out of focus and secondary to the character and box. Warm light from above illuminates the character’s face, hair, accessories, and hands. Give the face subtle, natural transitions between light and shadow and attractive eye reflections. Use a cinematic effect with a bright opening, a clearly lit character, and a deep, shadowed box interior.

STYLE AND FINISH
Use a high-end 3D CGI figurine style with refined character modeling, detailed hair strands, delicate skin, soft facial scattering, realistic corrugated cardboard, consistent lighting between the character and environment, natural contact shadows, global illumination, ambient occlusion, soft shadows, and moderate shallow depth of field. Use a warm palette of brown, gold, and natural skin tones. The final image should feel cute, polished, dimensional, and spatially convincing, like a photograph taken from the very bottom inside the box looking up at the character. Do not make the character look pasted onto the background.

REQUIRED COMPOSITION
The image must clearly include all of the following: an oversized chibi head; recognizable shoulders and a small portion of the upper body; both hands gripping the front rim; all four outward-folded box flaps; and deep interior walls viewed from the bottom. Keep the complete head and hairstyle within the frame. The upper portion should show the character, hands, outward-folded flaps, and blurred warm library; the lower portion should show the broad, deep, dark-brown box interior.

AVOID
A small head, realistic adult body proportions, an oversized body, a realistically proportioned head, a deformed or stretched face, asymmetrical eyes, misplaced features, changed identity, changed hairstyle or hair color, missing bangs, glasses, braids, bows, or hair accessories, changed clothing, cropped head or hairstyle, face outside the frame, or a face-only portrait. Avoid malformed fingers, extra fingers or arms, fused hands, hands passing through the cardboard, hands not gripping the rim, the character inside the box, or the full body in view. Avoid eye-level, top-down, or side-profile views; a camera at or outside the opening; and any view looking down into the box. Avoid a shallow box, missing or undersized interior walls, a front wall that is too low or absent, missing flaps, flaps removed or folded inward, a regular rectangular frame, floating boards, or incorrect perspective. Avoid plastic, metal, or glass boxes; printed text, shipping labels, graphics, barcodes, or brand marks on the cardboard; an overly sharp or distracting background; an overexposed face; plastic-looking skin or excessive smoothing; low resolution; blurred facial features; and barrel distortion. No text, watermark, or logo.