Single-Reference 3×3 Fashion Contact Sheet Prompt: Generating 9 Camera Angles with Strict Character Consistency

AI creator @johnAGI168 has shared a comprehensive prompt template on X (formerly Twitter) designed to generate a high-resolution 3×3 cinematic fashion contact sheet from a single uploaded reference image, rendering nine distinct camera angles and framing perspectives in a single pass while maintaining 100% character and wardrobe fidelity.

Image source: @johnAGI168 on X

In AI-driven fashion photography and visual storytelling, achieving reliable character consistency across diverse camera angles remains a formidable challenge. When creators attempt to generate individual shots sequentially, image foundation models frequently introduce subtle shifts in bone structure, skin complexion, hair texture, and clothing patterns, eroding the illusion that all images portray the exact same subject. @johnAGI168 resolves this limitation by structuring a vertical 9:16 canvas into a 3×3 grid of nine vertical sub-panels, explicitly designating the uploaded reference photograph as an unalterable "single source of truth" (SSOT) across all nine frames simultaneously.

1. The Single Source of Truth (SSOT) Principle and 100% Identity Fidelity

The core architectural strength of the prompt lies in how strictly it anchors the visual attributes of the reference photograph, preventing the model from improvising or introducing random generative drift.

• Anatomical and Facial Fidelity: The prompt explicitly enforces identical facial geometry, bone structure, eye shape, eyebrows, nose, lips, skin tone, pores, freckles, and moles, requiring exact reproduction rather than generic stylized approximations.
• Hairstyle and Grooming Continuity: Hairstyle, overall length, hairline contours, hair pigmentation, and makeup styling are strictly frozen to mirror the source image.
• Wardrobe, Accessories, and Proportions: Body build and physical proportions match the reference exactly. The outfit, footwear, accessories, and jewelry must adhere to identical color palettes, fabric textures, materials, and tailored cuts.
• Strict Anti-Styling Directives: To counteract the bias of diffusion models toward beauty filters, the prompt explicitly commands: "Do not beautify, slim, de-age or restyle anything." Furthermore, it instructs the model to extract solely the subject from the reference while strictly discarding its original background.

2. Minimalist Infinity Studio Environment and Uniform Diffused Lighting

To eliminate visual noise and maintain full focus on the subject and wardrobe, all nine panels are staged within a neutral infinity studio environment with unified lighting.

• Seamless Light-Gray Infinity Set: The setting features a seamless studio where the floor smoothly curves into the wall with no visible horizon lines, corners, furniture, props, or architectural elements. Only the subject and their soft natural floor shadow exist in frame.
• Diffused Studio Illumination: Lighting is calibrated as soft, even, diffused studio light paired with a gentle directional key light, identical across all nine panels, balanced with a neutral cool-gray color grading.
• High-Fashion Editorial Demeanor: The poses project confident, high-fashion editorial attitude rather than stiff, robotic standing stances.

3. The 3×3 Grid: Nine Distinct Camera Angles and Labeling Layout

The master canvas is framed in a vertical 9:16 aspect ratio, containing nine vertical 9:16 panels separated by black borders with softly rounded corners. Ordered from left to right and top to bottom, the grid covers a diverse spectrum of photographic perspectives:

Panel Position	Shot Type	Label Text	Staging, Pose & Camera Direction
Panel 1	Worm's-Eye	/wormseye:	Dramatic floor-level low angle. The subject towers over the lens with weight on one leg, one hand in a pocket, chin slightly lowered, gazing coolly down into the camera.
Panel 2	Extreme Close-Up	/extremecloseup:	Tight crop from eyebrow to lips. Eyes locked directly on the lens, showcasing detailed skin texture and facial features.
Panel 3	Drone View	/droneview:	High-altitude perspective looking straight down. The subject appears small at the center of the vast gray floor, captured mid-stride with an extended soft shadow.
Panel 4	Side Profile	/profile:	Clean side profile framed from the chest up. Head held high with gaze focused into the distance.
Panel 5	Top-Down	/topdown:	Vertical top-down perspective looking straight down on the standing subject, who tilts their face upward toward the lens, body foreshortened beneath.
Panel 6	Low Three-Quarter	/lowthreequarter:	Low-angle three-quarter full-body shot. Subject turned three-quarters away, glancing back over the shoulder into the camera.
Panel 7	Wide Full-Body	/widefull:	Expansive full-body shot. Subject framed small within the open studio space, walking toward the camera mid-step.
Panel 8	Over-The-Shoulder	/overshoulder:	Captured from behind over the shoulder. Subject's shoulder and hair softly blurred in the foreground, with the face turned in three-quarter profile.
Panel 9	High Angle	/highangle:	High-angle shot looking down. Subject seated on the studio floor with one knee raised, an arm resting on it, looking up into the lens.

At the base of each panel, a uniform white rounded rectangular label box displays clean black sans-serif typography with exact shot-type tags (/wormseye:, /extremecloseup:, /droneview:, etc.), producing the authentic aesthetic of a curated editorial contact sheet.

4. Full Production Prompt and Creative Workflow Applications

The complete, unabridged English prompt shared by @johnAGI168 is provided below:

Using the uploaded reference photo as the single source of truth for the person, create a high-resolution cinematic fashion contact sheet: a 3×3 grid of nine vertical panels on a vertical 9:16 canvas, each panel also a vertical 9:16 frame, separated by black borders with softly rounded panel corners. The person in every panel must be exactly the person in the reference photo, reproduced with 100% fidelity: identical face shape and bone structure, eyes, eyebrows, nose, lips, skin tone and texture, freckles and moles; identical hairstyle, hair length, hairline and hair color; identical makeup; identical body build and proportions. The outfit, shoes, accessories and jewelry must match the reference exactly in style, color, material and fit. Do not beautify, slim, de-age or restyle anything. Take only the person from the reference, never its background.

Every panel is shot in the same completely clean, seamless light-gray infinity studio, where the floor curves into the wall with no visible horizon line, no corners, no props, no furniture and no architecture. The only things in the frame are the person and their soft natural shadow on the floor. Lighting is soft, even, diffused studio light with a gentle directional key, identical across all panels, with a neutral cool-gray color grade. The poses are confident and high-fashion, with attitude, never stiff.

Reading left to right and top to bottom: panel one is a dramatic worm's-eye shot from floor level, the subject towering over the lens, weight on one leg, one hand in a pocket, chin slightly lowered, gazing down coolly into the camera. Panel two is an extreme close-up cropped tightly from brow to lips, eyes locked on the lens. Panel three is a drone view from very high above, the subject small at the center of the empty gray floor, mid-stride, with a long soft shadow. Panel four is a clean side profile, chest-up, head held high, gaze fixed into the distance. Panel five is a direct top-down view looking straight down on the standing subject, who tilts the face up toward the lens, with the body foreshortened beneath. Panel six is a low three-quarter full-body shot, the subject turned three-quarters away with the head looking back over the shoulder at the camera. Panel seven is a wide full-body shot, the subject small in the empty frame, walking toward the camera mid-step. Panel eight is an over-the-shoulder shot from behind, the subject's shoulder and hair softly blurred in the foreground, face turned in three-quarter profile. Panel nine is a high-angle shot looking down, the subject sitting on the floor with one knee up and an arm resting on it, looking up into the lens.

At the bottom of each panel, place a white rounded rectangular label box with clean black sans-serif text, matching position and size in every panel, with exactly these texts in order: "/wormseye:", "/extremecloseup:", "/droneview:", "/profile:", "/topdown:", "/lowthreequarter:", "/widefull:", "/overshoulder:", "/highangle:". The labels must be clearly readable and correctly spelled.

Photorealistic, premium fashion editorial photography, natural skin texture with visible pores, realistic anatomy and hands, realistic hair and fabric detail. No other text, no logos, no watermarks, no reference-photo inset, no additional people, no background objects.

Production and Pipeline Integration Notes

1. Character Modeling and Previsualization: Generating 3-quarter, full-body, close-up, and top-down perspectives in one generation makes this structure ideal for character concept turnarounds and 3D modeling texture reference sheets.
2. Keyframe Extraction for Image-to-Video (I2V): Cropping individual panels from the 3×3 grid yields nine perfectly coordinated starting keyframes sharing identical lighting, clothing, and facial features. These can be supplied as first-frame inputs to video generation engines such as Kling, MiniMax, Luma Dream Machine, or Runway to ensure camera cut transitions remain seamless.
3. Rigorous Negative Constraints: The closing directive (No other text, no logos, no watermarks, no reference-photo inset, no additional people, no background objects) is critical for preventing common generative artifacts, such as accidental picture-in-picture thumbnail insets or extraneous watermarks.

Original source

• X @johnAGI168 original post: Nine-grid Character Poses - 3×3 Fashion Contact Sheet Prompt
• Prompt Garden: Consistent Character 3×3 Contact Sheet Methodology