Image - 2026-09-22 13:38

There are no identity images. Create one believable person strictly from the written identity specification and keep that exact same person in every view without identity drift. IDENTITY SPECIFICATION — ALL FIELDS ARE BINDING: { "name": "Kazuki Andrade", "gender": "Male", "pronouns": "he/him", "age": "30–32", "ethnicity": "Japanese-Brazilian", "origin_country": "Brazil", "current_location": "Tokyo, Japan", "height": "5'8\"", "body_type": "Medium, slightly muscular", "skin_tone": "Light warm beige with golden undertones", "hair": "Straight black hair, medium length, worn parted to one side and slightly tousled", "eyes": "Dark brown", "distinguishing_features": "Always wears a pair of over-ear studio headphones around his neck even when not recording audio; a small keloid scar on the right earlobe from an old piercing", "immutable_identity_prompt": "Kazuki Andrade, Male, age 30–32, Japanese-Brazilian, from Brazil, living in Tokyo, Japan. Appearance: 5'8\", Medium, slightly muscular, Light warm beige with golden undertones, Straight black hair, medium length, worn parted to one side and slightly tousled, Dark brown, Always wears a pair of over-ear studio headphones around his neck even when not recording audio; a small keloid scar on the right earlobe from an old piercing. Life context: Audio engineer and AI audio-video workflow educator, Single, Studio hours in Tokyo, records at night when the building is quietest, meticulous about acoustic treatment in his recording corner, plays bass guitar recreationally. Personality: Technically precise, Niche-confident, Good-humored about being underrated, Methodical. Kazuki trained as a sound engineer in São Paulo and relocated to Tokyo for a contract with a music production house. He got drawn into AI video through clients who wanted synchronized audio-visual AI content and found that most AI video channels completely ignored the audio cost and quality problem. He carved out a unique niche: he covers AI video specifically from the audio-sync, voice quality, and audio credit angle — an entire dimension that most creators overlook until they've already burned credits on broken outputs. Preserve this exact identity, face, body proportions, age and background in every generation.", "biography_context": "Kazuki trained as a sound engineer in São Paulo and relocated to Tokyo for a contract with a music production house. He got drawn into AI video through clients who wanted synchronized audio-visual AI content and found that most AI video channels completely ignored the audio cost and quality problem. He carved out a unique niche: he covers AI video specifically from the audio-sync, voice quality, and audio credit angle — an entire dimension that most creators overlook until they've already burned credits on broken outputs." } OPERATOR'S CHARACTER-SHEET PROMPT: Use the provided images as a strict identity reference for the same person and preserve the exact likeness, including face, body, proportions, skin, and hair exactly as in the reference, with no changes, no stylization, and no beautification. Create a professional character turnaround sheet on a pure white background showing the same person in multiple views: front view full body, 3/4 front view full body, side profile full body, back view full body, and 3/4 back view full body, plus a close-up front portrait and a close-up 3/4 portrait. All full body views must show the entire body from head to feet with the feet fully visible, no cropping, and consistent scale across all views. The person must remain identical in every view with no identity drift, maintaining the same body type, proportions, clothing, and hairstyle. Neutral pose and expression, eye-level camera, minimal perspective distortion, clean soft studio lighting, pure white background, ultra photorealistic natural skin texture, no smoothing, no artifacts, no extra elements. The source rule above has priority: when no images are attached, interpret any mention of "provided images" as the written identity specification instead. CONSISTENCY REQUIREMENT: This is a casting/identity master asset for future video generation. All views must depict one exact person, with identical facial geometry, apparent age, body proportions, skin, hair and distinctive features.