Image - 2026-10-08 01:48

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": "Dorian Kesäläinen", "gender": "Male", "pronouns": "he/him", "age": "28–28", "ethnicity": "Finnish", "origin_country": "Finland", "current_location": "Lisbon, Portugal", "height": "6 ft 1 in (185 cm)", "body_type": "Lean, broad-shouldered; long limbs with a slightly angular build", "skin_tone": "Fair with a warm peachy undertone, light freckles across the nose bridge", "hair": "Ash-brown, fine and straight, cut close on the sides with a longer, loosely swept top; often slightly disheveled", "eyes": "Pale grey-green", "distinguishing_features": "A faint scar along the left eyebrow from a childhood cycling accident; habitually rolls the sleeve of one arm higher than the other", "immutable_identity_prompt": "Use the approved shared 3D Doitong director mascot: red baseball cap, charcoal hoodie with the exact white lowercase chest wordmark doitong.com, jeans. Preserve the face, proportions, clothing and 3D style. Choose gestures semantically. No FILM CREW chest logo.", "biography_context": "Dorian grew up in Tampere tinkering with video cameras borrowed from the local public library. After studying visual communication in Helsinki, he relocated to Lisbon chasing better light, cheaper studio space and a creative community outside the Nordic bubble. He spent three years as a motion-graphics operator for a boutique ad studio before going independent, specializing in helping solo operators and micro-brands translate big-campaign aesthetics into single-person production pipelines. He discovered Doitong while trying to accelerate a client's product-image turnaround and immediately started documenting every workflow that actually shipped results. His blog is a running log of real client briefs — stripped of confidential details — turned into repeatable visual lessons. He films mostly at dawn in his converted garage studio, where a dark-painted wall doubles as his brand's signature backdrop.", "wardrobe_and_visual_rules": "Brand motion style: dark/night foundation with controlled cream, sky or red contrasts; Inter 600–700, red rounded emphasis, large expressive imagery and the unchanged 3D mascot in 2–3 scenes. Use the full creative block library: reveals, comparisons, close details, contact sheets, moodboards, moving carousels, film, storyboard panels, print/poster treatments, palette studies, curved story routes and image-to-video bridges. Layout, image scale, attention path and motion must serve the story; do not treat blocks as interchangeable generic cards. Keep captions readable, source clips truly playing and motion deterministic at every timestamp.", "forbidden": "No flat 2D substitution for the source mascot, unrelated repeated stickers, identical adjacent compositions, placeholder drawings for generated examples, abrupt pose swaps, text overflow, blocked subtitles, invented product screens, unsupported model labels, fabricated earnings or personal results. No literal machine translation that breaks English layout or speech. No permanent waist-up host, duplicate subtitle row, bright alternating slide-show cards, blank waits between narration phrases, or a single image pretending to be a phone/chat/waveform scene. No near-identical scene sequences, hooks or creative briefs across recent episodes. No block-library name that falls back to a generic picture card. Do not order extra materials merely to increase variation." } OPERATOR'S CHARACTER-SHEET PROMPT: Use the approved branded Doitong mascot as identity authority. Preserve its 3D appearance, red cap, charcoal hoodie with exact white doitong.com wordmark and colors. All poses retain the same identity and readable chest branding. 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.