Men's Jacket Virtual Try-On

Identity: the face, skin, body and hair come exactly from #Image1 and never change. Where a hairstyle is described below, style that person's own hair into it; never change the hair's colour, length or texture. Apply only the outfit, makeup, hairstyling, actions and setting described below. PROMPT 1 — MiniMax H3 (15s, 9:16, Reference to Video) subject_definitions: <Subject 1> "streetwear model" — from #Image1: the subject. The subject's own hair is styled tousled, with pieces falling across the forehead. Small gold hoop earring in the left ear. Thin brown leather cord necklace. Calm confident expression with a natural slight smolder. The subject's face and earring must remain identical in every frame — identity locked from #Image1. <Subject 2> "all-black streetwear outfit" — from #Image2: a complete men's all-black streetwear look consisting of the following items, each described exactly as shown: - Black leather bomber jacket: oversized fit, smooth black leather with subtle sheen, pointed fold-down collar, silver-tone front zip closure, elastic ribbed knit cuffs and waistband in black, slightly puffy sleeves with natural leather creasing - Black ribbed tank top: slim-fit ribbed cotton vest with scoop neckline, form- fitting torso, visible ribbed knit texture, worn tucked or semi-tucked under the trousers - Black leather belt: smooth matte black leather strap with a rectangular silver metal buckle, single-prong closure, clean minimal design - Black wide-leg pleated trousers: tailored high-waisted fit at the top with a single front pleat on each leg, full wide-leg drape, clean pressed crease, cuffed hem at the ankles, structured woven fabric with a slight wool-blend appearance - Black chunky combat boots: lace-up ankle-height boots with thick platform sole, yellow contrast stitching along the welt (Dr. Martens style), black leather upper with 8-eyelet lacing, pull tab at the back heel, chunky rubber tread outsole Every piece must appear exactly as described from #Image2 — correct materials, correct fit, correct hardware colors. summary: keyframe completion + reference generation. #Image1 anchors <Subject 1>'s exact face, hair, and identity in every frame — this is a Virtual Try-On vlog-style showcase. #Image2 provides the complete outfit reference — every garment, accessory, and boot must match the items shown in #Image2 precisely. The model from #Image1 wears the full outfit from #Image2. The output is a 15-second vertical 9:16 men's streetwear bedroom vlog video with natural diffused indoor light, warm beige-toned bedroom set, and casual confident energy. retention_analysis: <Subject 1>: fully_preserved (face, gold hoop earring, leather cord necklace — identical in all 4 shots, no drift, no substitution) <Subject 2>: fully_preserved (every outfit piece from #Image2 maintained — black leather bomber jacket sheen and collar, black ribbed tank top texture, black leather belt with silver buckle, black wide-leg pleated trousers with cuffs, chunky combat boots with yellow stitching — all correct in every shot where visible) detailed_description: [Shot 1] Static medium shot, vertical 9:16. Warm beige-toned bedroom interior — a wooden wardrobe with slatted doors visible behind on the left, a minimalist desk with a lamp on the right, natural diffused light from a window screen-left casting soft warm shadows. <Subject 1> stands centered in the frame from the waist up, wearing the black ribbed tank top from #Image2 — the ribbed texture visible on the subject's torso, scoop neckline showing the subject's brown leather cord necklace. The subject's gold hoop earring glints in the left ear. The subject holds the black leather bomber jacket from #Image2 on a wooden hanger in the subject's right hand, presenting it toward the camera at shoulder height — the jacket hangs open showing its silver zip, pointed collar, elastic ribbed cuffs, and the smooth leather sheen catching the window light. The subject looks directly into the lens with a slight confident smile, eyes engaging the viewer. The subject's own hair is naturally tousled. Face is #Image1 — identical throughout. [English] Okay this jacket is doing all the work. (S1) — casual, confident, vlog-conversational tone, slight head nod at "all the work." Natural room tone, warm and intimate. [Shot 2] At 00:04.000, quick outfit transition — a fast vertical wipe or jump cut. <Subject 1> now wears the full look from #Image2: the black leather bomber jacket layered open over the black ribbed tank top, the black wide-leg pleated trousers sitting at the subject's natural waist with the black leather belt visible — silver rectangular buckle catching light — the trousers draping with a clean pressed crease and cuffed at the ankles above the black chunky combat boots with yellow contrast stitching and thick platform sole. The subject stands steady in the bedroom with both hands casually in the trouser pockets, the jacket falling open naturally showing the tank top underneath. The subject looks down briefly at the boots — a natural self-check — then looks up at the camera with an approving expression. Face is #Image1 — same earring, identity locked. The combat boots hit the floor with a single solid step as the subject shifts weight. [English] The boots just lock it in. (S1) — relaxed, affirming tone, slight smile, a small nod of approval. The subject emphasizes "lock it in" with a subtle hand gesture pulling from the pocket. [Shot 3] At 00:08.000, full-body shot, slightly wider framing showing head to boots. <Subject 1> steps forward from near the wardrobe toward the camera with a relaxed unhurried pace. The chunky combat boots from #Image2 are clearly audible — solid deliberate footsteps on the bedroom floor. The wide-leg pleated trousers sway naturally with each step, the leather jacket moves with the subject's body, the belt buckle glints. As the subject approaches mid-frame, the subject reaches to the desk and casually picks up a pair of dark sunglasses, slides them onto the top of the subject's head. The subject then turns 90 degrees to the subject's left, presenting the side silhouette to camera — the clean structure of the leather bomber jacket is highlighted in profile: the collar line, shoulder drop, puffy sleeve, elastic cuff, and the jacket's length falling at the hip. The wide-leg trousers create a strong vertical line below. The subject holds the pose for a beat. Face is #Image1 in profile — same earring visible. Camera remains static, the subject walks toward it. [Shot 4] At 00:12.000, slow smooth push-in from medium to close-up. The framing starts at upper body — the leather bomber jacket collar, the ribbed tank top neckline, the brown leather cord necklace all visible. As the camera pushes in slowly, the gold hoop earring and the necklace cord become detailed. The frame tightens to the subject's face from #Image1. The subject smiles confidently — a warm genuine smile — and looks directly into the camera. Face is #Image1 — identical, identity locked, final confirmation. [English] That's the fit. (S1) — short, definitive, satisfied, with a small decisive nod. At 00:14.500, the frame freezes — a clean freeze-frame on the subject's smiling face, holding for the final half-second. Slight film-grain texture appears on the freeze-frame for a vlog-authentic finish. overall_soundscape: Natural warm room ambience throughout — soft indoor tone, faint distant traffic hum, the lived-in feeling of a bedroom. At 00:00.500, subtle leather creak as the subject holds the jacket on the hanger. At 00:04.500, the solid thud of the combat boot hitting the floor — heavy, grounded, deliberate. At 00:08.000–00:10.000, rhythmic boot footsteps — chunky and audible on hard flooring, two to three steps. At 00:08.500, faint fabric rustle of the leather jacket moving. At 00:12.000, soft leather creak from the jacket as the push-in begins. The subject's voice is natural, close-mic, warm and intimate — vlog proximity. non_diegetic_music: Low-frequency street-style background instrumental — muted boom-bap beat with a deep sub-bass line and sparse dusty snare hits, 80–85 BPM. The beat enters softly at 00:00.000 and stays underneath the dialogue without competing. A warm muted piano or Rhodes sample loops minimally. At 00:12.000, the music begins fading out. By 00:14.000, the beat has fully dissolved to silence before the freeze-frame. No vocals, no lyrics. The vibe is laid-back, masculine, understated cool. Exclusions: No face change — <Subject 1>'s face from #Image1 must remain identical throughout, including gold earring and leather cord necklace. No identity drift, no substitution. No outfit changes beyond what is scripted — every piece from #Image2 must be worn correctly in every shot from Shot 2 onward. No garment swaps, no color shifts. No harsh or studio lighting — natural diffused indoor window light only. No watermarks, no brand logos, no text overlays at any point. No subtitles or captions. No additional people in frame — <Subject 1> is the sole person. No theatrical or exaggerated acting — natural, casual vlog energy throughout. No camera shake except subtle organic handheld feel in Shot 4 push-in. No background clutter — the bedroom is clean, minimal, warm beige-toned. No wrong outfit items — no substituting pieces not shown in #Image2. No face distortion or flickering identity between cuts. No Chinese text or garbled characters on any surface. Settings: MiniMax H3 | Reference to Video | 9:16 | 15 seconds Constraints: never change the person's face, skin or body, and never change the colour, length or texture of the person's hair — style it only as described.