正在加载视频...

视频加载失败

MiniMax H3 + Suno Beat-Synced Character Showcase Across 5 Environments First create a 15-seconds Suno track with style "punchy 4/4 beats" Then use your character reference sheet and generated audio track as references. MiniMax H3 Prompt: Use @[char ref] as the strict character reference and @[audio ref] as the...

18,006 次观看 • 1 个月前 •via X (Twitter)

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

GPT-Image-2 + Seedance 2.0目前已成AI视频标配 甚至可以根据给定图片推导过去和未来,制作storyboard,然后生成视频 使用方法: 1️⃣ 随便找一张图 2️⃣ 给以下提示词,然后制作storyboard 用以下提示词👇: Create a 3×3 cinematic storyboard grid based on the uploaded reference image. Use the uploaded image as the central moment of the story: Frame 5 must represent the exact “t” moment, matching the subject, scene, mood, composition, costume, environment, lighting style, and emotional tone of the reference image. The storyboard must show what happened before and after this moment as a time-based visual timeline. FRAME STRUCTURE: Frame 1: t-30: Establishing shot, the wider environment before the main event begins. Frame 2: t-10: The subject approaches or prepares for the key moment. Frame 3: t-5: Tension builds, body language and atmosphere lead toward the reference image. Frame 4: t-1: Final instant before the reference image, close emotional or action transition. Frame 5: t: Recreate the uploaded reference image as the central key frame. Frame 6: t+1: Immediate reaction or continuation right after the key moment. Frame 7: t+5: Alternate angle showing the consequence of the moment. Frame 8: t+15: Candid transition frame, natural movement, emotional aftermath. Frame 9: t+30: Strong final cinematic frame that clearly resolves the scene. STYLE: Ultra-realistic cinematic storyboard, 3×3 grid layout, cohesive visual tone across all frames, consistent character identity, consistent costume, consistent environment, cinematic lighting, shallow depth of field, realistic camera angles, natural motion continuity, no text labels, no numbers, no arrows, no captions inside the image. 3️⃣ seedance2.0 一键成片

Jason Zhu

34,160 次观看 • 5 个月前

Would you underestimate her just because she wears a school uniform? GPT Image 2 + Seedance 2.0 on Sjolt Try Canvas: prompt Character Identity Lock (Highest Priority): Use the exact same young East Asian woman from the provided reference character sheet. Preserve 100% identical facial features, face shape, eye shape, nose, lips, skin tone, hairstyle, hair color, proportions, and overall identity throughout the entire video. Do not redesign, reinterpret, or substitute the character. She must remain instantly recognizable as the same person from the reference image. She has shoulder-length wavy silver-gray hair with subtle blue undertones, bright expressive eyes, fair skin, and a confident slight smile that naturally transitions into a focused, determined combat expression. She wears the identical navy blue Korean high school uniform blazer over a gray sweater vest, white collared shirt, striped tie, and matching school skirt from the reference character sheet. Video Prompt: A cinematic, hyper-realistic action sequence inside a chaotic South Korean high school classroom. The classroom is filled with overturned desks, scattered chairs, flying notebooks, broken pencils, and papers drifting through the air. Bright natural daylight streams through large classroom windows, creating realistic highlights, soft shadows, and cinematic contrast. The young female student moves with incredible speed, confidence, and precision as she expertly defends herself against multiple aggressive male students wearing matching Korean school uniforms. Every movement is fluid, athletic, and grounded in realistic martial arts choreography. The camera remains highly dynamic, featuring cinematic handheld tracking shots, fast push-ins, orbit shots, dramatic slow-motion moments, whip pans, low-angle hero shots, and close-up impact shots. Capture rapid combinations of punches, clean high kicks, evasive footwork, parries, elbow strikes, blocks, and throws. Desks slide across the floor, chairs topple over, and dust particles catch the sunlight, emphasizing the intensity of the action. Maintain a high shutter-speed action-photography aesthetic with crisp motion detail, subtle motion blur only during extremely fast movements, physically accurate body mechanics, realistic cloth simulation, natural hair physics, authentic facial expressions, and believable impact reactions. Keep the camera frequently returning to sharp close-ups of her face to reinforce character continuity and emotional intensity. Her silver-gray hair flows naturally with every movement while her determined eyes remain locked on her opponents. Photorealistic cinematic quality, 4K HDR, ultra-detailed skin textures, realistic lighting, volumetric daylight, physically based rendering, shallow depth of field during close-ups, blockbuster Korean action film aesthetic, empowering heroine energy, consistent facial identity throughout every frame, no face drift, no character variation, no animation-style exaggeration.

Sharon Riley

26,184 次观看 • 2 个月前

Created with Google Flow Character Sheet Prompt : Create a professional, ultra-photorealistic CHARACTER CONSISTENCY SHEET using the uploaded reference image as the ONLY source for the character's identity. IMPORTANT — IDENTITY LOCK: The uploaded reference image is the definitive identity reference. Reproduce the EXACT SAME PERSON throughout the entire character sheet. Do NOT redesign, beautify, reinterpret, or replace the character. Preserve with maximum accuracy: - exact facial identity - facial structure and proportions - eyes, eye shape and iris color - eyebrows and natural brow shape - nose shape and proportions - lips, mouth shape and fullness - cheeks, jawline and chin - skin tone and natural skin texture - age appearance - hairline - exact hair color, length, texture and hairstyle - body proportions and physique - distinctive facial characteristics CHARACTER SHEET LAYOUT: Create one clean, professional reference-board image containing: 1. LARGE FRONT PORTRAIT / FACE CLOSE-UP 2. FRONT VIEW 3. 3/4 LEFT VIEW 4. 3/4 RIGHT VIEW 5. LEFT PROFILE 6. RIGHT PROFILE 7. BACK VIEW 8. FULL-BODY FRONT VIEW 9. FULL-BODY 3/4 VIEW 10. FULL-BODY SIDE VIEW 11. FULL-BODY BACK VIEW 12. NEUTRAL EXPRESSION 13. NATURAL SMILE 14. SOFT SMILE 15. LOOKING LEFT 16. LOOKING RIGHT 17. EYE CLOSE-UP 18. EYEBROW CLOSE-UP 19. NOSE CLOSE-UP 20. LIPS CLOSE-UP 21. HAIR CLOSE-UP 22. ACCESSORIES CLOSE-UP 23. OUTFIT / CLOTHING REFERENCE 24. COLOR PALETTE / SKIN-TONE REFERENCE CONSISTENCY: Every panel must show the SAME person. Keep facial identity, proportions, hairstyle, skin tone and physical characteristics consistent across every angle, pose and expression. For views not clearly visible in the reference, intelligently reconstruct the character while staying strictly faithful to the visible reference. Do not invent major distinguishing features. PRESENTATION: Premium professional film-production character bible / modeling reference sheet. Clean editorial layout. Neutral studio background. Soft realistic studio lighting. Sharp facial details. Natural skin pores and texture. Individual hair strands. Realistic fabric and accessories. Accurate human anatomy. Consistent camera perspective. Clean thin borders between panels. Professional labels underneath each view. Minimal elegant typography. High-end fashion/model reference aesthetic. PHOTOREALISM: Ultra-photorealistic. Real human appearance. Natural skin texture. Realistic eyes. Physically accurate hair. Natural shadows. Realistic proportions. No CGI appearance. No plastic skin. No doll-like face. No artificial beauty-face replacement. NEGATIVE PROMPT: different person, different face, face morphing, identity drift, altered facial structure, different eyes, different nose, different lips, different jawline, different skin tone, different hairstyle, inconsistent body proportions, duplicate person, distorted anatomy, asymmetrical face, plastic skin, waxy skin, CGI, 3D render, cartoon, anime, illustration, over-beautification, excessive makeup, unrealistic eyes, blurry face, low detail, extra fingers, missing fingers, malformed hands, bad anatomy. OUTPUT: One complete, highly detailed professional CHARACTER CONSISTENCY SHEET in a single image, suitable as a master reference for generating consistent images and videos of this character.

M. Asif

85,616 次观看 • 23 天前

📖THE STEP MOST CREATORS SKIP IS WHY THEIR AI ANIMATION LOOKS INCONSISTENT Consistency across clips doesn't come from prompting — it comes from the reference image. The pipeline, step by step: ▪ Start with ChatGPT Image 2 — generate a full character design sheet first, not just a single frame. Multiple angles, expressions, and outfit variations in one image keeps the character consistent across every scene ▪ Build a storyboard inside ChatGPT Image 2 as well — define each shot, camera angle, action, and mood before touching Seedance at all. This is the step most people skip and it's the reason clips look disconnected ▪ Define a color palette and lighting mood early — golden afternoon light, soft warm tones, dramatic shadows. Lock those values and repeat them across every prompt ▪ Take each storyboard frame into Seedance 2.0 as the reference image — one frame becomes one clip ▪ Write the Seedance prompt around the character action, not the scene description. The scene is already in the image. The prompt handles motion, camera behavior, and timing ▪ Keep clip duration between 4-6 seconds per shot — shorter clips give more control over pacing and reduce motion drift on character faces ▪ Match camera movement type across consecutive clips — if one shot dollies in, the next should hold or pull back, not dolly again The consistency across these frames comes from the character design sheet, not from luck. Seedance reads the reference image and the prompt together — if the reference is detailed enough, the output stays on-model. This video was created by ALOKXMEHTA 📥 tomorrow: the exact ChatGPT Image 2 prompt structure used to generate a multi-angle character design sheet like this one 🔖One article covers the entire workflow — it is pinned below, do not scroll past it.

Zentrix⌚️

14,015 次观看 • 3 个月前

Created with Kling 3.0 on Kling AI Prompt: Create a 15-second high-fashion editorial film starring the adult character in >> . Preserve their exact appearance, outfit, accessories and visual style. Render the entire film in the reference’s aesthetic. Use a minimal studio with a reflective floor, bold directional lighting and rhythmic photographic flashes. Show exactly 10 distinct fashion poses, each with a different silhouette and camera angle: 1. A confident standing pose, filmed from floor level with dramatic wide-angle perspective. 2. One hand beside the face, captured in an extreme side-profile close-up. 3. An asymmetric seated pose, seen directly overhead as the camera rotates. 4. One leg extended toward the lens, the foot or reference footwear dominating the foreground through foreshortening. 5. A quick, fluid leg cross, captured from a low diagonal angle. 6. Fingertips catching the edge of an existing sleeve or collar, framed in a tight detail shot. 7. A rear three-quarter turn with a deliberate glance back into the camera. 8. A forward lean toward the lens, ending with the palm briefly covering it. 9. An elongated upward stretch, revealed in a sharply tilted wide shot with strong side lighting. 10. A commanding full-body hero pose, looking down into the lens as the camera rapidly pulls back. Keep the performance fast and rhythmically tight. Flow naturally between poses, holding each for only a fraction of a second while keeping its silhouette clearly readable. No repeated poses or additional pose changes. Connect angles through whip pans, movement-matched cuts, snap zooms, flashes and lens occlusions. Orbit against the character’s turn, sweep from their floor reflection toward their face and plunge from overhead to floor level. Alternate intimate details with dramatic wide compositions. Accelerate between poses and brake sharply on each hold. Keep the sensual gestures quick, confident and fully clothed. Hair and fabric react naturally. No slow motion, lingering shots or gradual camera drift. Build momentum toward the tenth pose, then stop sharply for a crisp final hold. Stable identity and anatomy throughout. No outfit changes, added accessories or text. Sound: a driving 140 BPM fashion beat, rhythmic shutter clicks and subtle fabric movement.

Zara

19,857 次观看 • 25 天前

Made to move. Designed to shine. ⚽✨ Created with Seedance 2.0 on TapNow PROMPT: Create a 15-second high-fashion football shoe advertisement using the uploaded reference images for the gold metallic football cleats, white knee-high socks, and vintage feminine football styling. Keep the footwear design, colors, textures, and proportions consistent throughout the entire video. Environment: An enormous open outdoor football field, covered in lush natural green grass, with a completely open horizon and a beautiful dreamy pastel blue-and-pink sky. The field should feel spacious and untouched. No stadium, no spectators, no buildings, no bleachers, no indoor environment, no close fences. 0–3 sec: Wide cinematic shot of a young adult female footballer standing alone in the middle of the vast open field. She wears the same elegant vintage-inspired outfit from the reference images with white knee-high socks and the gold metallic football cleats. She gently places one foot on a football. Camera slowly moves toward her while sunlight reflects beautifully off the cleats. 3–6 sec: Cut to dramatic close-up shots of the gold cleats. Her foot steps firmly onto the grass, the studs press naturally into the turf, and she tightens the laces. Macro camera movement reveals the metallic texture, stitching, sole, and studs. Make the shoes the visual hero. 6–10 sec: She starts playing football across the completely open field, dribbling the ball quickly and confidently. Use a low-angle tracking camera focused on her feet and cleats as she changes direction, accelerates, and controls the ball. Her flowing outfit moves naturally with her movement. 10–13 sec: She takes a powerful run-up and strikes the football with the gold cleat. Capture the kick in cinematic slow motion, showing the shoe making contact with the ball, grass particles flying naturally, and the ball launching across the open field. 13–15 sec: Premium hero shot. The football rolls to a stop beside her gold cleats. She stands confidently in the background on the vast green field as warm sunlight catches the metallic shoes. Camera slowly pushes toward the cleats and ends on a sharp product-focused close-up. Visual style: luxury sports fashion campaign, dreamy editorial photography, cinematic natural lighting, realistic football movement, realistic grass physics, elegant feminine styling, dynamic camera movement, macro shoe details, shallow depth of field, premium commercial quality, photorealistic, subtle film texture. Important: Keep the gold football cleats identical throughout the video. No changing shoe design, no distorted feet, no extra limbs, no warped football, no artificial CGI appearance. The entire video takes place outdoors on one vast open football field.

Soulful Ai

16,834 次观看 • 1 天前

When the subway platform turns into a full-blown action scene. 🥊🚇🎬 Created with Seedance 2.5 Prompt:Create a 10-second cinematic action sequence set inside a gritty modern subway station, featuring a determined young woman confronting a larger male attacker on a wet underground platform. Maintain the same character appearance, facial features, body proportions, hairstyle, clothing, and accessories throughout the entire sequence. Begin with a cinematic medium shot of the woman standing on the subway platform beside a stopped silver train, looking alert and focused as the male opponent approaches her from the side → transition into a sudden close-range confrontation as the man attempts to attack, while she quickly reacts and raises her arms defensively → cut into a dynamic action sequence as the woman delivers a powerful side kick toward the man's torso, with realistic body mechanics and believable impact → transition to fast handheld-style camera movement as both characters exchange rapid punches, blocks, dodges, and defensive movements across the platform → capture the woman's controlled fighting technique as she remains balanced and focused while the larger man struggles to keep up → cut to a dramatic low-angle shot as she delivers a final powerful strike, causing the man to lose his balance and fall heavily onto the wet platform → show him lying on the ground while the woman stands above him, breathing steadily and watching him cautiously → transition to a wider cinematic shot as she turns away and begins walking down the subway platform while the defeated man remains motionless in the foreground → final shot follows behind the woman as she walks away beside the stationary train, creating a stylish action-movie ending. Visual style: high-end cinematic action filmmaking, realistic human movement, gritty underground subway atmosphere, wet reflective floor, dramatic overhead fluorescent lighting, realistic train details, natural clothing movement, subtle motion blur, dynamic handheld camera, low-angle action shots, fast cinematic cuts, believable martial-arts choreography, realistic impact physics, strong facial expressions, shallow depth of field, atmospheric urban tension, polished color grading, intense but grounded action tone. Character consistency: preserve the woman's exact facial identity, hairstyle, body proportions, black outfit, and overall appearance throughout every shot. Preserve the man's appearance, clothing, hairstyle, and body proportions throughout the entire sequence. No character morphing or identity drift. Negative prompt: distorted faces, changing faces, character morphing, extra limbs, missing limbs, extra fingers, broken hands, unnatural anatomy, floating bodies, unrealistic physics, cartoon movement, exaggerated CGI, duplicated characters, clothing changes, hairstyle changes, inconsistent characters, warped train, flickering background, excessive motion blur, text, subtitles, logos, watermark.

Elvorya

19,493 次观看 • 6 天前

Created with Minimax H3 Max Prompt: "Create a 15-second cinematic, photorealistic continuous-shot video based exactly on the reference image of “The Floating Night Market.” Preserve the original architecture, floating wooden market platforms, lantern designs, vendors, customers, boats, ocean, mountains, color palette, and overall composition. Do not redesign or replace any major elements. 0–3 seconds: Begin with a slow, smooth low-angle camera movement just above the dark ocean surface, approaching the floating night market. Hundreds of warm glowing paper lanterns gently sway in the night breeze. Their golden reflections shimmer naturally across the moving water. Small waves softly move around the floating platforms. 3–7 seconds: The camera slowly rises and moves forward through the market, revealing lively activity. Vendors naturally prepare food at small wooden stalls, gently stirring steaming pots and grilling food. Thin realistic steam rises into the lantern light. Customers walk casually across narrow wooden bridges, talking and browsing. Lanterns flicker subtly and sway with the wind. 7–11 seconds: Continue the same uninterrupted camera movement with a gentle cinematic arc around the market. Small traditional boats slowly pass underneath the floating platforms. Water ripples spread behind them. Food stalls glow with warm orange and amber light while the cool blue moonlight illuminates the surrounding ocean. The huge full moon remains visible in the background behind misty mountains. 11–15 seconds: Slowly pull upward and backward into a wider cinematic reveal, showing the entire floating night market surrounded by the vast ocean. Hundreds of lanterns form a glowing trail across the water. Reflections stretch and break naturally with the waves. Mist gently drifts around the distant mountains as the moonlight creates a magical atmosphere. End on a beautiful wide establishing shot. Visual style: ultra-photorealistic, cinematic fantasy, realistic human movement, realistic ocean and water physics, detailed wooden textures, natural lantern glow, volumetric moonlight, subtle atmospheric fog, realistic steam, shallow depth of field during close shots, cinematic 35mm photography, high dynamic range, extremely detailed, immersive scale, smooth professional camera movement. Motion: natural human gestures, subtle wind movement, gently swaying lanterns, flowing steam, moving water, realistic boat movement, no exaggerated animation. Camera: smooth stabilized cinematic camera, slow controlled movement, natural depth of field, gradual push-in → forward tracking → gentle arc → wide pull-back. One continuous shot with no cuts. Negative prompt: no scene changes, no cuts, no jump cuts, no camera shake, no distorted faces, no duplicated people, no warped buildings.

Nafees

10,863 次观看 • 23 天前

POV: You have 15 seconds to decide what to wear… and somehow end up with THREE completely different looks 😂✨ From casual to party-ready. which outfit would you choose? 👀💃 Created in Minimax H3 Prompt: Format: 15 seconds | 16:9 | 4K HDR | 24fps | photorealistic cinematic vlog Character: Use the girl from the uploaded reference image as the exact character reference. Preserve her facial identity, eye color, skin tone, hairstyle, body proportions, and overall appearance consistently throughout every shot. No face changes or identity drift. Scene & Story: 0–3 sec — The Mystery Package The video opens with a handheld creator-vlog shot in her cozy bedroom during late afternoon. She walks into frame holding a stylish garment bag, looking genuinely curious. She places it on the bed and looks directly into the camera with a playful expression. She says naturally: “Okay… I found something for tonight, but I have absolutely no clue if I can pull it off.” She unzips the garment bag, revealing only a glimpse of the outfit. 3–6 sec — First Reveal She quickly steps behind a nearby room divider. The camera follows with a fast handheld whip-pan. She emerges wearing a chic fitted top, tailored trousers, and elegant heels. She looks at herself in the mirror, slightly surprised by how good it looks. She turns toward the camera and says: “Wait… this might actually work.” She gives a small confident pose. 6–9 sec — The Unexpected Switch Instead of snapping her fingers, she grabs a jacket hanging beside her and dramatically throws it toward the camera. As the jacket briefly covers the lens, the outfit seamlessly transforms underneath it. When she pulls the jacket away, she is wearing a completely different fashion-forward look: a stylish mini dress with statement shoes and subtle accessories. She looks down, raises one eyebrow, then laughs. 9–12 sec — The Wild Card She walks toward the mirror while the camera circles around her. She notices a third outfit hanging on the wardrobe door. Suddenly, she steps backward and spins. During the spin, her outfit naturally morphs into a glamorous evening look with a sophisticated silhouette, elegant heels, and refined accessories. The transformation happens continuously during the movement with realistic fabric motion — no jump cut. 12–15 sec — Final Decision She walks toward the camera with confident energy, then stops very close to the lens. She looks at the camera, points toward herself, then gestures toward the three outfits visible behind her. With a playful smile, she says: “Okay… you’re choosing. Which one?” The camera quickly pushes in toward her face as she laughs, ending on a natural freeze-like moment. Visual Direction: Ultra-realistic fashion creator vlog, authentic handheld camera movement, natural body language, expressive facial reactions, realistic fabric physics, seamless outfit transitions, natural hair movement, subtle mirror reflections, cinematic depth of field, realistic skin texture, soft late-afternoon daylight mixed with warm practical bedroom lighting, detailed wardrobe and bedroom environment, premium fashion-film aesthetic while maintaining casual YouTube-vlog energy. Camera: Handheld selfie framing, medium shots, quick whip-pans, subtle camera shake, smooth tracking movements, one controlled orbit around the character, final slow push-in. Audio: Natural bedroom ambience, fabric and wardrobe sounds, footsteps, garment movement, subtle mirror-room reverb, upbeat modern fashion-vlog background music, natural spoken dialogue, soft whoosh effects during the outfit transitions. No subtitles, no logos, no watermark. Consistency & Quality: No jump cuts during transformations. No duplicated character. No distorted hands or fingers. No warped clothing. No inconsistent room layout. No facial identity changes. No unnatural skin smoothing. Keep the same character, bedroom, lighting logic, and visual realism throughout.

H A J R A

27,953 次观看 • 1 个月前

Made with Seedance 2.5 Prompt: Character: A beautiful woman in her early 20s with natural realistic features, long dark brown hair, athletic build, wearing a sleek black tactical jacket, fitted dark pants and combat boots. She looks determined and fearless. Scene — 0–3s: Nighttime in a rain-soaked city alley. Neon signs reflect across the wet pavement. The woman runs toward camera as a black SUV suddenly crashes through a barricade behind her. Sparks and debris fly through the air. Scene — 3–6s: She quickly slides across the hood of a parked car, spins around and narrowly dodges an incoming attack. The camera follows her with a fast handheld tracking shot. Her hair and jacket move naturally with the action. Scene — 6–8s: She grabs a motorcycle helmet from the seat, jumps onto a sleek black motorcycle and accelerates through the alley. The SUV chases behind her, headlights cutting through the rain. Scene — 8–10s: The motorcycle launches off a small ramp between two buildings. Freeze-like slow motion as she flies through the air, city lights glowing behind her. She lands smoothly and speeds away. Visual style: High-end Hollywood action blockbuster, photorealistic, cinematic lighting, dramatic rain, realistic physics, practical-looking explosions, dynamic camera movement, shallow depth of field, anamorphic lens flares, detailed facial expressions, realistic skin texture, premium VFX. Camera: Fast tracking shots → low-angle action shot → close-up → wide aerial shot. Smooth but intense camera movement, cinematic motion blur. Audio: Heavy cinematic percussion, roaring motorcycle engine, tire screech, rain, impact sounds and a dramatic bass hit at the final landing. Important: Keep the same female character, face, hairstyle and outfit consistent throughout all shots. No text, no subtitles, no distorted anatomy, no extra limbs, no cartoon appearance.

H A J R A

12,282 次观看 • 23 天前

He picked the wrong baddie to mess with. Made with seedance 2.5 Prompt : Create a 13-second ultra-realistic cinematic action sequence set inside a messy, atmospheric urban apartment/studio filled with books, posters, scattered furniture, old equipment and warm practical lamps. Two young women in realistic casual streetwear are engaged in an intense hand-to-hand fight. Begin with a wide establishing shot showing the entire room as the confrontation starts. One woman suddenly attacks with a long wooden object, while the other quickly blocks and dodges the attack. Build the sequence with fast, believable choreography: blocking, punches, evasive movements, close-range grappling, aggressive shoves and a powerful takedown. The fighters should move naturally with realistic weight, balance and physical impact. Clothing, hair and bodies should react naturally to every movement. Use dynamic handheld cinematic camera movement, alternating between wide shots, medium tracking shots, low-angle shots and tight close-ups during impacts. Add subtle camera shake and realistic motion blur during fast movements, but keep the characters clearly visible. The room should remain consistent throughout the sequence. Bright cool daylight streams through large windows while warm orange lamps illuminate parts of the room, creating a gritty cinematic teal-and-orange contrast. Use realistic shadows, volumetric light, dust particles and reflections on the slightly polished floor. Toward the final seconds, the fight becomes more intense. One woman loses balance and is thrown to the floor. The other remains standing in the foreground, breathing heavily and maintaining a strong defensive stance as the camera settles into a dramatic final shot. Ultra-realistic human movement, authentic fight choreography, detailed facial expressions, natural skin texture, realistic hair physics, cinematic depth of field, 35mm film look, high dynamic range, realistic motion blur, dramatic practical lighting, premium Hollywood action-film cinematography, no cartoon look, no exaggerated physics, no unnatural body deformation.

Noor 🌸

15,860 次观看 • 13 天前

Create more. Do more. AI Tools brings image generation, video creation, AI chat, and coding together in one powerful workspace. Prompt: Create a 10-second ultra-realistic premium SaaS technology commercial using the uploaded storyboard image as the exact visual reference. Preserve the same dark futuristic workspace, laptop and smartphone positioning, purple-blue lighting, UI design, typography style, and overall premium tech aesthetic throughout the video. 0–2 seconds APP REVEAL Start with a cinematic close-up of the laptop on the modern desk. The screen displays the AI Tools platform homepage with the AI Chat, Image Generator, Video Generator, and Code Generator options clearly visible. Slowly push the camera toward the laptop screen with subtle ambient lighting and realistic reflections. 2–5 seconds AI IN ACTION Smoothly transition into the Image Generator interface. A hand types a creative prompt into the input field and clicks Generate. The interface responds instantly, with elegant UI animation as a high-quality image appears on screen. Keep the laptop, interface and branding visually consistent. 5–8 seconds MULTIPLE AI TOOLS Use fast, seamless cinematic transitions between four features: Image Generator → Video Generator → AI Chat → Code Generator. Show each tool briefly in action with smooth interface animations, dynamic screen transitions, and subtle camera movement. Make the experience feel fast, powerful and effortless. 8–10 seconds HERO SHOT Pull the camera back to reveal the laptop and smartphone together on the desk. Both screens display the AI Tools branding. Add a subtle purple glow and cinematic reflections. End with clean on-screen text: AI TOOLS Create. Generate. Elevate. Visual style: photorealistic, premium SaaS advertisement, cinematic lighting, dark modern desk setup, purple and blue ambient glow, realistic hands, sharp screen details, smooth camera movements, elegant UI animations, high-end technology commercial, no distorted text, no extra objects, no changing product design, no flickering, no warped hands, consistent branding throughout.

𝐒𝐊_𝐀𝐈

31,597 次观看 • 1 个月前

1. Open Gemini / Grok / GPT Image 2.0 2. Upload your photo 3. Copy the prompt 4. Generate 5. Prompt ⤵️ POV: One night, three looks… but only ONE can steal the spotlight. 👗✨ Which one would you choose? 👀💃 Created with MiniMax H3 🎬 Prompt Format: 15s | 16:9 | 4K HDR | 24fps | Photorealistic cinematic fashion vlog Character: Use the uploaded reference girl as the exact character. Preserve her facial identity, skin tone, eyes, hairstyle, body proportions, and appearance consistently. No face changes or identity drift. Story: 0–3s: In a cozy warm-lit bedroom, she enters with a stylish garment bag, places it on the bed, and looks playfully at the camera: “Okay… I have no idea what to wear tonight!” 3–6s: She steps behind a room divider. A quick whip-pan reveals Look 1 — chic fitted top, tailored trousers, and elegant heels. She checks the mirror and smiles: “Wait… I actually love this!” 6–9s: She throws a jacket toward the camera. As it covers the lens, seamlessly transform into Look 2 — a trendy mini dress with statement shoes and accessories. She looks surprised and laughs. 9–12s: She spins gracefully toward the mirror, smoothly transforming into Look 3 — a glamorous evening outfit with elegant heels and refined accessories. 12–15s: She walks confidently toward the camera, gestures toward all three looks and says with a playful smile: “Your turn… which one wins?” End with a cinematic push-in as she laughs. Visual Style: Ultra-realistic fashion vlog, natural expressions, handheld camera, cinematic depth of field, warm bedroom lighting, realistic skin, hair and fabric movement, smooth seamless transformations, premium fashion-film aesthetic. Audio: Natural bedroom ambience, footsteps, fabric sounds, upbeat fashion-vlog music, natural dialogue and subtle whoosh effects. Negative: No jump cuts, face changes, identity drift, duplicated character, distorted hands, warped clothing, inconsistent background, subtitles, logos, or watermark.

Arina Ai

18,680 次观看 • 1 个月前

nijiJourneyV6 & seedance2.0でkawaii系MV🎵 みんなで踊るプロンプトを共有。15秒で5枚のリファレンスを使用💕 ✳️seedance2.0プロンプト Use the uploaded images as the primary visual references for character design, facial style, color palette, graphic motifs, and overall kawaii-chaotic tone. 15-second music-video style animation, ultra cute and hyper pop, fast-paced, candy-colored, chaotic but readable, anime-inspired graphic motion. Main direction: The characters dance in a cute, playful, slightly chaotic “mob dance” / “idol crowd dance” feeling. The motion should feel inferred naturally from the reference images, not rigid choreography. Emphasize fast switching expressions, group-like energy, rapid cut transitions, and a dense pop visual atmosphere. Visual style: Pastel neon palette, pink, cyan, lemon yellow, mint, lavender. Bold clean outlines, flat shading, sticker-like icons, bows, flowers, sparkles, spirals, abstract shapes, pop symbols, glitchy accents, halftone dots, split panels, manga-like framing, layered collage feeling. Cute and stylish chaos, not horror, not grotesque. Character motion: Generate adorable dance movement with small bouncy steps, side-to-side body sway, quick hand poses, synchronized hops, idol-style gestures, playful pointing, little spins, shoulder pops, head tilts, wink poses, cheerful bouncing, cute rhythmic stepping.The dance should feel like a spontaneous cute flash-mob or idol crowd routine, with repeated shared gestures, group energy, and playful synchronized timing. Include moments that feel like a crowd dance or mob dance, even if only one or a few characters are visible at a time. The dance should feel energetic, spontaneous, and rhythm-driven. Expression direction: Rapid expression changes: smile, wink, surprised face, excited open-mouth face, mischievous grin, hypnotic stare, sparkling eyes, dizzy spiral-eye mood, overjoyed face, playful chaos. Expressions should switch quickly with the cuts, giving a hyperactive kawaii feeling. Editing / camera: Very fast-cut visual rhythm. Use rapid cut-ins, jump cuts, smash zooms, push-ins, pull-backs, diagonal framing, split-screen panels, close-ups of faces, occasional medium shots for dance, and layered pop composition. Cuts can change every 0.2 to 0.8 seconds. Alternate between close-up face shots, upper-body dancing, and brief group/crowd-energy compositions. The camera should feel lively and music-synced. Scene flow: 0–3s: Introduce the character(s) with fast close-ups, blinking, cute smile, eye highlights, bows/flowers/icons popping in, fast panel cuts. 3–6s: Start the dance with small synchronized idol-like motions, side steps, hand poses, bouncing shoulders, quick expression switches. 6–9s: Increase the chaos. More split panels, more characters or crowd-energy feeling, fast alternating expressions, quick hops, spins, and rhythmic pose changes. 9–12s: Peak energy. Cute mob-dance vibe, dense visual layering, multiple rapid cut-ins, close-up reaction faces, synchronized bounce and gesture-heavy movement. 12–15s: Final climax. Maximum kawaii chaos with energetic dancing, smiling faces, wink, big pose finish, layered pop symbols exploding around the frame, ending on a strong cute final pose. Important priorities: Keep the characters cute and appealing at all times. Preserve readability of faces and silhouette. Let the dance and expressions feel naturally inferred from the references. The chaos should come from editing, framing, layered motifs, and rapid expression changes, not from broken anatomy or visual confusion. Negative prompt: horror, dark tone, realistic style, grotesque face, body deformation, extra limbs, broken hands, scary expressions, dull colors, muddy palette, slow motion, empty background, overly realistic physics, unreadable face, low energy, depressing mood.Make the choreography feel partially AI-inferred from the visual mood of the references: cute, chaotic, rhythmic, slightly unpredictable, but always charming and musically coherent.

Toshi@ニャルオAI

13,761 次观看 • 3 个月前

Made with Seedance 2.0 by Yapper Prompt: MASTER CINEMATIC PROMPT — ROOFTOP CHASE (INTENSE VERSION) SUBJECT: image1 Use the first image as the main subject. Maintain consistent face, body shape, hairstyle, clothing, and proportions throughout the entire video. Use the image2 as the primary storyboard reference. The second image strictly defines scene order, framing, and timing. Prioritize matching the second image over any creative interpretation. ⸻ FACE LOCK The face must remain sharp at all times. No blur, no distortion, no flickering. Expression progression: focused → tense → survival instinct → aggressive. ⸻ OUTFIT LOCK (STRICT) White undershirt (lightweight, slightly sweat-soaked, visible fabric texture, natural wrinkles) Red shorts (knee-length, soft fabric, natural folds, slightly loose fit) Barefoot (no footwear, visible natural foot movement and contact with surfaces) Rules: * Outfit must remain identical in all frames * No color change, no design change, no wardrobe switching * Clothing must stay consistent even when wet * Fabric reacts naturally to wind, movement, and water * Feet must remain barefoot at all times (no shoes appearing) ⸻ ENVIRONMENT Jakarta dense urban rooftop (corrugated metal roofs, rough concrete, tightly packed buildings) Golden hour lighting with strong backlight Hazy atmosphere with airborne dust particles Environment feels hot, dense, and visually chaotic ⸻ STYLE CORE Live-action, ultra-realistic, AAA cinematic quality High contrast, gritty, intense tone Natural motion blur (strong during fast movement) Heavy debris interaction and environmental destruction emphasis ⸻ CAMERA SYSTEM Handheld tracking, very close to the subject Micro-shake increases slightly on impact (controlled, not chaotic) Dynamic continuous movement following subject momentum Rule: Camera must feel physically present in the action No teleporting, no glitching Subject remains dominant in frame ⸻ TIMELINE (STRICT — HARD ACTION) 0.0 – 1.2s Wide rooftop view of Jakarta. Subject sprinting. A loud CRACK — bullet hits metal very close. Large sparks burst, slight camera shock reaction. ⸻ 1.2 – 2.5s Tight rear tracking shot. Heavy barefoot footsteps on metal roof (visible contact and impact). Bullet nearly hits the foot — debris flies toward camera. Clothesline hits his face; he forcefully pushes through without slowing. ⸻ 2.5 – 4.0s Fast slide under water tank. Bullet pierces the tank — heavy water burst crashes down. Clothing becomes wetter, sticks slightly to body. Camera partially passes through the water splash. He rolls hard and drops to a lower rooftop with impact weight. ⸻ 4.0 – 5.5s Running along a narrow ledge. Two rapid shots — concrete explodes beside his shoulder. Debris flies past camera. He nearly loses balance but recovers instantly. ⸻ 5.5 – 7.0s Full sprint into a large building gap jump. Slow motion mid-air. Bullet hits the edge behind him — fragments scatter in the air. Landing is unstable but controlled (barefoot impact visible). ⸻ 7.0 – 8.5s Grabs fire escape railing aggressively. Bullet slams into metal right beside his face — intense sparks. Camera swings with the momentum. He pulls himself up with force. ⸻ 8.5 – 9.5s Fast aggressive climb using windows and AC units. Bullet shatters glass right beside his head. Glass shards fall downward. Movement is fast, urgent, controlled panic. ⸻ 9.5 – 10.0s Reaches rooftop. Bullet hits near his feet. He pauses briefly, spots a hidden sniper suitcase under a water tank. Immediately sprints toward it. ⸻ PHYSICS & EFFECTS Bullet impacts create strong sparks, debris bursts, and visible force Water hits with weight and affects clothing behavior Barefoot contact interacts realistically with surfaces Camera reacts subtly to shock impacts Environment responds dynamically ⸻ CONSTRAINT No cuts No gore No additional scenes No timeline changes No mirrored movement No face distortion

Zar⭕on

11,116 次观看 • 4 个月前

EVERYONE PROMPTS THE ACTION. ALMOST NOBODY LOCKS THE IDENTITY — WHICH IS WHY TWO-CHARACTER SCENES FALL APART. Two freerunners racing across Tokyo rooftops, eight cuts, corkscrews over a rooftop gap at the end. The parkour is the easy part. Keeping them two separate people who never blend into each other is the part that actually breaks. Here's the full prompt built that way. Attach two reference photos as image_1 and image_2, and the same structure works for any multi-character action piece: FORMAT: 15 seconds, 16:9, 1080p, 8-cut cinematic ultra-advanced parkour footage. CHARACTERS: Two realistic individuals from image_1 and image_2. Use the attached images as absolute character references, and fully maintain the facial features, hairstyles, hair colors, skin textures, body types, height differences, outfits, color schemes, and age appearances of each person across all cuts. No altering into different people, face swaps, outfit changes, hairstyle changes, or mixing of the two individuals' features. SETTING: A sunny modern Japanese city reminiscent of Tokyo, Shibuya, and Yokohama — rooftops, alleys, staircases, railings, pipes, concrete walls. The two protagonists, as equals, race through at high speed running side by side, following, crossing paths, and coordinating. CUTS: 1. (00:00–00:01.60) Low-angle rear tracking. Both accelerate side by side and simultaneously kong vault over separate obstacles. 2. (00:01.60–00:03.40) Front low-angle. One wall runs the left wall, the other the right, then tic-tac to cross in midair and land on opposite rooftops. 3. (00:03.40–00:05.20) Lateral tracking. Consecutive precision jumps, then cat leaps to grab and climb a high wall. 4. (00:05.20–00:07.20) Rooftop tracking. The leader dash vaults, the trailer websters over the gap, then they swap front and back positions. 5. (00:07.20–00:09.20) Overhead moving camera. Both dive roll, then run side by side to speed vault a long railing. 6. (00:09.20–00:11.30) Handheld retreating from the front. One underbars, the other side flips, conquering the obstacle simultaneously. 7. (00:11.30–00:13.20) Drone from diagonal rear above. Both palm spin off left and right walls, kong vault, accelerate into the final jump. 8. (00:13.20–00:15.00) Climax. Both leap a large rooftop gap, each doing a corkscrew, camera circling them in midair as they land on separate rooftop edges — then run side by side into the distance. QUALITY: Live-action film quality. World-championship-level smooth freerunning. Realistic center-of-gravity shifts, muscle movement, natural landing impacts, swaying hair and clothing. Sharp background, natural motion blur only during high-speed movement. PROHIBITED: Facial distortion, altering into different people, face or body swaps, outfit changes, hairstyle changes, body type changes, limb multiplication, duplicates, body fusion, penetration, warping, floating, unnatural landings, anime style, CG style. A few things worth noticing about why it's built this way: The character block does identity work three separate times — the reference images, the "fully maintain" list, and the prohibited list at the end. That redundancy isn't padding; each one closes a different door the model tends to walk through. The prohibited list names the exact failure modes — face swaps, body fusion, limb multiplication. Telling the model what not to do is more effective here than describing what you want, because these are the specific ways two-character scenes collapse. Every cut assigns each person a distinct action — one wall runs left, the other right; one underbars, the other side flips. Giving them separate roles keeps them functionally two people, so the model can't average them into one. And the cuts are individually timed and framed. Long continuous motion is where identity drift creeps in — breaking it into eight discrete shots gives the model less room to blend them. Made in Seedance 2.0.

Nexlow

114,509 次观看 • 2 个月前

Contact sheet prompting is the hottest AI video technique right now 🤯 One image in → 6 consistent frames out → cinematic video ads in minutes. But everyone's doing it manually. I automated the entire workflow in n8n + Airtable. Here's why contact sheet prompting is blowing up: You give AI one reference image, and it generates a grid of consistent shots — same face, same outfit, different angles. Instant storyboarding, full creative control, no photoshoots. The problem? It's super tedious: → Write the prompt manually → Generate the contact sheet → Crop each frame by hand → Feed frames into a video model one by one → Repeat for every product This n8n automation handles all of it: → Upload character image + product image → AI analyzes both and writes the contact sheet prompt → Nano Banana Pro generates a 6-frame grid → System extracts each frame automatically → Kling 2.5 generates smooth transitions between frames → You get 5 video clips ready to stitch Approval checkpoints at every stage, no surprises. What lands in your Airtable: → AI-generated creative prompt → Core hero image (model + product) → 6-frame contact sheet → 5 cinematic video clips → Full control before each generation step Contact sheet prompting on autopilot. I filmed a 20 minute Loom video showing you exactly how I set it up. Want the Loom + the complete n8n workflow + Airtable base? > Comment "SHEET" > Like this post And I'll send it over (must be following so I can DM)

Mike Futia

53,789 次观看 • 9 个月前

Created with Google Gemini Character Sheet Prompt : UNIVERSAL MASTER PROMPT — CINEMATIC PODCAST HOST REFERENCE PERSON → SEATED STUDIO HOST REFERENCE / IDENTITY LOCK: Use the uploaded reference image as the ONLY identity reference for the person. Preserve the person's identity with maximum accuracy: - exact facial identity - face shape and proportions - eyes, eyebrows, nose, lips and jawline - natural skin tone - hairstyle and hairline - age and gender presentation - distinctive facial features - natural body proportions DO NOT beautify, redesign, masculinize, feminize, age, de-age, or alter the person's identity. The person in the final image MUST clearly remain the same individual from the reference image. SUBJECT TRANSFORMATION: Place the reference person as a professional podcast/video host seated directly in front of the camera. The person is sitting behind a dark premium studio desk, facing the camera straight-on in a natural centered position. Upper body and arms are clearly visible. The person is seated comfortably with both forearms resting naturally on the desk and hands positioned together in front of the body. Expression is calm, confident, intelligent, approachable and professional. Natural relaxed posture. Direct eye contact with the camera. OUTFIT: Keep the person's natural appearance and adapt the clothing into a simple premium dark/black casual-professional outfit, such as a plain black crew-neck T-shirt. No logos, no text, no distracting patterns. ENVIRONMENT: Create a premium cinematic podcast studio. Dark black/charcoal exposed brick wall in the background. A large professional black podcast microphone is positioned in the foreground on the LEFT side of the frame, mounted on a black articulated boom arm extending into the shot. The microphone should be close to the host but must NOT cover the face. Behind the host on the RIGHT side: - dark wooden studio shelving/desk - a professional camera - stacked dark books - a warm glowing vintage Edison-style lamp - subtle cyan/teal LED accent lighting underneath the shelf Three dark framed minimalist photographs/artworks are mounted on the background wall. The studio should feel expensive, modern, cinematic and professionally produced. COMPOSITION: 16:9 widescreen composition. Camera positioned directly in front of the seated person at approximately eye level. Medium-wide / medium shot showing: - entire head - shoulders - torso - both arms - hands - substantial portion of the desk Person positioned approximately center-right of the frame, leaving intentional negative space on the LEFT side around the microphone. The microphone boom arm enters from the far LEFT edge and angles naturally toward the host. IMPORTANT SPATIAL LOCK: The host MUST remain directly in front of the camera. The host MUST NOT be positioned sideways. The host MUST NOT be looking away from the camera. The microphone MUST remain on the LEFT side of the image. The camera, boom arm and microphone must NOT switch sides. Do not place any additional microphone, person, chair, doorway, window, gate, or unrelated object in the scene. CAMERA / LENS: Professional full-frame cinema camera. Approximately 50mm lens. Eye-level camera height. Natural perspective. Moderate depth of field. Host's face extremely sharp. Background softly separated but still recognizable. LIGHTING: Premium cinematic studio lighting. Soft warm key light illuminating the person's face from the front-left. Subtle controlled fill light. Warm practical light from the Edison lamp in the background. Very subtle cyan/teal practical accent light underneath the shelf. Deep shadows and controlled contrast. Natural skin highlights. Realistic skin texture. No plastic skin. VISUAL STYLE: Ultra-realistic professional podcast photography. High-end cinematic commercial production. Netflix-style premium color grading. Photorealistic materials and lighting. Natural human anatomy. Realistic hands and fingers. Realistic facial details. Physically accurate shadows and reflections. Subtle natural depth of field. REFERENCE IMAGE PRIORITY: Identity accuracy is the highest priority. The person's face must remain faithful to the uploaded reference. Do not copy the reference background. Only use the person's identity, facial features, hairstyle and natural physical characteristics from the reference. NEGATIVE CONSTRAINTS: No identity drift. No face swapping artifacts. No different person. No altered facial structure. No exaggerated beauty enhancement. No distorted hands. No extra fingers. No missing fingers. No duplicate limbs. No asymmetrical eyes. No deformed face. No cartoon appearance. No CGI appearance. No artificial skin. No excessive sharpening. No text. No logos. No watermark. No additional people. No second microphone. No microphone on the RIGHT. No camera covering the host's face. No sideways pose. No profile view. No looking away. No unnecessary objects. No doorway. No window. No exterior scene. FINAL OUTPUT: Create a single highly realistic cinematic photograph of the exact reference person seated as a professional podcast host in the described studio, looking directly into the camera, with the black microphone and boom arm clearly positioned on the LEFT side of the frame. RESOLUTION LOCK: Generate the final image in 16K resolution — 15360 × 8640 pixels, 16:9 aspect ratio.

M. Asif

15,320 次观看 • 19 天前

john wick seedance text to video prompt: [STYLE / CINEMATIC SETUP] A 10.5-second, 16:9 photorealistic AAA action-game cinematic rendered at real-time speed with no slow motion. The setting is a cramped, cluttered late-night Asian restaurant connected to a rain-soaked street. Cyan-green fluorescent light, red neon and warm practical lamps create a high-contrast mixed-light environment, with reflections across wet floors and pavement. Shoot with a 35mm spherical lens, shallow-to-moderate depth of field and cinematic motion blur appropriate to the actual speed of movement. Use close shoulder-mounted and handheld coverage, connecting seven short close-combat shots with fast hard cuts. The camera instinctively pans, retreats or drops with each block, takedown and collision while keeping the action and contact points readable. No dialogue, no subtitles and no BGM. Generate only synchronized rain, appliance hum, urgent footsteps, fabric movement, body impacts, gunshots, metal contact and breaking glass. [IMAGE REFERENCES] No external still-image reference. Follow the written character and environment descriptions consistently. If the platform supports reference video, use the supplied video only as a reference for editing rhythm, camera distance, action direction and lighting atmosphere, not for copying a specific actor’s identity. The protagonist remains the same lean, agile man in his early forties throughout the sequence: neck-length black hair swept back, a short beard, a tired but focused face, a slightly wrinkled black suit, white shirt and narrow black tie, all carrying faint rain and wear marks. Preserve his face, hairstyle, body proportions, clothing and screen direction across all seven shots. Keep every opponent visually distinct: a man in a blue work uniform, a bald man in a navy jacket, a heavy man in a black jacket, a bald counter attacker, a red-headband attacker, a red-jacketed armed attacker and a heavy man in a dark green coat outside. [TIMELINE SECOND BY SECOND] 0–1.9s: [Shoulder-height medium close-up, tight lateral handheld tracking, real-time speed] The protagonist stands on screen left, pinning the blue-uniformed attacker against a glass refrigerator with his left forearm and palm. He delivers two compact, weighted elbow and palm-heel strikes. Each impact drives the attacker’s head into the refrigerator door, loosening his white headband and leaving a small blood trace on the glass; the attacker finishes sliding down the door while the protagonist remains standing. 1.9–4.3s: [Medium shot transitioning into a high-angle overhead, shoulder-mounted drop, real-time speed] Hard cut near the restaurant’s rear entrance. The bald attacker in a navy jacket locks the protagonist from behind. The protagonist lowers his center of gravity, traps the attacker’s arm and rotates his hips, throwing him heavily over the shoulder onto the wet floor. The camera drops with them into an overhead view. Kneeling across the attacker’s torso, the protagonist draws a compact black pistol and fires one downward shot; recoil travels through his wrist and the attacker jolts once before becoming still. 4.3–5.9s: [Tight medium shot, lateral handheld follow, real-time speed] Hard cut with both men already upright. A heavy attacker in a black jacket swings from screen right. The protagonist slips outside the punch, allowing it to pass close to his face, circles behind the attacker and locks his shoulder and neck off balance. He presses the pistol close to the side of the attacker’s head and fires. The muzzle flash briefly illuminates both faces; the attacker’s head and shoulders snap backward and his body begins to collapse. 5.9–7.9s: [Counter-height medium close-up, subtle handheld push-in, real-time speed] Hard cut to the restaurant counter. Another bald attacker bends forward and clamps around the protagonist’s waist. The protagonist pins the attacker’s head and neck under his left arm while grabbing a short, rigid pointed utensil from the counter. He drives two compact downward thrusts into the upper shoulder and side of the neck. Each contact bends the attacker’s knees further; a restrained amount of blood marks the shirt and counter edge before the attacker hangs helplessly beneath the protagonist’s controlling arm. 7.9–9.0s: [Two-person medium close-up, fast pan with a short retreat, real-time speed] Hard cut as the red-headband attacker rushes into close range. He throws a wide hook from screen right. The protagonist raises his forearm to block, catches the wrist and pulls it outward, then drives a palm heel and forearm into the attacker’s face. The camera retreats with the impact as the attacker loses his balance and staggers toward the rear right of the frame. 9.0–9.9s: [Low-angle wide shot, slight arc around the action, real-time speed] Hard cut to a wider section of the restaurant. The red-jacketed armed attacker advances from screen left. Holding a long black firearm with both hands, the protagonist uses it as a blunt weapon and swings horizontally from right to left. The weapon strikes the attacker’s upper chest and shoulder, rotating his torso, crossing his feet and sending him off balance toward screen left. 9.9–10.5s: [Exterior rainy-street medium shot, fast parallel tracking, real-time speed] Hard cut outside the restaurant. The protagonist already controls a heavy attacker in a dark green coat and uses his forward momentum to drive the man’s head and upper body into the side window of a parked black station wagon. The glass bursts inward at the contact point, scattering both large and fine fragments. The attacker folds through the broken window while the protagonist regains stable footing beside the car, ending with glass fragments still falling. [STYLE & QUALITY BOOSTERS] Maintain the protagonist’s face, black suit, white shirt, tie, hairstyle and body proportions through every hard cut. The pistol, pointed utensil, injuries and blood marks must appear only in their designated shots and must never morph or change ownership. Throws, recoil, strike reactions, loss of balance and window breakage must show believable weight, inertia and precise contact. Apply motion blur only to rapidly moving arms, weapons, glass fragments and camera-relative backgrounds. No sudden face or costume changes; no extra fingers, fused limbs or inverted joints; no morphing weapons, utensils or vehicles; no foot sliding or rubber-like collision reactions; no blood, bullet damage or glass fragments appearing before physical contact.

underwood

24,627 次观看 • 1 个月前