标签「tutorial」的 AI 提示词

标签「tutorial」的 AI 提示词

1. Virtual Outfit Design Workflow

   

   OUTFIT CHOICES → LOW BUN → PERFUME → COMPLETE LOOK → FINAL TURN 10 shots, 20 seconds. REFERENCES @image1 = character sheet. The large left portrait controls facial geometry, features, skin texture and identity. The right full-body panel controls proportions and the starting black satin camisole an

   SEEDANCE2.5 · video

2. Thirteen Panels, One Face: A 17-Second Storyboard Lock

   

   Create a 17-second ultra-realistic cinematic vertical video featuring the woman from the provided character reference. Use the newly provided female character reference as the ONLY identity reference for the main character. Do NOT use the face or identity of the woman visible in the storyboard. Us

   SEEDANCE2.5 · video

3. Studio Actor And Brand Swap

   

   【任务：参考视频逐镜复刻，仅替换指定人物与品牌场景】 使用@视频1 {{Mixed 4}} 作为唯一的动作、表演、人物互动、摄影机运动、镜头构图、剪辑节奏和时间顺序参考。 将原视频中的男性角色完整替换为@图片1 {{Mixed 1}} 中的男性人物，将原视频中的女性角色完整替换为@图片2 {{Mixed 2}} 中的女性人物。将原视频的粉红色摄影棚背景和地面改为@图片3 {{Mixed 3}} 标志中的币安黄色，并在背景中设置清晰、准确的@图片3 {{Mixed 3}} 币安标志。 这是参考视频驱动的人物与场景替换，不是重新编排剧情，不是重新设计舞蹈，不是根据歌曲自由发挥。 最终视频时

   SEEDANCE2.5 · video

4. A Character Builder in One Chat: Magnific Meets Opus 5.5

   

   Stylized 3D art-toy character animation, Pixar-level render, 20 seconds, 16:9. The girl from the reference images (short wavy chestnut bob, brown cap with pins, freckles, rosy cheeks, dark brown oversized hoodie, olive cargo trousers, chunky trainers) on a seamless off-white studio backdrop, soft di

   SEEDANCE2.5 · video

5. Single Image To 30 Second Video

   

   Create a 30-second photorealistic cinematic action sequence beginning exactly from the supplied image. Use the supplied image as the exact identity anchor for the main vehicle and world. Preserve the futuristic race machine with white, orange and green livery, number 09, glowing circular rear propu

   SEEDANCE2.5 · video

6. The Frame-Break Effect: Popping Out of the Black Bars

   

   Use @[char ref]as the exact character and style reference. Preserve her white hair, red eyes, oversized black cropped top, long cream skirt with orange lining, bare feet and single slender sword. Keep the same angular painterly anime rendering. MAIN VISUAL GOAL: an unmistakable OUT-OF-FRAME, POP-O

   SEEDANCE2.5 · video

7. Realistic AI Video Workflow

   

   === REFERENCES === <<<image_2>>> is the exact START FRAME and master reference for the scene, car, location, framing, light and film grade. Frame one must match it pixel for pixel: camera inside a parked white sedan looking out through the open front passenger door, grey fabric headliner along the

   SEEDANCE2.5 · video