Create a 5-second vertical cinematic, photorealistic… | Deepfake AI视频

生成此视频所用的文字转视频提示词

Create a 5-second vertical cinematic, photorealistic emotional video based directly on the provided reference image. SUBJECT: A fluffy white cat and a golden retriever together on an old stone bridge at a Japanese lantern festival at night. Preserve the exact appearance, fur colors, body proportions, relative size, positions, and identities of both animals from the reference image. SCENE: A peaceful Japanese canal at night, illuminated by hundreds of floating red, orange, and warm white lanterns. Traditional festival stalls line both banks, with distant people and warm lights beneath willow trees. The dark blue evening sky and the lantern reflections create a quiet, contemplative atmosphere. The white cat is sitting on the stone bridge, facing the river. The golden retriever stands beside the cat, also gazing at the flowing lanterns. CAMERA: Preserve the exact elevated rear three-quarter composition of the reference image. Keep both animals in the foreground and the long lantern-lit canal stretching into the distance. Use a nearly locked-off camera. No panning, no orbiting, no zooming, and no camera shake. Maintain a stable composition for the entire five seconds. TIMELINE: 0–1 seconds: The white cat and golden retriever quietly watch the lanterns floating along the canal. The cat remains seated, and the dog stands calmly beside it. The lanterns drift slowly with the gentle current. 1–3 seconds: Continue the same peaceful composition. The lanterns move gradually downstream at a slow, steady pace. Their warm reflections shimmer softly on the water. A gentle night breeze barely stirs the dog's fur and the cat's tail. 3–5 seconds: The two animals continue quietly watching the river together. The dog makes one very subtle adjustment of its head, following the distant lanterns. The cat remains peacefully seated. The lanterns continue their slow journey into the distance, and their reflections shimmer gently across the dark water. End on the same quiet, contemplative scene. Nothing dramatic happens. VISUAL STYLE: Photorealistic cinematic animal animation, realistic fluffy fur, natural and subtle animal movement, detailed old stonework, warm paper lanterns, dark blue night sky, soft reflections on gently flowing water, distant festival lights, delicate atmospheric haze, and natural depth of field. Emphasize emotional warmth, quiet companionship, nostalgia, and peaceful contemplation. Use restrained motion and natural lighting. Avoid exaggerated cinematic effects or artificial-looking movement. AUDIO: A gentle night breeze. Soft, continuous flowing-water ambience. Very faint, distant festival chatter and indistinct crowd ambience. Occasional subtle sounds of water lapping against the stone embankment. A quiet, slow, emotionally warm instrumental melody with soft piano and delicate sustained strings. The music should feel tender and reflective, never sad or melodramatic. Let the natural ambience remain audible beneath the music. No dialogue. No narration. No exaggerated sound effects. CONTINUITY AND CONSTRAINTS: The white cat remains seated in its original position throughout the video. The golden retriever remains standing beside the cat in its original position. Both animals continue looking toward the lantern-lit river. Only natural breathing, very subtle head movement, and slight movement of fur are allowed. The camera remains almost perfectly stationary. The lanterns drift slowly and continuously downstream. Water movement remains gentle, smooth, and physically natural. Lantern reflections shimmer subtly without large waves or sudden distortions. The festival stalls, willow trees, stone bridge, distant buildings, and surrounding environment remain stable and consistent with the reference image. No fish, jumping animals, splashes, sudden ripples, or new events. No sudden lighting changes, moving buildings, duplicated backgrounds, or dramatic camera movements. No cuts, teleportation, morphing, or scene changes. The entire video should feel like a single quiet moment shared by the two animals. The emotional atmosphere and visual beauty are more important than action.