Create a 5-second vertical cinematic fantasy animal video… | Deepfake AI Video

Text-to-video prompt used to generate this video

Create a 5-second vertical cinematic fantasy animal video based directly on the reference image. SUBJECTS: One fluffy white cat with blue eyes, one golden retriever, and one spotted leopard. Preserve the exact appearance, fur patterns, body proportions, relative sizes, and identities of all three animals from the reference image. ENVIRONMENT: A beautiful old European village at golden hour. A narrow cobblestone street runs between ancient stone buildings with warm glowing windows, flower boxes, and ornate street lamps. A magnificent domed cathedral rises in the distance. Golden sunlight and tiny glowing dust particles fill the warm evening air. The white cat sits on the left side of the street. The golden retriever sits on the right. The leopard is positioned between them, facing away from the camera and looking down the street. CAMERA: Maintain the original vertical composition and low, rear three-quarter viewpoint. Keep all three animals visible in the foreground and the village street clearly visible behind them. Use a stationary camera. No panning, zooming, or camera rotation. TIMELINE: 0–1 seconds: The leopard begins walking calmly away from the cat and dog, moving straight down the cobblestone street toward the distant cathedral. Its body and spotted coat remain consistent. Its tail sways gently with each natural step. The cat and dog remain seated, watching the leopard leave. 1–2 seconds: The leopard continues walking away and becomes slightly smaller as it moves farther down the street. The golden retriever slowly turns its head toward the white cat. The cat turns its face toward the dog at almost the same time. 2–3 seconds: The cat and golden retriever briefly look directly at each other, holding eye contact as if silently wondering what they have just witnessed. The dog's ears lift slightly. The cat's ears remain alert. Their expressions convey quiet curiosity and mild confusion. 3–4 seconds: The golden retriever turns its head back toward the street, looking in the direction the leopard went. The white cat follows the dog's gaze and also looks down the street. 4–5 seconds: The leopard continues walking away in the middle distance without looking back. The cat and dog remain seated side by side, quietly watching the leopard disappear farther along the sunlit street. End with both animals looking in the same direction after the departing leopard. VISUAL STYLE: Photorealistic cinematic fantasy animation, realistic fluffy fur, natural animal anatomy, detailed leopard spots, authentic cobblestone textures, weathered medieval stone architecture, warm golden-hour sunlight, glowing windows, delicate floating dust particles, and atmospheric depth. The scene should feel charming, slightly mysterious, and subtly humorous. The humor comes from the cat and dog's brief mutual glance after the leopard casually leaves, as though they are silently asking each other what just happened. AUDIO: Soft evening wind in the narrow street. Gentle paw steps from the leopard as it walks away over the cobblestones. Faint distant village ambience. Subtle natural movement sounds from the cat and dog as they turn their heads. Add a very soft, playful musical accent during the moment when the cat and dog look at each other. No dialogue, narration, or exaggerated cartoon sound effects. The story must remain understandable without audio. CONTINUITY AND CONSTRAINTS: There is exactly one white cat, one golden retriever, and one leopard throughout the entire video. The leopard walks away from the animals and continues in the same direction down the street. The leopard does not turn around, approach the camera, stop abruptly, or change into another animal. The cat and dog remain seated in their original positions throughout the entire sequence. Only their heads, eyes, ears, and subtle facial expressions move. The cat and dog look at each other briefly before both turn to watch the departing leopard. Their head movements are natural and sequential, not exaggerated or perfectly synchronized. The leopard remains visible in the background at the end of the video. The buildings, cathedral, street lamps, and cobblestone street remain consistent and stationary. Golden dust particles drift gently without forming new objects. No additional animals or characters appear. No running, jumping, chasing, fighting, or sudden movements. No duplicated animals, distorted anatomy, background duplication, teleportation, or abrupt scene changes. No cuts. The final frame shows the cat and dog sitting together, looking down the street after the departing leopard.