プロンプト

A handheld smartphone POV video lasting 15 seconds, ultra-realistic and completely real-world, dim warm indoor lighting with natural shadows, slight motion blur, low-light grain, imperfect framing, fingers partially visible on frame edges. 0–5 seconds: from the Chihuahua’s thought perspective, the camera shows a real smartphone held close, playing a real video on the screen of a Chihuahua wearing a Superman costume while other real dogs like a Rottweiler and a Pitbull are calmly sitting and looking impressed, reflections visible on the phone glass, everything looking like an actual recorded clip. 6 seconds: the camera slowly zooms in on the real Chihuahua’s face, as if it is imagining itself as powerful, natural breathing and fur texture visible. 8 seconds: cut to the real Chihuahua now wearing a small Superman costume, confidently walking and standing in front of a real Rottweiler in the same dim room, expecting admiration. 10–11 seconds: the Rottweiler stares at the Chihuahua for one second, then gives a slow side-eye look directly at the camera. 12–15 seconds: the Rottweiler calmly stands up and walks past the Chihuahua without reacting, ignoring it completely, while the Chihuahua freezes, then barks in a funny, dramatic, high-pitched way out of frustration, playful and humorous vibe, real fur movement, real reactions, no aggression, no CGI, no cinematic effects, fully realistic environment and animals.

生成結果

A handheld smartphone POV video lasting 15 seconds, ultra-realistic and completely real-world, dim warm indoor lighti...

設定