Prompt 1 : Use the uploaded image reference as the strict final frame and composition reference.

Create a 15-second ultra-realistic cinematic video. Maintain the exact character appearance, outfit, hairstyle, facial features, body proportions, environment, lighting, color grading, and atmosphere from the image reference.

Scene starts with a very wide aerial establishing shot of a large empty dirt field under soft afternoon sunlight. A lone man dressed entirely in black walks slowly toward the center of the field. The camera smoothly descends while slowly pushing forward, creating a feeling of anticipation and isolation.

The man stops in the exact center of the field. Wind gently blows through his hair and clothing. His long shadow stretches across the ground. He calmly raises his head and stares forward without fear.

The camera continues its slow cinematic dolly-in, gradually matching the framing, perspective, focal length, camera height, composition, and distance of the uploaded image reference.

End the video by perfectly recreating the uploaded image reference as the final frame with identical composition. Hold the final shot for 2 seconds. No fighting, no other characters, no camera shake, no dialogue, only ambient wind. Epic cinematic atmosphere with subtle film grain, realistic lighting, anamorphic lens, shallow depth of field, Japanese delinquent movie aesthetic, 8K photorealistic.

Prompt 2 : Use the uploaded image reference as a strict character and composition reference. Preserve the exact face, hairstyle, clothing, open shirt, body proportions, lighting, crowd arrangement, and cinematic Japanese delinquent atmosphere.

10-second ultra-realistic cinematic scene. Medium close-up. The confident young gang leader with his shirt open stands at the front of hundreds of silent gang members wearing matching light gray uniforms. Everyone behind him remains perfectly still, staring coldly toward the unseen opponent.

A gentle breeze moves his open shirt and hair. He slowly tilts his head with a mocking smile, takes one step forward, and confidently challenges his opponent. The camera performs a slow cinematic dolly-in toward his face with subtle handheld movement, shallow depth of field, anamorphic lens, dramatic natural lighting, realistic skin details, tense atmosphere, Japanese live-action action film aesthetic.

He speaks in Japanese with a calm but intimidating tone:

「ふざけてるのか？ 他の仲間はどこだ？」

(Romaji: "Fuzaketeru no ka? Hoka no nakama wa doko da?")

English meaning: "Are you kidding me? Where are the rest of your men?"

After speaking, he smirks confidently while maintaining eye contact with the unseen opponent. The crowd behind him remains completely silent and motionless. No fighting, no cuts, one continuous cinematic shot, 8K photorealistic, high-detail facial animation, natural lip sync.

Prompt 3 : Use the uploaded image reference as a strict character reference. Preserve the exact face, hairstyle, beard, black school uniform, facial proportions, expression details, lighting, environment, and cinematic composition. Keep the same empty dirt field, warm afternoon sunlight, and Japanese delinquent movie atmosphere.

10-second ultra-realistic cinematic scene, one continuous shot.

The camera begins with a medium close-up of the lone man standing calmly in the middle of the empty field. He stares directly into the camera as if facing hundreds of enemies. A gentle wind moves his hair and uniform. His expression is completely calm and fearless.

The camera slowly performs a dramatic push-in until it reaches an extreme close-up of his face. As the camera gets closer, the corners of his mouth slowly curl upward into a disturbing, unsettling smile, similar to the eerie confidence of a Joker-like grin, while keeping his eyes completely cold and unblinking. His smile grows wider naturally without becoming exaggerated or cartoonish.

He speaks slowly in Japanese with absolute confidence:

「ふざけてるのか？ お前ら全員、俺一人で十分だ。」

Romaji: "Fuzaketeru no ka? Omaera zen'in, ore hitori de jūbun da."

English: "Are you kidding me? I'm enough to take on all of you."

After finishing the line, he lets out a faint sinister chuckle while maintaining the terrifying smile and unwavering eye contact. The camera ends on an extreme close-up of his face, emphasizing his cold eyes and unsettling grin. No cuts, no fighting, cinematic slow push-in, subtle handheld movement, anamorphic lens, shallow depth of field, realistic facial animation, perfect Japanese lip sync, photorealistic, 8K, dramatic natural lighting.

Prompt 4 : Use the uploaded image as a strict character reference. Preserve the exact face, hairstyle, skin tone, clothing, necklace, body proportions, background crowd, lighting, composition, and cinematic Japanese live-action style. Keep all background characters standing still.

Create a 10-second cinematic video in one continuous shot.

The camera begins with a medium close-up of the main character. He stands confidently in front of a large group of men wearing matching light gray uniforms. A gentle breeze slightly moves his jacket and hair while everyone behind him remains completely still.

The camera slowly pushes in toward his face. His expression gradually changes into a serious, stern look. He slightly lowers his eyebrows, tightens his jaw, and tilts his head forward while maintaining direct eye contact with the unseen person in front of him.

He speaks clearly in natural Japanese with a firm, commanding tone:

「ふざけるな。今すぐ仲間を呼んでこい。」

Romaji: "Fuzakeru na. Ima sugu nakama o yonde koi."

English: "Don't mess around. Call your men here now."

After speaking, he continues staring forward with a calm but determined expression. The camera finishes on a close-up of his face. No fighting, no sudden movements, no camera shake, no cuts. Cinematic natural lighting, realistic facial animation, accurate Japanese lip sync, shallow depth of field, anamorphic lens, photorealistic, high detail.

Prompt 5 : Use the uploaded image as a strict character reference. Preserve the exact face, hairstyle, beard, black Japanese school uniform, body proportions, posture, lighting, environment, and cinematic composition. Keep the empty field and warm afternoon lighting exactly as shown.

Create a 10-second ultra-realistic cinematic video in one continuous shot.

The character stands alone in the middle of the field with both hands relaxed in his pockets. A gentle breeze moves his hair and uniform slightly. His expression is calm and full of confidence.

The camera begins with a wide shot matching the uploaded reference and slowly performs a smooth cinematic dolly-in toward a medium close-up. As the camera approaches, the character lets out a quiet laugh and smiles with calm confidence while maintaining direct eye contact toward someone off-camera.

He speaks naturally in Japanese with a confident, composed tone:

「ははは……俺一人で十分だ。」

Romaji: "Hahaha... Ore hitori de jūbun da."

English: "Hahaha... I'm enough on my own."

After speaking, he gives a subtle confident smile while remaining completely still. The wind continues to move naturally. No fighting, no running, no sudden movements, no camera shake, no cuts. Cinematic Japanese live-action style, realistic facial animation, accurate Japanese lip sync, anamorphic lens, shallow depth of field, photorealistic, 8K.

Prompt 6 : Use the uploaded image as a strict character and scene reference. Preserve the exact face, hairstyle, clothing, necklace, body proportions, background crowd, lighting, color grading, and cinematic Japanese live-action style. Maintain the same composition and atmosphere.

Create an 8-second ultra-realistic cinematic video in one continuous shot.

The camera begins with a medium close-up of the gang leader standing confidently in front of a large formation of men wearing matching light gray uniforms. Everyone behind him remains perfectly still, watching forward in silence. A gentle breeze subtly moves their jackets and hair.

The camera slowly pushes toward the leader's face. He narrows his eyes, raises his chin slightly, and suddenly shouts in Japanese with a powerful commanding voice:

「行け！」

Romaji: "Ike!"

English: "Go!"

Immediately after his command, the crowd behind him surges forward in a coordinated run past the leader, kicking up dust as they move across the open field. The leader remains standing calmly in the foreground, watching them with a determined expression while the camera holds focus on him before slightly widening to reveal the movement behind him.

Natural daylight, cinematic Japanese action film aesthetic, realistic facial animation, accurate Japanese lip sync, subtle handheld camera, anamorphic lens, shallow depth of field, photorealistic, 8K, one continuous shot, no cuts.