Process
Generation data
COPY ALL
Resources used
Prompt
External Generator
How the reference pictures align with the target video — Picture 1 (from Shot 1) aligns with the 0.00-second mark of the target video; Picture 2 (from Shot 1) aligns with the 8.00-second mark of the target video.
integrated_multimodal_description: [Shot 1] 3D CG, cinematic commercial look, a medium close-up begins in the exact pose, framing, lighting, and rose-gold voxel-head appearance established by Picture 1: a human head and neck built from dense metallic cubes over a pale pinstripe collared shirt against pure black, with a few cubes already lifted near the crown and cheeks. The camera performs an Arc Shot with medium amplitude at slow speed around the subject from the opening front three-quarter toward the opposite side. As it orbits, facial cubes peel outward in a progressive particle breakup from the forehead, temples, nose bridge, and jaw, floating and tumbling with shallow-depth bokeh while the remaining grid keeps the face readable. Near the end, the breakup densifies into a wider suspended cube cloud, the head orientation and camera angle settle, and the composition lands on the final dispersed facial-particle state, spacing, and framing established by Picture 2.
overall_soundscape: Soft high-frequency crystalline clicks as metal cubes separate and collide lightly in air. A low studio-room hush continues underneath with faint air movement around the drifting particles.
non_diegetic_music: Sparse low electronic pulse at a slow tempo, joined by thin metallic synth tones that gradually increase in volume through the orbit, then settle into a short sustained note at the end.
Negative prompt
The raw video download includes the complete WF.
Other metadata
cfgScale:1
steps:8
sampler:Euler
Discussion



