Generation Modes

Designed for music videos centered on a performer or vocalist. The pipeline plans scenes around stage presence, vocal delivery, and audience engagement. When speech alignment is available, this mode injects lip-sync cues into video prompts so the generated performer appears to sing along.

Best for: music videos, live performance visuals, artist content

Plans a narrative arc with characters, settings, conflict, and resolution across scenes. The treatment builds dramatic progression that follows the music's emotional curve — building tension in verses, peaking at choruses, and resolving in the outro.

Best for: narrative music videos, short stories, emotional pieces

Optimized for commercial and branded content. Scenes are planned around product shots, brand identity, call-to-action framing, and commercial pacing. Reference images are especially valuable here for maintaining product consistency.

Best for: product launches, brand videos, commercial spots

Applied anime visual conventions throughout: dynamic poses, expressive character reactions, stylized environments, speed lines, dramatic lighting, and characteristic anime cinematography.

Best for: anime-style music videos, animation, fan content

Plans cinematic compositions with atmospheric lighting, deliberate pacing, minimal dialogue, and visual storytelling. Prioritizes mood, composition, and cinematic language over narrative exposition.

Best for: art films, mood pieces, cinematic experiments

Plans observational scenes with natural lighting, diverse locations, informational composition, and a documentary visual language. Emphasizes realism, environmental context, and authentic human moments.

Best for: documentary-style videos, factual content, social media