Cinematic prompts
Generate a sequence of shots featuring the same character. **Step 1: write the character lock.** This exact text goes into every shot prompt, word for word, before anything else. Never paraphrase it. CHARACTER LOCK: "[NAME], a [AGE] year old [DESCRIPTION: build, height impression], with [HAIR: exact length, color, texture, and how it is
Multi-Shot Character Consistency
Keep one character looking like the same person across separately generated shots using a locked description block and fixed style spine.
[SHOT TYPE: slow dolly-in / handheld tracking shot / static wide shot] of [SUBJECT + ACTION: a lighthouse keeper climbing a spiral staircase, lantern in hand]. Setting: [LOCATION + TIME: inside a stone lighthouse at dusk, warm lantern light against cold blue dusk light through slit windows]. Camera: [MOVEMENT + LENS: dolly rises with hi
Veo Cinematic Shot
A Veo prompt structure for cinematic shots: subject and action, camera movement, lighting, and native audio direction in one pass.
Build the video for a song in three locked blocks + a shot list. Video models have no memory between clips: consistency comes entirely from repeating these blocks verbatim. CHARACTER BIBLE (write once, paste word-for-word into EVERY shot prompt: any paraphrase causes drift): [40-60 WORDS, EXHAUSTIVE: "A woman in her late 20s with waist-l
AI Music Video
The full music video workflow: a frozen character bible, shots mapped to song sections, and a style spine that makes clips cut together.
Build a trailer for an ORIGINAL film concept as 5 separate generations, cut together in editing. (Original characters and worlds only: trailers imitating real franchises or real actors get channels struck.) THE FILM: [TITLE + LOGLINE + GENRE, e.g. "'SALT LINE': a lighthouse keeper discovers the tide has stopped obeying the moon. Slow-bur
AI Movie Trailer
A five-generation trailer structure for a film that doesn't exist (establisher, character, conflict, montage, title card) with the cinematography language that sells it.
Generate a b-roll pack that cuts together like one shoot. The discipline: ONE master look block, repeated verbatim in every clip; only the subject line changes. What the b-roll supports: [THE A-ROLL/PROJECT: "a talking-head video about remote work" / "my SaaS launch video" / "a coffee brand's social content"] The cutaway moments I need t
B-Roll Pack
Generate a matching set of b-roll clips from one master prompt: locked grade and lens, loop-friendly motion, cut-in ready for any edit.
An anime scene: [THE MOMENT: "a girl waits at a rural train crossing as the evening train thunders past" / "two rivals face off on a school rooftop, wind lifting their jackets"]. The 2D lock (without these, models render smooth 3D motion wearing an anime costume): Hand-drawn 2D cel animation, flat cel shading with hard shadow edges, bold
2D Anime Scene
Prompt video models for real anime feel: cel shading, limited animation on twos, painted static backgrounds, and motion in discrete beats.