Optimizer

Make the prompt do the work

Veo, Seedance, Kling, Sora — anywhere a shot has to be described before it can be rendered.

Your current prompt

**Overall Concept and Narrative**
A single continuous talking-head shot of the founder addressing {{topic}} directly to camera, structured as one clear argument: name the objection, concede what is true about it, then state the actual answer. The emotional beat is candor - this reads as a person leveling with the viewer, not a rehearsed pitch. No scale device; the entire film is one person, one frame.

**Key Scenes and Transitions**
Single shot, no transitions or cuts. Start frame is a medium close-up on the founder, already mid-thought rather than starting cold. Movement within the shot is limited to natural hand gesture and a slight forward lean at the moment the actual answer is delivered. End framing holds on the founder's face for one full second of silence after the last line, no fade.

**Visual Style and Aesthetics**
Documentary-adjacent aesthetic in the register of an Errol Morris interview setup - direct, unadorned, credible. Primary light source is a single large soft key at a 30-degree angle, 4300K, with a low-ratio fill so shadow depth stays gentle and the face reads as approachable rather than dramatic. No haze. Grade is a clean, neutral corrective pass with slightly lifted shadows - no cinematic teal-and-orange treatment, which would undercut the sincerity.

**Motion and Dynamics**
Camera is locked off on a tripod for the entire shot - no push, no handheld drift. The founder's gestures are unforced and occur naturally around emphasis points, never choreographed. What is explicitly NOT moving: the framing and the background, so the only variable the viewer tracks is the founder's face and hands. Tension curve builds gently through the concession, then resolves cleanly on the stated answer.

**Audio and Timing**
Duration is 45 to 60 seconds, 30fps. Dialogue is the founder speaking live and unscripted-sounding, recorded with a lavalier mic, not a scripted voiceover laid over b-roll. Three cues: clean room tone with no added ambience, no music bed under the dialogue at all, and a single soft tone under the final held second of silence to mark the end for platforms that auto-caption.

**Technical Details**
1080x1920 vertical for {{platform}} unless the platform is explicitly landscape, 30fps, shallow depth of field (background softly out of focus at roughly f/2.8 equivalent) to keep attention on the face. No bloom, no particles, no HDR.

**Negative Prompts**
scripted-sounding delivery, cutaway b-roll interrupting the shot, dramatic music underscore, hard three-point studio lighting, handheld camera shake, fast jump cuts, low-resolution or soft focus on the face, forced enthusiastic smiling, teleprompter eye movement, background distractions or motion, jitter, audio clipping

Template · 2 variables

2 of 2 still blank. Anything left blank is sent to the model as {{placeholder}}.

Describe your ideal output (optional)

ModeModel

7 blocks · 3 clarifying questions · Auto rotates through the models your plan unlocks, switching every two runs per mode.

⌘ + Enter

Video frame

What you will get back

01Overall Concept and Narrative
One paragraph: the emotional beat, the scale or contrast that carries it, and a summary of the camera arc. A single shot if the prompt says so, otherwise a three-scene arc.
02Key Scenes and Transitions
Start frame → movement → end framing. Multi-scene reads "Scene 1 … Transition: <named move> into Scene 2 …".
03Visual Style and Aesthetics
Genre language, the primary light source and its color temperature, shadow depth, atmosphere (fog, dust, haze), the grade (teal-versus-red and the like), and named references.
04Motion and Dynamics
Camera verb plus pace, the subject's gait, what is explicitly NOT moving, and the tension curve across the duration.
05Audio and Timing
Duration, fps (24 or 30 for cinematic, 60 for slow motion), dialogue yes or no, and three concrete ambient or score cues.
06Technical Details
Resolution, aspect ratio, texture targets, light bloom / volumetrics / particles, HDR. Every concrete item from the ideal-output description reappears here.
07Negative Prompts
A comma-separated list of roughly 10–12: wrong time of day, crowds, wrong color, handheld or shaky, fast cuts, low resolution, wrong mood (smiling), jitter, artifacts.

Plus 3 clarifying questions you can answer to re-run with more facts.