Skip to main content
Prompts Cinematic Model Train Assembly Video Script

model image_generation template risk: low

Cinematic Model Train Assembly Video Script

Describes a timed three-shot sequence featuring Komar, an 18-year-old Indonesian teen: extreme close-up of his focused face, macro shot of his hands assembling a miniature train lo…

PROMPT 

[00:00 - 00:02]
[Extreme close-up] of Komar's face, an 18-year-old Indonesian teenage boy, short hair, wearing black-framed glasses with minus lenses reflecting the light of a desk lamp. A very meticulous and focused expression. Warm lighting from a desk lamp, ${cinematic_bokeh}, ${volumetric_lighting}, [8k resolution], [ultra-realistic skin texture].

[00:02 - 00:04]
${macro_shot} of the hands of Komar, an 18-year-old Indonesian teenage boy, wearing a dark blue short-sleeved t-shirt, assembling a miniature Indonesian train locomotive using tweezers. Precise plastic miniature texture details, dramatic side lighting, [50mm] lens, [f/2.8], ${professional_studio_lighting}, intricate mechanical details.

[00:04 - 00:06]
${medium_shot} Komar, an 18-year-old Indonesian man with short hair, wearing black-framed glasses with minus lenses, wearing a plain navy blue short-sleeved t-shirt with a regular fit. Sitting at a wooden workbench filled with model kit equipment. Warm atmosphere, ${dust_motes} visible in light beams, ${cinematic_color_grading}, ${soft_shadows}.

INPUTS

cinematic_bokeh REQUIRED

Cinematic bokeh effect style

e.g. cinematic bokeh

volumetric_lighting REQUIRED

Volumetric lighting effect

e.g. volumetric lighting

macro_shot REQUIRED

Macro shot camera style

e.g. macro shot

professional_studio_lighting REQUIRED

Professional studio lighting setup

e.g. professional studio lighting

dust_motes REQUIRED

Dust motes visible in light beams effect

e.g. dust motes

cinematic_color_grading REQUIRED

Cinematic color grading style

e.g. cinematic color grading

soft_shadows REQUIRED

Soft shadows lighting effect

e.g. soft shadows

EXPECTED OUTPUT

Format
plain_text

CAVEATS

Missing context
  • Target AI video/image generation tool or model.
  • Framerate, total duration, or output format (e.g., MP4, sequence of images).
  • Definition or common expansions for stylistic placeholders.
Ambiguities
  • Inconsistent age descriptor: 'teenage boy' in first two scenes, 'Indonesian man' in third.
  • Unclear expansion of placeholders like '${cinematic_bokeh}', '${macro_shot}'.

QUALITY

OVERALL
0.70
CLARITY
0.85
SPECIFICITY
0.90
REUSABILITY
0.30
COMPLETENESS
0.80

IMPROVEMENT SUGGESTIONS

  • Introduce placeholders like {character_name}, {object_type}, {clothing} to make it templated and reusable.
  • Standardize descriptors (e.g., '18-year-old Indonesian boy' throughout) for consistency.
  • Add transitions between scenes and overall video specs (e.g., 8K, 30fps).
  • Group common styles (e.g., lighting, resolution) at the top to reduce repetition.

USAGE

Copy the prompt above and paste it into your AI of choice — Claude, ChatGPT, Gemini, or anywhere else you're working. Replace any placeholder sections with your own context, then ask for the output.

MORE FOR MODEL