PromptweetPromptweet
Library / Cinematic realistic / Twilight on the River: A Poetic Journey

Twilight on the River: A Poetic Journey

Cinematic realisticShort filmMuse AI

A four-segment cinematic adaptation of the Tang Dynasty poem "Evening by the River," following the progression from sunset to moonlit night across a continuous riverside landscape with coordinated keyframe transitions.

Prompt779 copies
Create a 40-second, 16:9 cinematic ink-wash animation in the style of classical Chinese landscape painting, set on a river in early autumn of the Tang Dynasty. The video consists of four 10-second segments with seamless keyframe continuity—each segment must begin exactly where the previous one ended, maintaining identical composition, lighting, and environmental state, with time flowing continuously forward. Do not reset shots, repeat prior frames, or use jump cuts. Segment 1 (0–10s): "A Single Ray of Sunlight Spreads Across the Water" The setting sun hangs above distant mountains, casting golden-red slanted light across the river surface. Water ripples gently. Camera slowly pushes forward. End frame: sunset approaches the mountain ridge; river surface shows intertwined red and green tones. White serif Chinese subtitles centered at bottom: "一道残阳铺水中。" Gentle female Mandarin voiceover reciting the line; soft guzheng background music. Segment 2 (10–20s): "Half the River Jade-Green, Half the River Crimson" Continuing from Segment 1's end frame. The sun gradually sinks behind the mountain; half the river appears jade-green, the other half fiery red, water tones blending. Camera slowly pans right. End frame: sun completely sets; sky transitions to soft pink-purple twilight. White subtitles: "半江瑟瑟半江红。" Continued gentle voiceover and guzheng accompaniment. Segment 3 (20–30s): "How Pitiful the Third Night of September" Continuing from Segment 2's end frame. Twilight gradually fades; sky deepens to blue-purple. A thin crescent moon appears above distant mountains. Camera tilts slightly upward. End frame: blue-purple night sky, curved moon, deep teal river surface. White subtitles: "可怜九月初三夜。" Continued voiceover and guzheng. Segment 4 (30–40s): "Dew Like Pearls, Moon Like a Bow" Continuing from Segment 3's end frame. Camera slowly moves closer to the right riverbank's grassy edge. Crystalline dewdrops shimmer like pearls in the foreground. The crescent moon glows like a bow in the distance; the river surface remains tranquil. End frame: foreground dewdrops, middle-ground river water, background crescent moon; camera becomes static. White subtitles: "露似真珠月似弓。" Final voiceover and guzheng fade gently. Unified requirements: 16:9 landscape orientation; 4 segments of 10 seconds each; cinema-grade ink-wash animation in Tang Dynasty setting; same riverbank, distant mountains, reeds throughout; smooth, steady camera movement; white serif simplified Chinese subtitles (centered, lower third); gentle female Mandarin recitation of each poem line; delicate guzheng background music; video size under 20 MB. Absolutely prohibit: camera resets, image repetition, abrupt cuts, human characters, modern objects, or unrelated text. All four segments must form a natural visual continuum with accurate subtitles and clear voiceover.
Includes a consistency lock: a trait the prompt asks the model to hold constant.
How to use this prompt
  1. 1
    Copy the prompt

    Use the copy button above to grab the text exactly as written.

  2. 2
    Paste it into Muse AI

    Drop it in unchanged since the camera, lighting and duration are already specified.

  3. 3
    Swap the subject, keep the structure

    Change only the subject or setting for the most predictable result; the same wording carries over to other models too.

Aspect ratio
16:9
Camera
tracking · push-in · pan · tilt · static/fixed
Lighting
golden hour · warm tone · blue hour · cool tone · cinematic · volumetric
Mood
poetic · serene · melancholic
Duration
40s
Difficulty
Advanced
Model
Muse AI
Includes
Subject lock

More from Muse AI

What makes this prompt work

Every claim below is measured against the 627 prompts in this library, not asserted.

Camera

‘tracking’ is used by 368 prompts in the library, rank #2 of the camera terms seen here.

Lighting

‘golden hour’ appears in 238 prompts library-wide, rank #3.

Aspect ratio

16:9 is used by 472 of the 627 prompts in the library. Naming it at all matters more than which one is picked.

Consistency

This prompt declares a consistency lock, which is what keeps a subject recognisable across a clip.

Model

Muse AI accounts for 5.6% of the library (35 of 627 prompts).

Difficulty

Marked advanced, based on how many specs it stacks (camera, lighting, duration, lock) at once.