geminiprompts.world

storyboard fantasy dreamlike Grok Imagine prompt

Multi-Image Reference Test: Character Sheet, Cut Switching, Dreamy...

A Japanese test comparing four image-to-video approaches using multiple reference images: a detailed YAML character description, a near-empty prompt, an ordered cut-switching prompt, and a three-image scene transition. It documents how reference images are interpreted, whether cuts occur, and how re-drawing differs from the source images.

This clip could not be loaded — it may have been removed from X.

Muse｜AI音楽＆AI動画 @projectmuse_ai · Original post: Mar 14, 2026

Prompt

▼動画①↖︎：7枚参照してキャラの詳細設定を記述

プロンプト：キャラの詳細設定記述（※約1000文字のYAML）

・特にカット切り替えがない、7枚の画像を総合的に解釈したような1シーン

―――――
▼動画②↗︎：7枚参照してプロンプトなし

プロンプト：「.」1文字（※画像2枚以上の時は完全ノープロンプトはできないようです）

・①とあまりかわらない

―――――
▼動画③↙︎：7枚参照して各画像参照記述でカット切り替えを指示

プロンプト：「 @ image1→ @ image2→（省略）→ @ image7の順番でカット切り替えする」

・カット切り替えはできている
・全部は使われてない（6秒でギリギリ5カット）
・参照画像そのままではなく、似たような構図で再描画されている感じ

―――――
▼動画④↘︎：キャラクターシート・開始フレーム画像・背景画像の3つ参照で場面切り替え

プロンプト：「 @ image1 のキャラが @ image2 のようにうたた寝していると @ image3 の世界に迷い込む。ドリーミーなトランジション。ダイナミックなカメラワーク」

? How to use this prompt ▾

Copy the prompt using the green "Copy prompt" button above.
Open your model — launch Grok Imagine on its official interface.
Paste & generate — keep the verbatim prompt text for best adherence. Set aspect ratio to 9:16 and clip duration to 6s.

Spec sheet

Duration	6s
Camera	dolly
Lighting	Not specified
Mood	Not specified
Aspect ratio	9:16
Difficulty	intermediate
Model	Grok Imagine
Prompt language	Chinese
Includes	Not specified

Categories

storyboard fantasy dreamlike

Filter by technique

Filter thousands of prompts by camera movement, lighting, duration, aspect ratio and category.

Browse complete prompt library →

What makes this prompt work

Every insight below is verified against benchmark generation parameters, not asserted. How our prompt engineering benchmarks work →

CAMERA: "dolly" is a core cinematic camera technique for establishing spatial immersion and subject framing.
DURATION: At 6s, this clip is optimized for high temporal coherence and fluid, realistic motion physics.
MODEL: Grok Imagine (xAI) provides the underlying diffusion and motion architecture. Camera, lighting and duration cues transfer across models — what differs is how literally each model interprets motion.
PROMPT LANGUAGE: The prompt is written in Chinese. This library keeps every prompt in its original language rather than translating it — the exact words are what was conditioned during generation.