name: jimeng-prompt-text2video description: "Provides comprehensive guidance for crafting text-to-video prompts for 即夢 (Dreamina/Jimeng) video models (影片3.0 Pro, Doubao Seedance 2.0, Seedance 1.5/1.0, 智慧多幀). Video prompts require two additional dimensions beyond image prompts: explicit motion description and camera movement direction. Use when the user wants to write, refine, or optimize a video generation prompt; mentions 文生影片, text2video, 影片提示詞, 運鏡, camera movement, 生成一段...的影片, 幫我寫個影片; describes a scene they want as a video; or provides a rough scene description to be turned into a polished video prompt. This skill covers 12 video scenario categories with 35 annotated examples, a motion and camera word library, and a complete camera movement reference covering 7 basic plus 6 advanced compound techniques with emotional effect mappings. Always use this skill when the user needs help writing any video generation prompt for 即夢." license: Complete terms in LICENSE.txt

jimeng-prompt-text2video — 即夢文生影片提示詞

Craft production-ready text-to-video prompts for 即夢 Dreamina video models (影片3.0 Pro, Doubao Seedance 2.0, Seedance 1.5, Seedance 1.0, 智慧多幀).

When to use this skill

Use this skill when the user: - Asks you to write a video generation prompt ("幫我寫個影片提示詞") - Describes a scene they want as a moving image / video - Wants to refine or optimize an existing video prompt - Mentions keywords like: 文生影片, text2video, 影片生成, 影片提示詞, 運鏡, camera movement, Seedance - Asks about how to describe motion, camera work, or temporal progression in a prompt

Do NOT use this skill for: - Executing CLI commands to generate videos → use jimeng-cli-text2video - Writing image-to-video prompts → use jimeng-prompt-image2video - Writing text-to-image prompts → use jimeng-prompt-text2image

Model Version Guide

即夢 has multiple video model lines. The core writing approach differs by model:

Core Methodology

The video prompt formula extends the image formula with two critical dimensions: motion and camera.

For 影片3.0/3.0 Pro 文生影片:

主體 + 動作 + 場景 + 鏡頭 + 風格 + (情緒演繹) + (照明)

For 圖生影片 (image-to-video):

動作 + 鏡頭 + (情緒/照明)

For Doubao Seedance 2.0 系列 文生影片:

主體 + 動作/運動 + 空間背景/光影/風格 + 鏡頭排程/音效

The key difference from text-to-image prompting: - Motion is mandatory: a video without motion is just a still image - Camera adds storytelling: how the camera moves determines the viewer's emotional experience - Duration shapes pacing: a 5-second clip needs different action density than a 10-second clip - For 影片3.0 Pro specifically: 自然語言自由書寫, 核心思路是"直觀表達出你想要的效果" - For Doubao Seedance 2.0: 支援多模態參考(圖片/音訊/影片), 可在提示詞中用"圖片1""圖片2"指代參考素材

How to use this skill

Step 1: Identify video scenario category

→ Load rules/video-category-table.md to match user's request to the right category and example file

Step 2: Load reference materials

Load video vocabulary — choose by what you need:

Load camera movement references — choose by complexity:

Load reference guides: - references/jimeng-video-3.0-guide.md — when user mentions 影片3.0/3.0 Pro - references/smart-multi-frame-guide.md — when user mentions 智慧多幀/多幀/一鏡到底

For color descriptions, cross-reference text2image's color-library/chinese-traditional.md or gugong-384-colors.md.

Step 3: Build the prompt

7w4.net收錄了海量優質技能外掛。

→ Load rules/video-core-methodology.md for component-by-component build guide + presentation format

Step 4: Apply video writing rules

→ Load rules/video-writing-rules.md for all 10 rules (motion, camera, duration, light, model-matching, differentiation, action layers)

Step 5: Validate

→ Load rules/video-validation-checklist.md and run through all checks

Step 6 (User assessment): Evaluate prompt output

When the user provides an existing prompt output and asks for evaluation ("評估""檢測命中率""看看最佳化方向"): → Load references/evaluation-framework.md for the systematic 6-dimension assessment methodology

Gotchas

1. Action must be explicit — 即夢 cannot infer motion from static description. "一個人在街上" = static shot
2. Complex interactions fail — multi-person interactions + camera movement = distortion risk
3. Chinese camera terms work better — "鏡頭緩緩推近" > "dolly in slowly"
4. Seedance quality/speed tradeoff — seedance2.0 = highest quality/slowest; fast = faster/lower quality
5. Duration-to-action matching — 5s with 3-stage action = rushed. Match complexity to time
6. First-time web authorization — some models require browser auth before first use
7. Character consistency not guaranteed — same face across segments not reliable
8. Camera + complex motion = risk — prioritize one over the other
9. Model-prompt mismatch is the #1 output killer (Rule 8) — long descriptive prose → 影片3.0 Pro; structured short sentences → Seedance 2.0. Mismatching causes detail loss and poor generation. This is the single most common error in real usage.
10. Action layer count by model (Rule 10) — Seedance 2.0 can't handle 4+ action layers reliably. Cap at 3. 影片3.0 Pro can handle 4-5.
11. Multi-scheme differentiation is non-optional (Rule 9) — When providing 2+ alternatives, verify visual distinction. At least 2 dimensions must differ (運鏡/動作密度/景別/節奏/場景). Similar schemes waste user's time.
12. Light must change, not just exist (Rule 5) — "灑入" is a static snapshot. Use "緩緩流動""逐漸變亮""光影移動" to encode time passage.
13. ⚠️ Never write hex color codes in video prompts — Same as image prompts: #RRGGBB values get rendered as text in the video frames, NOT as color instructions. Use Chinese color names only

Available Resources

這個提示詞技能質量很好，體系完整、規則清晰、詞庫豐富。它抓住了影片生成的核心要點——motion必須明確寫出來、運鏡要匹配情感、不同模型需要不同寫法——這些正是新手容易踩坑的地方。配套的評估框架能幫你檢查自己寫的提示詞好不好用。唯一的小遺憾是示例數量還有提升空間，部分高階技巧的講解可以更詳細。總體來說，這是一個值得信賴的專業工具。