Craft prompts for animating reference images into videos using Dreamina's 4 video modes.
When to use this skill
Use this skill when the user:
- Provides image(s) and wants to generate a video from them ("把这张图做成视频")
- Mentions 图生视频, image2video, 图片转视频, 让图动起来
- Describes a specific sub-mode: 单图生视频, 首尾帧, 多帧故事, 全能参考
- Has multiple images and wants to create a narrative video
- Asks how to describe motion from a static reference image
Do NOT use for:
- Text-to-video (no reference images) → use jimeng-prompt-text2video
- CLI execution → use jimeng-cli-image2video
- Image-to-image editing (output is still an image) → use jimeng-prompt-image2image
Core Methodology
Image-to-video prompting is fundamentally incremental: the reference image already provides the visual content. The prompt only needs to describe what MOVES and CHANGES.
[从哪里开始] + [什么在动/怎么动] + [运镜方式] + [环境/光影变化] + [时长/节奏] + [风格一致]
The I2V Golden Rule
Don't describe what's already in the image. Only describe what happens next.
- ✗ "A girl in a red dress stands in a garden, the sunlight is bright..." — the image already shows this
- ✓ "The girl slowly turns to face the camera, the red dress flutters in the wind, the camera slowly pushes in" — this is what happens NEXT
4 Sub-Modes Overview
| # | Mode | Input | Core Prompt Focus | Example File |
|---|---|---|---|---|
| 1 | 单图生视频 | 1 image | "Starting from this image, what movement happens next" | examples/single-image.md |
| 2 | 首尾帧 | 2 images | "How to transition from image A to image B" | examples/first-last-frame.md |
| 3 | 多帧故事 | 2-20 images | "The causal relationship and passage of time between frames" | examples/multi-frame.md |
| 4 | 全能参考 | images+video+audio | "Synthesize all reference materials to generate the target video" | examples/multimodal-ref.md |
How to use this skill
Step 1: Identify the sub-mode
Ask the user or infer from context:
- Has 1 image → Sub-mode 1 (单图生视频)
- Has 2 images described as start/end → Sub-mode 2 (首尾帧)
- Has 2+ images forming a sequence/storyboard → Sub-mode 3 (多帧故事)
- Has mixed media (images + video + audio) → Sub-mode 4 (全能参考)
Step 2: Load reference materials
Load the matched example file from examples/ for sub-mode-specific patterns.
Load references/mode-library.md for detailed templates per sub-mode.
Load references/word-library.md for I2V-specific motion and coordination vocabulary.
For camera movement vocabulary, cross-reference the text2video skill's camera-library.md — it covers 7 basic + 6 advanced camera movements with emotional mappings, not duplicated here.
Step 3: Build the prompt (incremental description)
For sub-mode 1 (单图生视频):
- Starting point (从哪里开始): Acknowledge the reference image — "从这张画面开始"
- What moves (什么在动): The MOST important component. Be specific about WHICH elements move and HOW. "头发在微风中飘动，水面的波纹缓缓扩散" — describe only what changes
- What stays still (什么不动): Explicitly state static elements — "建筑和远山保持完全静止"
- Camera movement (运镜): How the camera moves through the scene
- Duration/pacing (时长/节奏): 4-15 seconds, match complexity
- Style consistency (风格一致): The output must match the reference image's style
For sub-mode 2 (首尾帧):
- Describe the TRANSITION from frame A to frame B — "花瓣从含苞逐渐绽放至完全盛开"
- Describe the pacing of the transition — "前半段缓慢积蓄，后半段加速绽放"
- Camera can remain static or follow the transformation
For sub-mode 3 (多帧故事):
- Describe the causal relationship between frames — "因为风吹过，所以花瓣飘落"
- Describe the passage of time — "从清晨到正午，光影在建筑表面缓缓移动"
- Camera work should connect frames narratively
For sub-mode 4 (全能参考):
- Assign clear roles to each reference — "图一提供人物特征，图二提供场景风格"
- Describe the synthesis — how elements from different references interact
Step 4: Apply I2V-specific rules
- Incremental only: Don't repeat what the reference image already shows
- Motion specificity: "她的头发在微风中轻轻飘动" not "有风"
- Stillness is intentional: Explicitly state what does NOT move
- Camera respects the reference: Camera movement is constrained by the reference composition
- Style must match: The output must be stylistically consistent with the reference
Step 5: Validate against checklist
Run through the Validation Checklist. Every item must pass before presenting the prompt to the user.
Step 6: Present the result
Always present: sub-mode label + motion description + complete prompt + duration + camera explanation.
Writing Rules for Image-to-Video
Rule 1: Incremental description — only write what changes
The reference image IS the visual. Don't describe its static content in the prompt. Focus 100% on motion and change.
Rule 2: Explicit stillness is as important as motion
Without explicit stillness constraints, AI tends to animate everything. Write "保持建筑完全静止""只有水在流动，其他一切不动".
Rule 3: Match sub-mode to prompt structure
Each sub-mode needs a different prompt structure. Don't use a single-image prompt for a frames2video task.
Rule 4: Camera movement respects the reference
Unlike text-to-video where camera can go anywhere, I2V camera movement is bound by the reference image's composition. Camera descriptions should work WITH the existing composition.
Rule 5: Duration scales with complexity
| Sub-mode | Motion Complexity | Suggested Duration |
|---|---|---|
| 单图 | 1-2 moving elements | 5-8s |
| 首尾帧 | 1 complete transformation | 8-12s |
| 多帧 | Multi-stage narrative | 10-15s |
| 全能参考 | Complex multi-source synthesis | 8-12s |
Validation Checklist
- Prompt describes only what MOVES/CHANGES (not static content from the reference image)
- Specific elements are named as moving + specific motion verbs used
- Elements that should stay still are explicitly listed
- Camera movement is described (not just named — explain the movement logic)
- Duration matches motion complexity
- Style consistency with reference image is addressed
- Correct sub-mode is identified and communicated
Gotchas
- Don't describe the reference image — the #1 I2V mistake. "A girl in a red dress standing in a garden" is useless if the reference already shows this. Write what HAPPENS: "The girl slowly turns..."
- Everything moves unless you stop it — AI's default is to animate everything. Use "everything else remains completely still" to lock down static elements
- Camera terms need explanation, not just naming — 只写"推镜头"不够，需要写"镜头缓缓向前推进，逐渐聚焦人物的面部表情"
- Resolution varies by sub-mode — Seedance 2.0 = 720p, legacy 3.5pro frames2video = 1080p
- Multiframe limit — 2-20 images for multi-frame story mode. More images = better consistency but slower generation
- Multimodal limits — max 9 images + 3 videos + 3 audio clips
- Style drift possible — output video may not perfectly match reference image style; use "保持参考图的风格和色调完全一致" to minimize drift
Available Resources
| Resource | Description | When to Load |
|---|---|---|
references/mode-library.md |
4 sub-mode templates with prompt structures | When building any I2V prompt |
references/word-library.md |
I2V-specific motion, stillness, coordination vocabulary | When building any I2V prompt |
examples/single-image.md |
Single-image-to-video examples | User has 1 reference image |
examples/first-last-frame.md |
First-and-last-frame examples | User has 2 images as start/end |
examples/multi-frame.md |
Multi-frame story examples | User has 2+ sequential images |
examples/multimodal-ref.md |
Omni-reference examples | User has mixed media references |