seedance-video-creator
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseSeedance 2.0 分镜视频创作工具
Seedance 2.0 Storyboard Video Creation Tool
将创意想法转化为专业分镜提示词,并通过即梦 API 直接生成视频、自动下载。
Turn creative ideas into professional storyboard prompts, and directly generate and automatically download videos via the Jimeng API.
前置条件
Prerequisites
使用本技能前,确保以下服务可用:
-
jimeng-free-api-all 服务运行中(默认端口 8000)bash
# Docker 部署 docker run -it -d --init --name jimeng-free-api-all \ -p 8000:8000 -e TZ=Asia/Shanghai \ wwwzhouhui569/jimeng-free-api-all:latest -
获取 SessionID:
- 打开 https://jimeng.jianying.com 并登录
- F12 → Application → Cookies → 复制 值
sessionid
-
环境变量(可选,也可在交互中指定):
- :API 地址(默认
JIMENG_API_URL)http://127.0.0.1:8000 - :即梦 SessionID
JIMENG_SESSION_ID
Before using this tool, ensure the following services are available:
-
jimeng-free-api-all service is running (default port 8000)bash
# Docker Deployment docker run -it -d --init --name jimeng-free-api-all \ -p 8000:8000 -e TZ=Asia/Shanghai \ wwwzhouhui569/jimeng-free-api-all:latest -
Obtain SessionID:
- Open https://jimeng.jianying.com and log in
- F12 → Application → Cookies → Copy the value of
sessionid
-
Environment Variables (optional, can also be specified during interaction):
- : API address (default
JIMENG_API_URL)http://127.0.0.1:8000 - : Jimeng SessionID
JIMENG_SESSION_ID
核心能力
Core Capabilities
Seedance 2.0 特性
Seedance 2.0 Features
多模态输入(最多12个文件):
- 图片:≤9张(首帧/尾帧/角色/场景参考)
- 视频:≤3个,总时长≤15s(运镜/动作/特效参考)
- 音频:≤3个,总时长≤15s(配乐/音效/对白参考)
- 文本:自然语言描述
视频参数:
- 模型:/
seedance-2.0seedance-2.0-pro - 比例:/
1:1/4:3/3:4/16:99:16 - 分辨率:/
480p/720p1080p - 时长:/
4/5秒10
交互方式:使用 、(或 、)指定素材用途
@1@2@图1@image1Multimodal Input (up to 12 files):
- Images: ≤9 (first frame/last frame/character/scene reference)
- Videos: ≤3, total duration ≤15s (camera movement/action/effect reference)
- Audio: ≤3, total duration ≤15s (background music/sound effects/dialogue reference)
- Text: Natural language description
Video Parameters:
- Model: /
seedance-2.0seedance-2.0-pro - Aspect Ratio: /
1:1/4:3/3:4/16:99:16 - Resolution: /
480p/720p1080p - Duration: /
4/5seconds10
Interaction Method: Use , (or , ) to specify material usage
@1@2@图1@image1工作流程
Workflow
模式一:完整引导模式(推荐新手)
Mode 1: Full Guidance Mode (Recommended for Beginners)
适合不确定要什么效果的用户,通过 5 步引导完成创作。
Suitable for users who are unsure about the desired effect, complete creation through 5-step guidance.
模式二:快速生成模式
Mode 2: Quick Generation Mode
适合已有明确想法的用户,直接提供提示词和素材即可生成。
Suitable for users with clear ideas, directly provide prompts and materials to generate videos.
模式三:纯提示词模式
Mode 3: Prompt-only Mode
只生成分镜提示词,不调用 API(用于在即梦平台手动使用)。
Only generate storyboard prompts without calling the API (for manual use on the Jimeng platform).
第一阶段:分镜提示词生成
Phase 1: Storyboard Prompt Generation
步骤一:理解用户想法
Step 1: Understand User's Idea
用友好的方式询问用户:
- 你想讲什么故事?(一句话概括核心内容)
- 视频时长?(4/5/10秒,默认10秒)
- 有参考素材吗?(图片/视频路径)
- 是否需要直接生成视频?(是→进入第二阶段 / 否→只输出提示词)
Ask the user in a friendly manner:
- What story do you want to tell? (One-sentence summary of the core content)
- Video duration? (4/5/10 seconds, default 10 seconds)
- Do you have reference materials? (Image/video path)
- Do you need to directly generate a video? (Yes → proceed to Phase 2 / No → only output prompts)
步骤二:深入挖掘细节
Step 2: Dig into Details
根据用户的初步回答,逐步引导完善以下维度:
Based on the user's initial response, gradually guide to improve the following dimensions:
1. 内容叙事
1. Content Narrative
- 故事的起承转合
- 关键情节和角色
- 对白/旁白内容
- The beginning, development, climax and ending of the story
- Key plots and characters
- Dialogue/voiceover content
2. 视觉风格
2. Visual Style
- 整体风格:写实/动画/水墨/科幻/复古/电影感
- 色调氛围:明亮/昏暗/暖色/冷色/黑白
- 画面比例:竖屏(9:16)/横屏(16:9)/电影宽屏(2.35:1)/标准(4:3)
- Overall style: Realistic/Animation/Ink wash/Sci-fi/Retro/Cinematic
- Tone and atmosphere: Bright/Dim/Warm color/Cool color/Black and white
- Aspect ratio: Vertical (9:16)/Horizontal (16:9)/Cinematic widescreen (2.35:1)/Standard (4:3)
3. 镜头语言
3. Lens Language
- 景别变化:远景→全景→中景→近景→特写
- 运镜方式:推/拉/摇/移/跟/环绕/升降/希区柯克变焦
- 转场方式:硬切/渐变/匹配剪辑/特效转场
- Shot changes: Long shot → Full shot → Medium shot → Close-up → Extreme close-up
- Camera movement: Push/Pull/Pan/Truck/Follow/Orbit/Rise/Fall/Hitchcock zoom
- Transition methods: Cut/Dissolve/Match cut/Effect transition
4. 动作与节奏
4. Action and Rhythm
- 主体动作:行走/奔跑/打斗/舞蹈/表情变化
- 动作节奏:舒缓/急促/有张有弛
- 是否需要音乐卡点
- Main action: Walking/Running/Fighting/Dancing/Facial expression changes
- Action rhythm: Slow/Urgent/With tension and relaxation
- Whether music beat matching is needed
5. 声音设计
5. Sound Design
- 配乐风格:激昂/温馨/悬疑/欢快/史诗
- 音效需求:环境音/动作音效/特殊音效
- 对白/旁白:台词内容和语气
- Background music style: Passionate/Warm/Suspenseful/Cheerful/Epic
- Sound effect requirements: Ambient sound/Action sound effect/Special sound effect
- Dialogue/voiceover: Line content and tone
步骤三:构建分镜结构
Step 3: Build Storyboard Structure
将故事拆解为时间轴上的镜头序列。
示例结构(10秒视频):
0-2秒:开场镜头,建立场景
2-4秒:发展,引入主体/冲突
4-7秒:高潮,核心动作/情感爆发
7-9秒:转折/过渡
9-10秒:结尾/落版Break down the story into a sequence of shots on the timeline.
Example Structure (10-second video):
0-2 seconds: Opening shot, establish the scene
2-4 seconds: Development, introduce the main subject/conflict
4-7 seconds: Climax, core action/emotional outburst
7-9 seconds: Twist/Transition
9-10 seconds: Ending/Closing shot步骤四:生成专业提示词
Step 4: Generate Professional Prompts
根据收集的信息,生成符合 Seedance 2.0 语法的提示词。
提示词结构模板:
【整体描述】风格 + 时长 + 画面比例 + 整体氛围
【分镜描述】
0-X秒:[镜头运动],[画面内容],[主体动作],[光影/特效]
X-Y秒:[镜头运动],[画面内容],[主体动作],[光影/特效]
...
【声音说明】配乐风格/音效/对白
【参考素材说明】(如有)
@1 作为首帧/角色参考
@2 参考运镜/动作提示词书写原则:
- 时间轴清晰,标注每段的秒数范围
- 镜头语言明确(推/拉/摇/移/跟/环绕等)
- 动作描述具体,避免模糊词汇
- 多图引用时使用 、
@1格式(对应上传图片顺序)@2 - 总长度控制在 500 字以内,Seedance 对过长提示词效果下降
Generate prompts that comply with Seedance 2.0 syntax based on the collected information.
Prompt Structure Template:
[Overall Description] Style + Duration + Aspect Ratio + Overall Atmosphere
[Storyboard Description]
0-X seconds: [Camera movement], [Frame content], [Main action], [Lighting/Effects]
X-Y seconds: [Camera movement], [Frame content], [Main action], [Lighting/Effects]
...
[Sound Instructions] Background music style/Sound effects/Dialogue
[Reference Material Instructions] (if any)
@1 As first frame/character reference
@2 Reference camera movement/actionPrompt Writing Principles:
- Clear timeline, mark the time range for each segment
- Explicit lens language (push/pull/pan/truck/follow/orbit, etc.)
- Specific action descriptions, avoid vague terms
- Use ,
@1format when referencing multiple images (corresponding to the upload order of images)@2 - Keep the total length within 500 words, as Seedance's performance declines with overly long prompts
步骤五:优化与确认
Step 5: Optimization and Confirmation
- 检查是否违反平台规则(写实人脸限制)
- 提供素材建议
- 确认用户满意后进入第二阶段
- Check for violations of platform rules (realistic face restrictions)
- Provide material suggestions
- Proceed to Phase 2 after confirming user satisfaction
第二阶段:视频生成与下载
Phase 2: Video Generation and Download
步骤一:确认生成参数
Step 1: Confirm Generation Parameters
在调用 API 前,向用户确认以下参数:
| 参数 | 说明 | 默认值 |
|---|---|---|
| API 地址 | jimeng-free-api-all 服务地址 | |
| SessionID | 即梦平台的 sessionid | 环境变量或用户提供 |
| 模型 | seedance-2.0 或 seedance-2.0-pro | |
| 比例 | 视频画面比例 | |
| 分辨率 | 480p/720p/1080p | |
| 时长 | 4/5/10 秒 | |
| 参考图片 | 本地图片路径列表 | 无 |
Before calling the API, confirm the following parameters with the user:
| Parameter | Description | Default Value |
|---|---|---|
| API Address | jimeng-free-api-all service address | |
| SessionID | sessionid of the Jimeng platform | Environment variable or provided by user |
| Model | seedance-2.0 or seedance-2.0-pro | |
| Aspect Ratio | Video aspect ratio | |
| Resolution | 480p/720p/1080p | |
| Duration | 4/5/10 seconds | |
| Reference Images | List of local image paths | None |
步骤二:调用 API 生成视频
Step 2: Call API to Generate Video
根据是否有参考图片,使用不同的调用方式:
Use different calling methods depending on whether there are reference images:
方式A:纯文本生成(无参考图片)
Method A: Text-only Generation (No Reference Images)
bash
curl -s -X POST "${API_URL}/v1/videos/generations" \
-H "Authorization: Bearer ${SESSION_ID}" \
-H "Content-Type: application/json" \
-d "{
\"model\": \"${MODEL}\",
\"prompt\": \"${PROMPT}\",
\"ratio\": \"${RATIO}\",
\"resolution\": \"${RESOLUTION}\",
\"duration\": ${DURATION}
}"bash
curl -s -X POST "${API_URL}/v1/videos/generations" \
-H "Authorization: Bearer ${SESSION_ID}" \
-H "Content-Type: application/json" \
-d "{
\"model\": \"${MODEL}\",
\"prompt\": \"${PROMPT}\",
\"ratio\": \"${RATIO}\",
\"resolution\": \"${RESOLUTION}\",
\"duration\": ${DURATION}
}"方式B:多图参考生成(有本地图片)
Method B: Multi-image Reference Generation (Local Images)
bash
curl -s -X POST "${API_URL}/v1/videos/generations" \
-H "Authorization: Bearer ${SESSION_ID}" \
-F "model=${MODEL}" \
-F "prompt=${PROMPT}" \
-F "ratio=${RATIO}" \
-F "resolution=${RESOLUTION}" \
-F "duration=${DURATION}" \
-F "files=@/path/to/image1.jpg" \
-F "files=@/path/to/image2.jpg"bash
curl -s -X POST "${API_URL}/v1/videos/generations" \
-H "Authorization: Bearer ${SESSION_ID}" \
-F "model=${MODEL}" \
-F "prompt=${PROMPT}" \
-F "ratio=${RATIO}" \
-F "resolution=${RESOLUTION}" \
-F "duration=${DURATION}" \
-F "files=@/path/to/image1.jpg" \
-F "files=@/path/to/image2.jpg"方式C:多图参考生成(图片 URL)
Method C: Multi-image Reference Generation (Image URLs)
bash
curl -s -X POST "${API_URL}/v1/videos/generations" \
-H "Authorization: Bearer ${SESSION_ID}" \
-H "Content-Type: application/json" \
-d "{
\"model\": \"${MODEL}\",
\"prompt\": \"${PROMPT}\",
\"ratio\": \"${RATIO}\",
\"resolution\": \"${RESOLUTION}\",
\"duration\": ${DURATION},
\"file_paths\": [\"https://example.com/img1.jpg\", \"https://example.com/img2.jpg\"]
}"重要:
- API 是同步阻塞的,会自动轮询直到视频生成完成(通常 60-120 秒)
- curl 超时建议设置为 300 秒:
--max-time 300 - 提示词中的 、
@1对应@2参数中图片的上传顺序files
bash
curl -s -X POST "${API_URL}/v1/videos/generations" \
-H "Authorization: Bearer ${SESSION_ID}" \
-H "Content-Type: application/json" \
-d "{
\"model\": \"${MODEL}\",
\"prompt\": \"${PROMPT}\",
\"ratio\": \"${RATIO}\",
\"resolution\": \"${RESOLUTION}\",
\"duration\": ${DURATION},
\"file_paths\": [\"https://example.com/img1.jpg\", \"https://example.com/img2.jpg\"]
}"Important:
- The API is synchronously blocking and will automatically poll until video generation is complete (usually 60-120 seconds)
- It is recommended to set curl timeout to 300 seconds:
--max-time 300 - ,
@1in the prompt correspond to the upload order of images in the@2parameterfiles
步骤三:解析结果
Step 3: Parse Results
API 返回 OpenAI 兼容格式:
json
{
"created": 1700000000,
"data": [
{
"url": "https://v3-dreamnia.jimeng.com/...",
"revised_prompt": "原始提示词"
}
]
}从响应中提取 即为视频下载地址。
data[0].urlThe API returns an OpenAI-compatible format:
json
{
"created": 1700000000,
"data": [
{
"url": "https://v3-dreamnia.jimeng.com/...",
"revised_prompt": "Original prompt"
}
]
}Extract from the response as the video download address.
data[0].url步骤四:下载视频
Step 4: Download Video
bash
undefinedbash
undefined提取视频 URL 并下载
Extract video URL and download
VIDEO_URL=$(echo "${RESPONSE}" | jq -r '.data[0].url')
OUTPUT_FILE="seedance_$(date +%Y%m%d_%H%M%S).mp4"
curl -L -o "${OUTPUT_FILE}" "${VIDEO_URL}"
echo "视频已下载到: $(pwd)/${OUTPUT_FILE}"
undefinedVIDEO_URL=$(echo "${RESPONSE}" | jq -r '.data[0].url')
OUTPUT_FILE="seedance_$(date +%Y%m%d_%H%M%S).mp4"
curl -L -o "${OUTPUT_FILE}" "${VIDEO_URL}"
echo "Video downloaded to: $(pwd)/${OUTPUT_FILE}"
undefined步骤五:展示结果
Step 5: Present Results
向用户报告:
- 视频生成成功/失败
- 视频文件路径和大小
- 使用的提示词(方便用户微调重试)
Report to the user:
- Video generation success/failure
- Video file path and size
- Prompt used (convenient for users to fine-tune and retry)
错误处理
Error Handling
API 错误码
API Error Codes
| 状态码 | 含义 | 处理方式 |
|---|---|---|
| 200 | 成功 | 提取 data[0].url |
| 401 | SessionID 过期 | 提示用户重新获取 |
| 400 | 参数错误 | 检查 model/ratio/duration |
| 429 | 积分不足 | 提示用户等待或充值 |
| 500 | 服务器错误 | 重试或检查服务状态 |
| Status Code | Meaning | Handling Method |
|---|---|---|
| 200 | Success | Extract data[0].url |
| 401 | SessionID expired | Prompt user to re-obtain |
| 400 | Parameter error | Check model/ratio/duration |
| 429 | Insufficient credits | Prompt user to wait or recharge |
| 500 | Server error | Retry or check service status |
常见问题
Common Issues
| 问题 | 解决方案 |
|---|---|
| 连接拒绝 | 检查 jimeng-free-api-all 容器是否运行 |
| 生成超时 | 增加 curl --max-time,或降低分辨率 |
| 内容被过滤 | 修改提示词,避免敏感内容 |
| 视频 URL 失效 | URL 有时效性,及时下载 |
| 积分不足 | 每日免费积分有限,次日刷新 |
| Issue | Solution |
|---|---|
| Connection refused | Check if the jimeng-free-api-all container is running |
| Generation timeout | Increase curl --max-time, or reduce resolution |
| Content filtered | Modify the prompt to avoid sensitive content |
| Video URL expired | The URL has a time limit, download immediately after generation |
| Insufficient credits | Daily free credits are limited (about 66 credits), plan usage reasonably |
完整示例对话
Complete Example Dialogue
示例:海边跳舞视频
Example: Beach Dance Video
用户:帮我生成一个女孩在海边跳舞的视频
引导:
- 什么风格的舞蹈?现代舞/古典舞/街舞/自由舞动?
- 海边是什么时间?日出/白天/日落/夜晚?
- 整体氛围?欢快/忧伤/自由/浪漫?
- 时长多少秒?有参考图片吗?
生成的提示词:
电影级写实风格,10秒,16:9宽屏,日落黄金时刻的温暖氛围
0-2秒:远景缓慢推近,海平线夕阳,女孩剪影站在沙滩上,裙摆被海风吹动
2-5秒:中景环绕镜头,女孩开始旋转起舞,长发和裙摆飞扬,夕阳逆光形成轮廓光
5-8秒:近景跟随移动,女孩面向镜头舞动,表情自由愉悦,海浪轻拍沙滩作为背景
8-10秒:远景拉远,女孩在落日余晖中定格,画面渐暗
背景音效:海浪声 + 轻柔的钢琴配乐API 调用:
bash
curl -s --max-time 300 -X POST "http://127.0.0.1:8000/v1/videos/generations" \
-H "Authorization: Bearer ${SESSION_ID}" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2.0",
"prompt": "电影级写实风格,10秒,16:9宽屏,日落黄金时刻的温暖氛围\n\n0-2秒:远景缓慢推近,海平线夕阳,女孩剪影站在沙滩上,裙摆被海风吹动\n2-5秒:中景环绕镜头,女孩开始旋转起舞,长发和裙摆飞扬,夕阳逆光形成轮廓光\n5-8秒:近景跟随移动,女孩面向镜头舞动,表情自由愉悦,海浪轻拍沙滩作为背景\n8-10秒:远景拉远,女孩在落日余晖中定格,画面渐暗\n\n背景音效:海浪声 + 轻柔的钢琴配乐",
"ratio": "16:9",
"resolution": "720p",
"duration": 10
}'User: Help me generate a video of a girl dancing on the beach
Guidance:
- What style of dance? Modern dance/Classical dance/Hip-hop/Free dance?
- What time of day is it at the beach? Sunrise/Daytime/Sunset/Night?
- Overall atmosphere? Cheerful/Sad/Free/Romantic?
- Duration in seconds? Do you have reference images?
Generated Prompt:
Cinematic realistic style, 10 seconds, 16:9 widescreen, warm atmosphere of the golden hour at sunset
0-2 seconds: Long shot slowly pushing in, sunset on the horizon, girl's silhouette standing on the beach, skirt blown by the sea breeze
2-5 seconds: Medium shot with orbit camera, girl starts spinning and dancing, hair and skirt flying, backlighting from the sunset forms a rim light
5-8 seconds: Close-up follow shot, girl dances facing the camera, expression free and joyful, waves gently hitting the beach as background
8-10 seconds: Long shot pulling out, girl freezes in the afterglow of the sunset, frame fades to dark
Background sound effects: Sea waves + soft piano background musicAPI Call:
bash
curl -s --max-time 300 -X POST "http://127.0.0.1:8000/v1/videos/generations" \
-H "Authorization: Bearer ${SESSION_ID}" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2.0",
"prompt": "Cinematic realistic style, 10 seconds, 16:9 widescreen, warm atmosphere of the golden hour at sunset\n\n0-2 seconds: Long shot slowly pushing in, sunset on the horizon, girl's silhouette standing on the beach, skirt blown by the sea breeze\n2-5 seconds: Medium shot with orbit camera, girl starts spinning and dancing, hair and skirt flying, backlighting from the sunset forms a rim light\n5-8 seconds: Close-up follow shot, girl dances facing the camera, expression free and joyful, waves gently hitting the beach as background\n8-10 seconds: Long shot pulling out, girl freezes in the afterglow of the sunset, frame fades to dark\n\nBackground sound effects: Sea waves + soft piano background music",
"ratio": "16:9",
"resolution": "720p",
"duration": 10
}'示例:多图参考视频
Example: Multi-image Reference Video
用户:用这两张图片生成一个两人跳舞的视频
- 图片1:/home/user/dancer1.jpg
- 图片2:/home/user/dancer2.jpg
生成的提示词:
电影级写实风格,10秒,4:3画幅,舞台灯光氛围
0-2秒:中景,@1 和 @2 面对面站立,灯光从上方打下,准备动作
2-5秒:全景,两人开始双人舞,镜头缓慢环绕,动作优雅协调
5-8秒:中近景跟随,舞步加快,旋转动作,光影交错
8-10秒:远景拉出,两人定格在舞蹈结束的pose,画面渐暗API 调用:
bash
curl -s --max-time 300 -X POST "http://127.0.0.1:8000/v1/videos/generations" \
-H "Authorization: Bearer ${SESSION_ID}" \
-F "model=seedance-2.0" \
-F "prompt=电影级写实风格,10秒,4:3画幅,舞台灯光氛围..." \
-F "ratio=4:3" \
-F "resolution=720p" \
-F "duration=10" \
-F "files=@/home/user/dancer1.jpg" \
-F "files=@/home/user/dancer2.jpg"User: Generate a video of two people dancing using these two images
- Image 1: /home/user/dancer1.jpg
- Image 2: /home/user/dancer2.jpg
Generated Prompt:
Cinematic realistic style, 10 seconds, 4:3 aspect ratio, stage lighting atmosphere
0-2 seconds: Medium shot, @1 and @2 stand face to face, lights from above, preparation pose
2-5 seconds: Full shot, the two start a duet, camera slowly orbits, movements are elegant and coordinated
5-8 seconds: Medium close-up follow shot, dance steps speed up, spinning movements, light and shadow interweave
8-10 seconds: Long shot pulling out, the two freeze in the ending pose of the dance, frame fades to darkAPI Call:
bash
curl -s --max-time 300 -X POST "http://127.0.0.1:8000/v1/videos/generations" \
-H "Authorization: Bearer ${SESSION_ID}" \
-F "model=seedance-2.0" \
-F "prompt=Cinematic realistic style, 10 seconds, 4:3 aspect ratio, stage lighting atmosphere..." \
-F "ratio=4:3" \
-F "resolution=720p" \
-F "duration=10" \
-F "files=@/home/user/dancer1.jpg" \
-F "files=@/home/user/dancer2.jpg"分镜模板速查
Quick Reference for Storyboard Templates
模板一:叙事故事类
Template 1: Narrative Story Type
【风格】电影级写实/动画/水墨/科幻风格
【时长】10秒
【画幅】16:9
0-2秒:[镜头运动],[场景建立],[主体引入]
2-4秒:[镜头运动],[情节发展],[动作描述]
4-7秒:[镜头运动],[高潮/冲突],[情绪爆发]
7-9秒:[镜头运动],[转折/过渡]
9-10秒:[镜头运动],[结尾/落版]
【声音】配乐风格 + 音效 + 对白
【参考】@1 作为首帧,@2 参考角色[Style] Cinematic realistic/Animation/Ink wash/Sci-fi style
[Duration] 10 seconds
[Aspect Ratio] 16:9
0-2 seconds: [Camera movement], [Scene establishment], [Main subject introduction]
2-4 seconds: [Camera movement], [Plot development], [Action description]
4-7 seconds: [Camera movement], [Climax/Conflict], [Emotional outburst]
7-9 seconds: [Camera movement], [Twist/Transition]
9-10 seconds: [Camera movement], [Ending/Closing shot]
[Sound] Background music style + Sound effects + Dialogue
[Reference] @1 as first frame, @2 as character reference模板二:产品展示类
Template 2: Product Display Type
【风格】商业广告/极简/高端/科技感
【时长】10秒
0-2秒:开场抓眼球,产品特写或悬念设置
2-4秒:产品全景展示,运镜环绕/推拉
4-7秒:产品细节特写,材质/工艺展示
7-9秒:使用场景,产品在实际环境中的应用
9-10秒:品牌落版,slogan展示
【声音】大气恢宏/轻快时尚/科技感配乐
【参考】@1 产品外观,@2 材质参考[Style] Commercial advertisement/Minimalist/High-end/Technological
[Duration] 10 seconds
0-2 seconds: Eye-catching opening, product close-up or suspense setup
2-4 seconds: Full shot of product, orbit/push-pull camera movement
4-7 seconds: Close-up of product details, material/craft display
7-9 seconds: Usage scenario, product application in real environment
9-10 seconds: Brand closing, slogan display
[Sound] Grand/Cheerful and fashionable/Technological background music
[Reference] @1 product appearance, @2 material reference模板三:角色动作类
Template 3: Character Action Type
【风格】根据角色设定(武侠/科幻/现代/奇幻)
【时长】10秒
0-2秒:角色亮相,定格或缓慢展示造型
2-4秒:动作起始,准备姿势
4-8秒:核心动作展示(打斗/舞蹈/特技)
8-9秒:动作收尾,pose定格
9-10秒:特效/氛围强化,画面落版
【声音】动作音效 + 氛围配乐
【参考】@1 角色形象,@2 动作参考[Style] Based on character setting (Martial arts/Sci-fi/Modern/Fantasy)
[Duration] 10 seconds
0-2 seconds: Character appearance, freeze frame or slow display of posture
2-4 seconds: Action start, preparation pose
4-8 seconds: Core action display (Fighting/Dancing/Stunt)
8-9 seconds: Action conclusion, pose freeze
9-10 seconds: Effect/atmosphere enhancement, frame closing
[Sound] Action sound effects + Ambient background music
[Reference] @1 character image, @2 action reference模板四:风景旅拍类
Template 4: Scenery Travel Shot Type
【风格】电影级纪录片/治愈系/史诗感
【时长】10秒
0-2秒:大景别建立镜头,展示环境全貌
2-4秒:中景推进,引入人物或细节
4-7秒:多角度切换,展示环境不同面貌
7-9秒:特写细节,光影变化
9-10秒:回到大景别或意境落版
【声音】环境音 + 氛围配乐
【参考】@1-@5 场景参考[Style] Cinematic documentary/Healing/Epic
[Duration] 10 seconds
0-2 seconds: Wide establishing shot, showing the full environment
2-4 seconds: Medium shot pushing in, introducing characters or details
4-7 seconds: Multi-angle switching, showing different aspects of the environment
7-9 seconds: Close-up of details, light and shadow changes
9-10 seconds: Return to wide shot or artistic closing
[Sound] Ambient sound + Ambient background music
[Reference] @1-@5 scene references模板五:视频延长/续拍
Template 5: Video Extension/Continuation
将@视频1延长X秒(生成长度选择X秒)
延续前视频的风格和主体:
0-X秒:[新内容描述],与前视频无缝衔接
【要求】保持角色一致性,动作连贯流畅Extend @Video 1 by X seconds (select X seconds as the generated length)
Continue the style and main subject of the previous video:
0-X seconds: [New content description], seamlessly connected with the previous video
[Requirements] Maintain character consistency, smooth and coherent movements模板六:剧情颠覆/编辑
Template 6: Plot Subversion/Editing
基于@视频1进行编辑:
【保留】原视频的运镜/部分动作/场景
【修改】[具体修改点]
【颠覆】[剧情反转描述]
【要求】保持镜头连贯,只在指定位置修改Edit based on @Video 1:
[Retain] Camera movement/partial action/scene of the original video
[Modify] [Specific modification points]
[Subvert] [Plot reversal description]
[Requirements] Maintain lens coherence, only modify at specified positions镜头语言速查
Quick Reference for Lens Language
| 中文 | 效果 | 适用场景 |
|---|---|---|
| 推镜头 | 强调主体,营造紧张感 | 情感爆发、细节展示 |
| 拉镜头 | 展现场景,营造疏离感 | 开场建立、结尾收束 |
| 摇镜头 | 左右/上下展示环境 | 环境介绍、角色关系 |
| 移镜头 | 平行移动,跟随主体 | 行走、追逐 |
| 跟镜头 | 跟随主体移动 | 动作跟拍 |
| 环绕镜头 | 360度展示主体 | 产品展示、角色亮相 |
| 升降镜头 | 从上往下或从下往上 | 场景全貌、气势展示 |
| 希区柯克变焦 | 背景压缩/拉伸效果 | 悬疑、心理变化 |
| 手持晃动 | 纪实感/紧张感 | 纪录片、追逐 |
| 一镜到底 | 不切镜头,连续拍摄 | 沉浸感、长叙事 |
| Chinese | Effect | Applicable Scenario |
|---|---|---|
| 推镜头 | Emphasize the subject, create tension | Emotional outburst, detail display |
| 拉镜头 | Show the scene, create a sense of distance | Opening establishment, closing conclusion |
| 摇镜头 | Display the environment left/right/up/down | Environment introduction, character relationship |
| 移镜头 | Parallel movement, follow the subject | Walking, chasing |
| 跟镜头 | Follow the subject to move | Action follow-shot |
| 环绕镜头 | 360-degree display of the subject | Product display, character appearance |
| 升降镜头 | From top to bottom or bottom to top | Full scene display, momentum display |
| 希区柯克变焦 | Background compression/stretching effect | Suspense, psychological changes |
| 手持晃动 | Documentary feel/tension | Documentary, chasing |
| 一镜到底 | No cuts, continuous shooting | Immersion, long narrative |
氛围关键词速查
Quick Reference for Atmosphere Keywords
光影:逆光、侧光、顶光、伦勃朗光、剪影、轮廓光、体积光、丁达尔效应
色调:暖色调、冷色调、高饱和、低饱和、黑白、赛博朋克、复古胶片
质感:电影级、纪录片风格、广告质感、MV风格、油画感、水墨感
情绪:温馨、紧张、悬疑、欢快、忧伤、史诗、治愈、惊悚
Light and Shadow: Backlight, Side light, Top light, Rembrandt light, Silhouette, Rim light, Volumetric light, Tyndall effect
Tone: Warm tone, Cool tone, High saturation, Low saturation, Black and white, Cyberpunk, Retro film
Texture: Cinematic, Documentary style, Advertisement texture, MV style, Oil painting feel, Ink wash feel
Emotion: Warm, Tense, Suspenseful, Cheerful, Sad, Epic, Healing, Thrilling
特殊场景处理
Special Scene Handling
1. 角色一致性需求
1. Character Consistency Requirement
- 建议用户提供角色参考图作为 上传
files - 提示词中用 指定角色参考
@1 - 注意:暂不支持写实真人脸部素材
- It is recommended that users upload character reference images as
files - Specify character reference with in the prompt
@1 - Note: Realistic human face materials are not supported temporarily
2. 运镜/动作复刻
2. Camera Movement/Action Replication
- 建议用户提供参考视频
- 提示词中说明"完全参考@视频1的所有运镜效果"
- It is recommended that users provide reference videos
- Explain in the prompt "fully reference all camera movement effects of @Video 1"
3. 视频延长
3. Video Extension
- 明确说明"将@视频1延长Xs"
- duration 参数设为新增部分的时长
- Clearly state "extend @Video 1 by Xs"
- Set the duration parameter to the length of the new part
4. 剧情颠覆/编辑
4. Plot Subversion/Editing
- 基于已有视频进行修改时,清晰描述改动点
- When modifying based on an existing video, clearly describe the changes
5. 音乐卡点
5. Music Beat Matching
- 时间轴标注与音乐重拍对齐
- 建议提供参考视频展示节奏
- Mark the timeline to align with the strong beats of the music
- It is recommended to provide a reference video to show the rhythm
注意事项
Notes
- 暂不支持上传包含写实真人脸部的素材
- 视频参考会消耗更多生成额度
- 混合输入总上限是12个文件
- 优先上传对画面影响最大的素材
- API 调用是同步阻塞的,生成 10 秒视频通常需要 60-120 秒
- 视频下载 URL 有时效性,生成后应立即下载
- 每日免费积分有限(约66积分),合理规划使用
- Materials containing realistic human faces are not supported temporarily
- Video references will consume more generation credits
- The total limit for mixed input is 12 files
- Prioritize uploading materials that have the greatest impact on the frame
- API calls are synchronously blocking, generating a 10-second video usually takes 60-120 seconds
- The video download URL has a time limit, download immediately after generation
- Daily free credits are limited (about 66 credits), plan usage reasonably
输出格式
Output Format
最终输出应包含:
- 理解确认:确认理解的故事内容
- 分镜提示词:可直接使用的完整提示词
- 生成参数:model/ratio/resolution/duration
- 生成结果:视频文件路径(如果调用了 API)
- 使用提示:如需在即梦平台手动使用的说明
The final output should include:
- Understanding Confirmation: Confirmed story content
- Storyboard Prompt: Complete prompt that can be used directly
- Generation Parameters: model/ratio/resolution/duration
- Generation Result: Video file path (if API was called)
- Usage Tips: Instructions for manual use on the Jimeng platform