将创意想法转化为专业分镜提示词,通过即梦 API 先生成参考图,再基于图片+提示词生成视频、自动下载。
Works with
AI-first code editor with Composer
Before installing skills in Cursor, ensure your development environment meets these requirements:
node --versionseedance-video-creatorExecute the skills CLI command in your project's root directory to begin installation:
Fetches seedance-video-creator from wwwzhouhui/skills_collection and configures it for Cursor.
The CLI shows a list of agents. Use arrow keys and space to select Cursor:
Confirm successful installation by checking the skill directory location:
Restart Cursor to activate seedance-video-creator. Access via /seedance-video-creator in your agent's command palette.
We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.
Skills execute code in your environment. Always review source, verify the publisher, and test in isolation before production.
Submit your Claude Code skill and start earning
Automate repetitive workflows and reduce manual effort
Example
Generate reports, summarize documents, draft communications
Save 3-5 hours per week on routine tasks
Learn new skills, understand complex topics, get expert guidance
Example
Explain concepts, provide examples, suggest learning resources
Accelerate learning and skill development by 2x
Enhance output quality through reviews, suggestions, and refinements
Example
Review drafts, suggest improvements, catch errors
Improve work quality by 30-40% with less effort
0
total installs
0
this week
194
GitHub stars
0
upvotes
Run in your terminal
0
installs
0
this week
194
stars
将创意想法转化为专业分镜提示词,通过即梦 API 先生成参考图,再基于图片+提示词生成视频、自动下载。
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)
# 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:
sessionid 值环境变量(可选,也可在交互中指定):
JIMENG_API_URL:API 基础地址(默认 http://127.0.0.1:8000),注意只填基础地址,不要包含路径部分。如使用 duckcloud 服务则为 https://jimeng.duckcloud.funJIMENG_SESSION_ID:即梦 SessionID重要约束:Seedance 2.0 必须至少提供一张参考图片,不支持纯文本生成视频。当用户没有提供图片时,需要先通过文生图 API 生成首帧参考图。
多模态输入(最多12个文件):
视频参数:
seedance-2.0-fast(推荐,快速版)/ jimeng-video-seedance-2.0-fast(等价别名)/ jimeng-video-seedance-2.0(Pro版)/ seedance-2.0 / seedance-2.0-pro(Pro等价别名)1:1 / 4:3 / 3:4 / 16:9 / 9:16 / 3:2 / 2:3 / 21:9480p / 720p(默认)/ 1080p4 - 15 秒交互方式:使用 @1、@2(或 @图1、@image1)指定素材用途
核心流程:分镜提示词 → 文生图生成首帧 → 图片+提示词生成视频
用户输入创意 → 第一阶段:生成分镜提示词
→ 第二阶段:调用文生图 API 生成首帧参考图 → 下载图片到本地
→ 第三阶段:用参考图 + 分镜提示词调用 Seedance 2.0 → 下载视频
用友好的方式询问用户:
根据用户的初步回答,逐步引导完善以下维度:
将故事拆解为时间轴上的镜头序列。
示例结构(4秒视频):
0-1秒:开场镜头,建立场景
1-3秒:发展,核心动作/情感
3-4秒:结尾,画面定格
根据收集的信息,分别生成:
描述视频第一帧的静态画面,作为 Seedance 2.0 的首帧参考图。
首帧提示词要求:
示例:
日落时分的海边沙滩,一位穿着白色飘逸长裙的年轻女孩站在海边,面朝大海,夕阳逆光照射,金色光晕笼罩全身,长发和裙摆被海风轻轻吹动,远处海平线上的落日将天空染成橘红色,脚边浅浅的海浪泡沫
完整的分镜提示词,用 @1 引用首帧参考图。
提示词结构模板:
【整体描述】风格 + 时长 + 画面比例 + 整体氛围
@1 作为画面首帧参考
【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
提示词书写原则:
@1 引用首帧图片(首帧图片由第二阶段自动生成)@1、@2 分别引用目的:Seedance 2.0 必须有参考图片,当用户没有提供图片时,先通过文生图 API 生成首帧画面。
如果用户已提供图片:跳过此阶段,直接进入第三阶段。
curl -s --max-time 120 -X POST "${API_URL}/v1/images/generations" \
-H "Authorization: Bearer ${SESSION_ID}" \
-H "Content-Type: application/json" \
-d "{
\"model\": \"jimeng-4.5\",
\"prompt\": \"${首帧图片提示词}\",
\"ratio\": \"${RATIO}\",
\"resolution\": \"2k\"
}"
参数说明:
| 参数 | 说明 | 推荐值 |
|---|---|---|
| model | 图像生成模型 | jimeng-4.5(稳定高质量) |
| prompt | 首帧画面描述 | 第一阶段生成的首帧提示词 |
| ratio | 画面比例 | 与视频比例一致(如 9:16) |
| resolution | 图片分辨率 | 2k |
API 返回格式:
{
"created": 1700000000,
"data": [
{ "url": "https://p6-heycan-hgt.byteimg.com/..." }
]
}
IMAGE_URL=$(echo "${RESPONSE}" | jq -r '.data[0].url')
IMAGE_FILE="/tmp/seedance_frame_$(date +%Y%m%d_%H%M%S).png"
curl -sL -o "${IMAGE_FILE}" "${IMAGE_URL}"
报告生成结果,让用户确认首帧画面满意后进入第三阶段。
| 参数 | 说明 | 默认值 |
|---|---|---|
| API 地址 | jimeng-free-api-all 服务地址 | http://127.0.0.1:8000 |
| SessionID | 即梦平台的 sessionid | 环境变量或用户提供 |
| 模型 | seedance-2.0-fast | seedance-2.0-fast |
| 比例 | 视频画面比例 | 与首帧图片一致 |
| 分辨率 | 视频分辨率 | 720p |
| 时长 | 4-15 秒 | 4 |
| 参考图片 | 首帧图片路径(第二阶段生成或用户提供) | 必需 |
使用本地图片(multipart/form-data):
curl -s --max-time 300 -X POST "${API_URL}/v1/videos/generations" \
-H "Authorization: Bearer ${SESSION_ID}" \
-F "model=seedance-2.0-fast" \
-F "prompt=${VIDEO_PROMPT}" \
-F "ratio=${RATIO}" \
-F "resolution=${RESOLUTION}" \
-F "duration=${DURATION}" \
-F "files=@${IMAGE_FILE}"
多张图片时:
curl -s --max-time 300 -X POST "${API_URL}/v1/videos/generations" \
-H "Authorization: Bearer ${SESSION_ID}" \
-F "model=seedance-2.0-fast" \
-F "prompt=${VIDEO_PROMPT}" \
-F "ratio=${RATIO}" \
-F "resolution=${RESOLUTION}" \
-F "duration=${DURATION}" \
-F "files=@/path/to/image1.jpg" \
-F "files=@/path/to/image2.jpg"
重要:
{"code":-2001,"message":"Seedance 2.0 需要至少一张图片"}--max-time 300@1、@2 对应 files 参数中图片的上传顺序Bearer 前缀,格式为 Bearer your_sessionidAPI 返回 OpenAI 兼容格式:
{
"created": 1700000000,
"data": [
{
"url": "https://v3-dreamnia.jimeng.com/...",
"revised_prompt": "原始提示词"
}
]
}
VIDEO_URL=$(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}"
向用户报告:
| 错误 | 含义 | 处理方式 |
|---|---|---|
code: -2001 |
Seedance 需要至少一张图片 | 先调文生图 API 生成首帧,再重试 |
| HTTP 200 | 成功 | 提取 data[0].url |
| HTTP 401 | SessionID 过期 | 提示用户重新获取 |
| HTTP 400 | 参数错误 | 检查 model/ratio/duration |
| HTTP 429 | 积分不足 | 提示用户等待或充值 |
| HTTP 500 | 服务器错误 | 重试或检查服务状态 |
| 问题 | 解决方案 |
|---|---|
| Seedance 报错需要图片 | 必须先通过文生图生成首帧,再用图片调 Seedance |
| 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,或降低时长 |
| 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 |
用户:帮我生成一个橘猫在海边捉螃蟹的视频,9:16竖屏,4秒
第一阶段 - 生成提示词:
首帧图片提示词:
阳光明媚的海边沙滩,一只圆滚滚的橘色猫咪蹲在潮湿的沙滩上,好奇地盯着面前一只小螃蟹,金色阳光照射,海浪轻轻拍打岸边,色彩鲜明活泼,3D动画风格
视频分镜提示词:
可爱3D动画风格,4秒,9:16竖屏,阳光明媚的海边
@1 作为画面首帧参考
0-1秒:中景,画面中的橘猫好奇地盯着沙滩上的小螃蟹,海浪轻拍岸边
1-3秒:近景跟随,橘猫伸出爪子试探性地去抓螃蟹,螃蟹举起钳子反击,橘猫被吓得往后一跳,表情夸张可爱
3-4秒:中景微拉远,橘猫和螃蟹对峙,背景碧蓝大海和白色浪花
背景音效:欢快俏皮卡通配乐 + 海浪声
第二阶段 - 生成首帧参考图:
# 1. 调用文生图 API 生成首帧
curl -s --max-time 120 -X POST "${API_URL}/v1/images/generations" \
-H "Authorization: Bearer ${SESSION_ID}" \
-H "Content-Type: application/json" \
-d '{
"model": "jimeng-4.5",
"prompt": "阳光明媚的海边沙滩,一只圆滚滚的橘色猫咪蹲在潮湿的沙滩上,好奇地盯着面前一只小螃蟹,金色阳光照射,海浪轻轻拍打岸边,色彩鲜明活泼,3D动画风格",
"ratio": "9:16",
"resolution": "2k"
}'
# 2. 下载图片
IMAGE_URL=$(echo "${RESPONSE}" | jq -r '.data[0].url')
curl -sL -o /tmp/seedance_frame.png "${IMAGE_URL}"
第三阶段 - 生成视频:
curl -s --max-time 300 -X POST "${API_URL}/v1/videos/generations"Prerequisites
Time Estimate
15-45 minutes depending on use case complexity
Steps
Common Pitfalls
✓ Do
✗ Don't
💡 Pro Tips
✓ Use when
Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.
✗ Avoid when
Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.
wwwzhouhui/skills_collection
affaan-m/everything-claude-code
remotion-dev/skills
supercent-io/skills-template
heygen-com/skills
whyashthakker/agent-skills-marketing
Registry listing for seedance-video-creator matched our evaluation — installs cleanly and behaves as described in the markdown.
seedance-video-creator reduced setup friction for our internal harness; good balance of opinion and flexibility.
Useful defaults in seedance-video-creator — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
I recommend seedance-video-creator for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
I recommend seedance-video-creator for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.
Useful defaults in seedance-video-creator — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.
Solid pick for teams standardizing on skills: seedance-video-creator is focused, and the summary matches what you get after install.
Keeps context tight: seedance-video-creator is the kind of skill you can hand to a new teammate without a long onboarding doc.
seedance-video-creator has been reliable in day-to-day use. Documentation quality is above average for community skills.
Registry listing for seedance-video-creator matched our evaluation — installs cleanly and behaves as described in the markdown.
showing 1-10 of 28