← Back to Skills Marketplace
40
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install stitch-jimeng-video
Description
即梦AI视频生成3.0 1080P。通过火山引擎即梦AI API生成视频（图生视频-首尾帧模式）。 触发词：即梦、极梦、视频生成、图生视频、首尾帧、火山引擎视频
README (SKILL.md)
即梦AI 视频生成3.0 1080P
通过火山引擎即梦AI API生成视频（图生视频-首尾帧模式）。
前置要求
在环境变量或 .env 中配置：
export VOLC_ACCESS_KEY="你的 Access Key ID"
export VOLC_SECRET_KEY="你的 Secret Access Key"
使用方式
python3 {baseDir}/scripts/jimeng_video.py \
--prompt "镜头缓缓推进，画面从冬天的枯树过渡到春天的花开" \
--first "/path/to/start.jpg" \
--last "/path/to/end.jpg"
参数
| 参数 | 说明 | 必填 |
|---|---|---|
| --prompt | 视频描述（建议400字以内） | 是 |
| --first | 首帧图片路径或URL | 是 |
| --last | 尾帧图片路径或URL | 是 |
| --seed | 随机种子（默认-1随机） | 否 |
| --output | 输出文件路径 | 否 |
| --no-poll | 只提交不轮询 | 否 |
API 信息
- 端点：
https://visual.volcengineapi.com - 提交任务 Action：
CVSync2AsyncSubmitTask - 查询任务 Action：
CVSync2AsyncGetResult - req_key：
jimeng_i2v_first_tail_v30_1080 - 认证：火山引擎 HMAC-SHA256 签名（SDK 自动处理）
Usage Guidance
Install only if you are comfortable using Volcengine API credentials and sending the selected prompt plus first/last-frame images to Volcengine. Use non-sensitive media, watch for API charges, and prefer reviewing the returned download URL behavior before using it in a sensitive environment.
Capability Assessment
Purpose & Capability
The documented purpose is generating first/last-frame videos through the Volcengine Jimeng API, and the script behavior matches that purpose: it submits prompts and images, polls task status, and downloads the generated video.
Instruction Scope
The skill discloses API use, endpoint, credentials, and CLI arguments, but the trigger terms are broad and there is no explicit runtime privacy confirmation before uploading prompt and image data.
Install Mechanism
No installer, auto-update logic, package mutation, or hidden setup behavior was found. The script imports the Volcengine SDK and expects it to already be available.
Credentials
Use of VOLC_ACCESS_KEY and VOLC_SECRET_KEY plus outbound API calls is proportionate for cloud video generation, but it is billing- and privacy-sensitive.
Persistence & Privilege
The script reads only user-provided image paths or URLs and writes the output video to a user-specified path or the OpenClaw workspace default. No background persistence, privilege escalation, deletion, or broad indexing was found.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install stitch-jimeng-video - After installation, invoke the skill by name or use
/stitch-jimeng-video - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of jimeng-video-gen skill for generating HD 1080P videos via Volcano Engine's AI API.
- Supports video generation from first and last images with descriptive prompt.
- Provides command-line interface and detailed usage instructions.
- Environment variable configuration for secure API authentication.
- Includes options for random seed, output path, and simple task control.
Metadata
Frequently Asked Questions
What is Jimeng Video Generator?
即梦AI视频生成3.0 1080P。通过火山引擎即梦AI API生成视频（图生视频-首尾帧模式）。 触发词：即梦、极梦、视频生成、图生视频、首尾帧、火山引擎视频. It is an AI Agent Skill for Claude Code / OpenClaw, with 40 downloads so far.
How do I install Jimeng Video Generator?
Run "/install stitch-jimeng-video" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Jimeng Video Generator free?
Yes, Jimeng Video Generator is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Jimeng Video Generator support?
Jimeng Video Generator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Jimeng Video Generator?
It is built and maintained by sdT328606 (@sdt328606); the current version is v1.0.0.
More Skills