← Back to Skills Marketplace
github-gamma

Jiuma AI Video Generation (Free)

by github-gamma · GitHub ↗ · v1.0.8 · MIT-0
cross-platform ✓ Security Clean
297
Downloads
2
Stars
0
Active Installs
8
Versions
Install in OpenClaw
/install jiuma-ai-video-generation
Description
免费的ai视频生成创作平台(Video Generation Skill),支持生成视频、图片、声音、视频动作模仿、视频人物替换等等。九马AI官网:https://www.jiuma.com
README (SKILL.md)

📁 文件结构

scripts/
├── submit_generation_task.py        # 提交生成任务🚀
├── task_result.py        # 结果查询工具📊
├── upload_file.py         # 文件上传工具
└── auth.py          # 获取token

🚀 快速开始(推荐)

重要:注意用户的操作系统,需要使用适配用户的操作系统的类型的命令行代码,若是windows,请改成绝对路径调用

0. 检查授权状态

python ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/check_auth_status.py

1. 一键授权(已授权则跳过)

# 默认授权方法
python ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/auth.py --identification_code="\x3C身份标识码(若无留空)>" --channel="\x3C消息渠道(如:openclaw-weixin、webchat等)>"

#强制重新授权
python ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/auth.py --identification_code="" --channel="\x3C消息渠道(如:openclaw-weixin、webchat等)>" --force

2. 生成视频(提交生成任务)

python ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/submit_generation_task.py --task_params="{'reference_urls': ['https://picsum.photos/800/450'], 'prompt': '自然', 'duration': 3, 'task_type': 'wan2.6'}"

提交生成任务时,图片、视频、音频等等资源文件必须先上传到平台获得url,不得直接使用本地路径提交生成 task_type为枚举类型,必须严格与下表严格对应,否则无法生成

3. 查询任务结果

python ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/task_result.py  --task_id=\x3C任务ID>

4. 上传本地文件(获得url)

python ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/upload_file.py --file_path=\x3C文件路径>

支持的任务类型(task_type)

task_type(必须严格对应,枚举类型) 名称 功能描述 任务参数 提示词要求 提示词示例
"wan2.6(ref2video)" 万象2.6模型 图像生成视频(可控制说话、动作、运镜、画面内容) reference_urls:array,参考图片或者视频的url;prompt:string,动作描述+画面描述+运镜描述+说话内容;duration:int,视频秒数,取值2~10,最大10秒,最小2秒 同一段提示词里面包含:动作描述+画面描述+运镜描述+说话内容,提示词通过“character1、character2”这类标识引用角色。角色顺序与 reference_urls 数组一一对应,即第 1 个 URL 为 character1,第 2 个为 character2,依此类推。 character2 坐在靠窗的椅子上,手持 character3,在 character4 旁演奏一首舒缓的美国乡村民谣。character1 对character2开口说道:“听起来不错”。
"wan2.6(text2video)" 万象2.6文生视频 模型可自动进行分镜切换,例如从全景切换到特写,适合制作MV等场景。 prompt:string,动作描述+画面描述+运镜描述+说话内容;duration:int,视频秒数,取值2~10,最大15秒,最小2秒,请勿超出时长 同一段提示词里面包含:动作描述+画面描述+运镜描述+说话内容 一段紧张刺激的侦探追查故事,展现电影级叙事能力。第1个镜头[0-3秒] 全景:雨夜的纽约街头,霓虹灯闪烁,一位身穿黑色风衣的侦探快步行走。 第2个镜头[3-6秒] 中景:侦探进入一栋老旧建筑,雨水打湿了他的外套,门在他身后缓缓关闭。 第3个镜头[6-9秒] 特写:侦探的眼神坚毅专注,远处传来警笛声,他微微皱眉思考。 第4个镜头[9-12秒] 中景:侦探在昏暗走廊中小心前行,手电筒照亮前方。 第5个镜头[12-15秒] 特写:侦探发现关键线索,脸上露出恍然大悟的表情。
"action_imitation_user_background_onetoall(prompt)" 动作模仿(用户特别要求适配身高时使用) 自动适配角色的身高,特别是针对小朋友、卡通角色等等动作模仿 image_url:url,角色图片;video_url,url,参考动作视频;prompt,text,动作提示词 一个角色在跳舞
"action_imitation_user_background(prompt)" 动作模仿(常用) 图片中的人物模仿视频中的角色的动作 image_url:url,角色图片;video_url,url,参考动作视频;prompt,text,动作提示词 一个角色在跳舞
"action_imitation_video_backgound(prompt)" 人物替换/角色替换 把视频中的角色换成图片中的角色 image_url:url,角色图片;video_url,url,参考动作视频;prompt,text,动作提示词 一个角色在跳舞

注意:task_type需要严格对应,否则无法制作

🎬 完整示例:制作短视频

重要:注意用户的操作系统,需要使用适配用户的操作系统的类型的命令行代码,若是windows,请改成绝对路径调用

步骤0:检测授权状态

python ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/check_auth_status.py

重要:注意用户的操作系统,需要使用适配用户的操作系统的类型的命令行代码,若是windows,请改成绝对路径调用

步骤1:授权(已授权则跳过)

python ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/auth.py --identification_code="58fe87fb26b579b309ad782afb7a157155d338f31ad2a26419ae8550cda16747" --channel="openclaw-weixin"

重要:注意用户的操作系统,需要使用适配用户的操作系统的类型的命令行代码,若是windows,请改成绝对路径调用

步骤2:生成分镜

# 分镜1:开场特效(3秒)
python ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/submit_generation_task.py --task_params="{'reference_urls': ['https://picsum.photos/800/450'], 'prompt': '纯黑背景,白色发光文字快速闪现,科技感光晕', 'duration': 3, 'task_type': 'wan2.6'}"

# 分镜2:情感铺垫(9秒)
python ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/submit_generation_task.py --task_params="{'reference_urls': ['https://picsum.photos/800/450'], 'prompt': '年轻人拿着泛黄老照片,表情落寞,怀旧色调', 'duration': 9, 'task_type': 'wan2.6'}"

# 分镜3:AI处理(10秒)
python ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/submit_generation_task.py --task_params="{'reference_urls': ['https://picsum.photos/800/450'], 'prompt': '照片被AI扫描处理,科技感特效,代码流动画', 'duration': 10, 'task_type': 'wan2.6'}"

重要:注意用户的操作系统,需要使用适配用户的操作系统的类型的命令行代码,若是windows,请改成绝对路径调用

步骤3:检查进度

python ~/.openclaw/workspace/skills/jiuma-ai-video-generation/scripts/task_result.py  --task_id=ai-69cf39df3e61e1280

📄 输出说明

任务结果

JSON格式输出,关键字段:

  • task_id: 任务唯一标识
  • task_status: 任务状态(PENDINGRUNNINGSUCCEEDEDFAILEDCANCELED
  • video_url: 生成的视频地址(任务成功时)
  • image_url: 生成的图片地址(任务成功时)

上传结果

  • file_url: 上传的文件地址

🏆 总结

改进版技能优势:

  1. 快速上手 - 新用户5分钟内开始生成视频
  2. 稳定运行 - 减少授权相关问题
  3. 方便管理 - 随时查看任务状态
  4. 批量处理 - 支持多任务工作流

重要:注意用户的操作系统,需要使用适配用户的操作系统的类型的命令行代码 💡 提示: 首次使用建议运行 python ~/.openclaw/workspace/skills/jiuma/scripts/auth.py --identification_code="\x3C身份标识码(会话历史中无则留空)>" --channel="\x3C消息渠道(如:openclaw-weixin、webchat等)>" 完成授权,后续使用会非常顺畅!

Installation

pip install keyring
pip install keyrings.alt
Usage Guidance
This skill appears coherent for connecting to Jiuma's video-generation API. Before installing or running: (1) verify that api.jiuma.com is the intended official endpoint for the service you expect; (2) be aware the scripts will store an API bearer token in your system keyring — revoke it at the provider if you stop using the skill; (3) only upload local files you trust and explicitly provide as arguments (the skill will read any file path you pass to upload_file.py); (4) run the scripts in a trusted or isolated environment if you are concerned about data leakage; (5) the skill suggests installing keyring via pip — prefer creating a virtual environment before installing Python packages. If you need higher assurance, ask the skill author for documentation of the API and token lifecycle (how to revoke tokens) or run the code in a sandbox first.
Capability Analysis
Type: OpenClaw Skill Name: jiuma-ai-video-generation Version: 1.0.8 The skill bundle provides a functional interface for the Jiuma AI video generation platform. It includes scripts for secure authentication using the system keyring (auth.py), file uploading (upload_file.py), and task management (submit_generation_task.py, task_result.py), all communicating with the legitimate domain api.jiuma.com. The code follows standard security practices for local secret storage and lacks any indicators of malicious intent, data exfiltration, or harmful prompt injection.
Capability Assessment
Purpose & Capability
Name/description advertise AI video generation and included scripts (auth, upload, submit task, check status, result) interact exclusively with https://api.jiuma.com endpoints to authorize, upload media, submit generation tasks, and query results. Required capabilities (keyring token storage, HTTP calls, file upload) align with the stated purpose.
Instruction Scope
Runtime instructions tell the user/agent to run the provided Python scripts from the skill workspace. The scripts will: (a) read and write a token in the system keyring, (b) open and stream user-supplied local files for upload (upload_file.py uses open(os.path.expanduser(file_path),'rb')), and (c) send requests to the jiuma API. This behavior is expected for an upload-and-submit client, but note that any local file path passed to upload_file.py will be read and uploaded to the external service — only supply files you intend to upload.
Install Mechanism
No automated install spec; SKILL.md recommends installing keyring and keyrings.alt via pip. There are no downloads from untrusted URLs or archive extraction steps. The install instructions are minimal and appropriate for the code.
Credentials
The skill requests no environment variables or external credentials. It uses the system keyring to persist a service token (key 'jiuma_ai' / 'authorized_token'), which is proportional to needing a bearer token for the provider API. Network calls are limited to api.jiuma.com which matches the skill's claimed backend.
Persistence & Privilege
The skill is not always-enabled and does not modify other skills or global agent settings. Its only persistent effect is storing a service token in the user's system keyring, which is a reasonable design choice for an API client but worth noting.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install jiuma-ai-video-generation
  3. After installation, invoke the skill by name or use /jiuma-ai-video-generation
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.8
- Updated all command-line code examples to use the correct skill folder name jiuma-ai-video-generation. - Added repeated reminders to adapt command-line path syntax based on the user's operating system, especially for Windows users. - Revised "任务类型(task_type)" descriptions and examples, including new naming such as "wan2.6(ref2video)" and "wan2.6(text2video)". - Improved clarity and accuracy in task parameter explanations and usage instructions. - Added and highlighted multiple "重要" (Important) sections to prevent path and OS-related errors for end-users.
v1.0.7
Major update: Completely refactored video generation workflow with modular scripts and improved authorization flow. - Split main script into modular tools: task submission, result querying, uploading, and authorization. - Added new scripts for auth, check auth status, task submission, result polling, and file upload. - Updated SKILL.md with detailed modern workflow, task_type documentation, and step-by-step usage examples. - Removed legacy scripts and previous usage instructions. - Enhanced result and upload output formats and clarified parameter requirements.
v1.0.6
- Skill name updated from "jiuma" to "jiuma-ai-video-generation" - Script and usage examples now use the new directory and naming convention: jiuma-ai-video-generation - Added an Installation section with instructions to install "keyring" - No changes were made to the main workflow or API parameters - Channel/media handling instructions unchanged
v1.0.5
Version 1.0.5 - Added _meta.json metadata file. - Clarified and updated the process for sending media to the openclaw-weixin channel. - Improved instructions on delivering QR code images for authorization. - Updated description to emphasize video generation platform focus. - No changes to core functionality; workflow and command usage remain the same.
v1.0.4
- 增加了技能描述,明确支持上传图片生成数字人说话视频,并提供九马AI官网链接。 - 扩充了平台介绍,说明用户可通过上传图片生成数字人口播视频,九马AI提供算力支持。 - 其它功能与使用方式保持不变。
v1.0.3
- Updated skill description for clarity and brevity. - Clarified and adjusted example commands to use explicit absolute paths instead of "{baseDir}" and “~”. - Added instructions to always replace “~” with a full absolute path when running scripts. - Introduced usage of the --channel parameter for session/channel context, with example values. - Removed outdated website help instructions from the description. - Improved formatting and command examples for easier reference.
v1.0.2
- 更新描述,明确支持通过上传图片生成数字人说话视频 - 增加“九马AI提供算力支持”与九马官网帮助链接 - 其他功能和使用方式未变,接口和示例保持一致
v1.0.0
jiuma-ai-video-generation 1.0.0 - Initial release of the skill. - Supports submitting asynchronous video generation tasks via API. - Enables file upload (images, videos, sounds) to the platform and returns resource URLs. - Provides clear usage instructions for command-line execution, including parameter passing rules. - Implements status polling and sends generated video files to users upon task completion. - Includes detailed documentation on workflow, parameters, and output interpretation.
Metadata
Slug jiuma-ai-video-generation
Version 1.0.8
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 8
Frequently Asked Questions

What is Jiuma AI Video Generation (Free)?

免费的ai视频生成创作平台(Video Generation Skill),支持生成视频、图片、声音、视频动作模仿、视频人物替换等等。九马AI官网:https://www.jiuma.com. It is an AI Agent Skill for Claude Code / OpenClaw, with 297 downloads so far.

How do I install Jiuma AI Video Generation (Free)?

Run "/install jiuma-ai-video-generation" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Jiuma AI Video Generation (Free) free?

Yes, Jiuma AI Video Generation (Free) is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Jiuma AI Video Generation (Free) support?

Jiuma AI Video Generation (Free) is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Jiuma AI Video Generation (Free)?

It is built and maintained by github-gamma (@github-gamma); the current version is v1.0.8.

💬 Comments