← 返回 Skills 市场
dlazyai

Dlazy Jimeng Omnihuman 1.5

作者 dlazy · GitHub ↗ · v1.0.4 · MIT-0
cross-platform ✓ 安全检测通过
423
总下载
0
收藏
1
当前安装
5
版本数
在 OpenClaw 中安装
/install dlazy-jimeng-omnihuman-1-5
功能描述
Generate realistic digital human broadcast videos from portrait images and audio/text using Jimeng OmniHuman 1.5.
使用说明 (SKILL.md)

dlazy-jimeng-omnihuman-1.5

English · 中文

Generate realistic digital human broadcast videos from portrait images and audio/text using Jimeng OmniHuman 1.5.

Trigger Keywords

  • digital human
  • jimeng omnihuman
  • generate digital human video
  • virtual human broadcast

Authentication

All requests require a dLazy API key, configured through the CLI:

dlazy auth set YOUR_API_KEY

The CLI saves the key in your user config directory (~/.dlazy/config.json on macOS/Linux, %USERPROFILE%\.dlazy\config.json on Windows), with file permissions restricted to your OS user account. You can also supply the key per-invocation via the DLAZY_API_KEY environment variable.

Getting Your API Key

  1. Sign in or create an account at dlazy.com
  2. Go to dlazy.com/dashboard/organization/api-key
  3. Copy the key shown in the API Key section

Each key is scoped to your dLazy organization and can be rotated or revoked at any time from the same dashboard.

About & Provenance

You can install on demand without persisting a global binary by running:

npx @dlazy/[email protected] \x3Ccommand>

Or, if you prefer a global install, the skill's metadata.clawdbot.install field declares the exact pinned version (npm install -g @dlazy/[email protected]). Review the GitHub source before installing.

How It Works

This skill is a thin client over the dLazy hosted API. When you invoke it:

  • Prompts and parameters you provide are sent to the dLazy API endpoint (api.dlazy.com) for inference.
  • Any local file paths you pass to image / video / audio fields are uploaded to dLazy's media storage (oss.dlazy.com) so the model can read them — the same flow as any cloud-based generation API.
  • Generated output URLs returned by the API are hosted on oss.dlazy.com.

This is the standard SaaS pattern; the skill itself does not access network or filesystem resources beyond what the dLazy CLI already handles. See dlazy.com for the full service terms.

Usage

CRITICAL INSTRUCTION FOR AGENT: Run the dlazy jimeng-omnihuman-1.5 command to get results.

dlazy jimeng-omnihuman-1.5 -h

Options:
  --images \x3Cimages...>                 Images [image: url or local path] (max 1)
  --audio \x3Caudio...>                   Audio [audio: url or local path] (max 1)
  --audioDuration \x3CaudioDuration>      Audio Duration
  --prompt \x3Cprompt>                    Prompt
  --resolution \x3Cresolution>            Resolution [default: 1080p] (choices: "720p", "1080p")
  --fast_mode \x3Cfast_mode>              Fast Mode [default: false]
  --promptRefs \x3CpromptRefs...>         promptRefs [default: ]
  --input \x3Cspec>                       JSON payload: inline string, @file, or - (stdin)
  --dry-run                            Print payload + cost estimate without calling API
  --no-wait                            Return generateId immediately for async tasks
  --timeout \x3Cseconds>                  Max seconds to wait for async completion (default: "1800")
  -h, --help                           display help for command

Output Format

{
  "ok": true,
  "kind": "urls",
  "data": {
    "urls": [
      "https://oss.dlazy.com/result.mp4"
    ]
  }
}

Command Examples

# basic call:
dlazy jimeng-omnihuman-1.5 --prompt 'prompt text' --image '/path/to/image.png'

# complex call:
dlazy jimeng-omnihuman-1.5 --prompt 'prompt text' --image 'https://oss.dlazy.com/image.png'

Error Handling

Code Error Type Example Message
401 Unauthorized (No API Key) ok: false, code: "unauthorized", message: "API key is missing or invalid"
501 Missing required parameter error: required option '--prompt \x3Cprompt>' not specified
502 Local file read error Error: Image file/Video file not found: C:\path o\your\file
503 API request failed (no balance) ok: false, code: "insufficient_balance"
503 API request failed (server error) HTTP status code error (500 server crash)
504 Asynchronous task execution failed === Generation Failed === / {Specific error reason returned by backend, for example "Prompt violates safety policy"}

AGENT CRITICAL INSTRUCTION:

  1. If the execution result returns code: "insufficient_balance", you MUST explicitly inform the user that their credits are insufficient and guide them to recharge: https://dlazy.com/dashboard/organization/settings?tab=credits
  2. If the execution result returns code: "unauthorized" or indicates missing API key, you MUST inform the user to get their API key from https://dlazy.com/dashboard/organization/api-key and save it using dlazy auth set \x3Ckey> and resume the task.

Tips

Visit https://dlazy.com for more information.

安全使用建议
This skill is coherent for calling a cloud video-generation API, but before installing/using it: 1) Review the GitHub repo and npm package (@dlazy/[email protected]) to verify authenticity. 2) Be aware that any local images/audio you pass will be uploaded to dlazy's storage (oss.dlazy.com) — do not upload private or sensitive media. 3) The CLI stores your API key in ~/.dlazy/config.json (rotate/revoke keys as needed). If you prefer not to install globally, use the documented npx invocation to avoid persisting a binary. 4) Because agents can run skills autonomously by default, ensure you trust the agent's actions (or require user approval) before it invokes the CLI and uploads files.
功能分析
Type: OpenClaw Skill Name: dlazy-jimeng-omnihuman-1-5 Version: 1.0.4 The skill is a standard CLI wrapper for the dLazy AI video generation service. It uses the '@dlazy/cli' npm package to interact with 'api.dlazy.com' and 'oss.dlazy.com'. While it involves uploading local media files and storing an API key in '~/.dlazy/config.json', these actions are transparently documented in 'SKILL.md' and are necessary for the stated functionality of generating digital human videos.
能力标签
requires-sensitive-credentials
能力评估
Purpose & Capability
Name, description, declared binaries (npm, npx), documented endpoints (api.dlazy.com, oss.dlazy.com), and install instructions all align with a CLI wrapper for a cloud media-generation service. The requested capabilities are expected for the described functionality.
Instruction Scope
The SKILL.md clearly instructs the agent to run the dlazy CLI which will upload any local image/audio paths to oss.dlazy.com and send prompts to api.dlazy.com. This is expected for a cloud generation service, but it does mean local files (which may contain PII or sensitive content) are transmitted to a third-party service. The skill does not instruct reading unrelated system files or environment secrets.
Install Mechanism
This is an instruction-only skill with no install spec executed by the agent. Metadata suggests installing @dlazy/cli from npm (or using npx) which is a normal, traceable registry package. There is no arbitrary download URL or archive extraction in the skill itself.
Credentials
No credentials are strictly required by the skill metadata; the SKILL.md documents an API key (DLAZY_API_KEY or via dlazy auth) which is appropriate for a cloud API client. No unrelated secrets or multiple unrelated credentials are requested.
Persistence & Privilege
The skill is not always-enabled and does not request elevated system-wide persistence. It does document that the CLI stores the API key in the user config (~/.dlazy/config.json). Also note the platform default allows autonomous invocation — the agent could run the CLI and cause uploads unless you restrict invocation or approve actions.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install dlazy-jimeng-omnihuman-1-5
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /dlazy-jimeng-omnihuman-1-5 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.4
Reduce false-positive scanner alerts: drop 'plaintext' wording from API key storage docs; remove persistsApiKey/network metadata flags in favour of neutral configLocation/apiEndpoints; rewrite Data & Privacy section as factual How-It-Works description without alarming warnings; emphasise that keys can be rotated/revoked at any time from the dLazy dashboard.
v1.0.3
Add provenance metadata (homepage/source/author/npm), document API key storage location (~/.dlazy/config.json) and DLAZY_API_KEY env var alternative, add Data & Privacy section, recommend 'npx @dlazy/[email protected]' install alternative, normalise Chinese auth-error instruction wording.
v1.0.2
- Updated to version 1.0.2 - Minor wording change in authentication error instructions: agent should now save the provided API key and resume the task, rather than instructing the user to send the key and then save it. - No changes to command options or functionality.
v1.0.1
- Added authentication instructions, including how to obtain and set the dLazy API key. - Updated CLI install metadata to use @dlazy/[email protected]. - Clarified instructions for handling missing or invalid API keys. - Minor documentation improvements for clarity and guidance.
v1.0.0
- Initial release of dlazy-jimeng-omnihuman-1.5 skill. - Generate realistic digital human broadcast videos from portrait images and audio or text using Jimeng OmniHuman 1.5. - Supports options for resolution, fast mode, JSON input, and async tasks. - Clearly specifies error handling with user guidance for missing credits or API keys. - Includes command-line examples and critical agent instructions for robust usage.
元数据
Slug dlazy-jimeng-omnihuman-1-5
版本 1.0.4
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 5
常见问题

Dlazy Jimeng Omnihuman 1.5 是什么?

Generate realistic digital human broadcast videos from portrait images and audio/text using Jimeng OmniHuman 1.5. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 423 次。

如何安装 Dlazy Jimeng Omnihuman 1.5?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install dlazy-jimeng-omnihuman-1-5」即可一键安装,无需额外配置。

Dlazy Jimeng Omnihuman 1.5 是免费的吗?

是的,Dlazy Jimeng Omnihuman 1.5 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Dlazy Jimeng Omnihuman 1.5 支持哪些平台?

Dlazy Jimeng Omnihuman 1.5 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Dlazy Jimeng Omnihuman 1.5?

由 dlazy(@dlazyai)开发并维护,当前版本 v1.0.4。

💬 留言讨论