Turn a static character image and prompt into an action video through a hosted CLI workflow.
Design & media
数字人视频 即梦 OmniHuman 1.5
Turn one portrait plus audio or a text prompt into a digital-human broadcast video with Jimeng OmniHuman 1.5.
What it does
Generate a digital-human broadcast video with Jimeng OmniHuman 1.5 from up to one portrait image and one audio file, with a text prompt available for direction or text input. The CLI accepts local paths or URLs, supports 720p or 1080p, fast mode, dry-run cost estimates, and asynchronous execution, then returns hosted output URLs.
When to use it
- Presenter videos from a portrait and narration
- Virtual-human announcements from scripted text
- 720p or 1080p digital-human broadcasts
- Asynchronous media-generation workflows
The skill document
数字人视频 即梦 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. The recommended way to authenticate is:
dlazy login
This runs a device-code flow (also works in remote shells) and automatically saves your API key to the local CLI config — no manual copy/paste required.
Alternative: Set the Key Manually
If you already have an API key, you can save it directly:
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 Manually
- Sign in or create an account at dlazy.com
- Go to dlazy.com/dashboard/organization/api-key
- 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
- CLI source code: github.com/dlazyai/cli
- Maintainer: dlazyai
- npm package:
@dlazy/cli(pinned to1.2.3in this skill's install spec) - Homepage: dlazy.com
You can install on demand without persisting a global binary by running:
npx @dlazy/cli@1.2.3
Or, if you prefer a global install, the skill's metadata.clawdbot.install field declares the exact pinned version (npm install -g @dlazy/cli@1.2.3). 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 (
files.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
files.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 [images...] Images [image: url or local path] (max 1)
--audio [audio...] Audio [audio: url or local path] (max 1)
--prompt [prompt] Prompt
--resolution [resolution] Resolution [default: 1080p] (choices: "720p", "1080p")
--fast_mode [fast_mode] Fast Mode [default: false]
--dry-run Print payload + cost estimate without calling API
--no-wait Return generateId immediately for async tasks
--timeout Max seconds to wait for async completion (default: "1800")
-h, --help display help for command
Any flag also accepts pipe references —
-(auto-pick from upstream stdin),@N(n-th output),@N.path(jsonpath into output),@*(all primary values),@stdin/@stdin:path(whole envelope). Seedlazy --helpfor details.
Output Format
{
"ok": true,
"result": {
"tool": "jimeng-omnihuman-1.5",
"modelId": "jimeng-omnihuman-1.5",
"outputs": [
{
"type": "image",
"id": "o_xxxxxxxx",
"url": "https://files.dlazy.com/result.png",
"mimeType": "image/png"
}
]
}
}
Async tasks (when
--no-waitis passed) returnoutputs: []and atask: { generateId, status }field instead. Usedlazy status --waitto poll.
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://files.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 ' not specified |
| 502 | Local file read error | Error: Image file/Video file not found: C:\path\to\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:
- 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- 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 usingdlazy auth setand resume the task.
Tips
Visit https://dlazy.com for more information.
Questions people ask
- What inputs can I provide?
- You can submit up to one image and one audio file, each as a local path or URL, plus a text prompt. Local media is uploaded to the hosted service so the model can process it.
- Can I choose the output resolution or run asynchronously?
- Yes. Resolution can be set to 720p or 1080p, and fast mode is available. With no-wait enabled, the command returns a generation ID that can be polled for completion.
- What authentication is required?
- A dLazy API key is required. You can authenticate through the CLI device-code flow, save a key manually, or provide it per invocation with the DLAZY_API_KEY environment variable.
Related skills
Turn a single first-frame image and prompt into a 5- or 10-second Jimeng-generated video.
Turn first and last frame images into a 5- or 10-second Jimeng transition video.
Turn text prompts and optional reference images into hosted Jimeng image outputs.
Generate Kling V3 Omni videos from prompts and optional image, subject, or video references.
Generate Seedream 4.5 images from prompts or up to 10 reference images at 2K or 4K resolution.