Generate 4–12 second videos from prompts, media references, or first and last frames.
Design & media
视频生成 Seedance 2.0
Generate 4–15 second videos from prompts, media references, or first and last frames.
What it does
Generate videos with Seedance 2.0 from a text prompt, multimodal image/video/audio references, or first and last frames. Configure 480p, 720p, or 1080p output, six aspect ratios, 4–15 second duration, and audio generation. The CLI uploads local references to the hosted API and returns hosted output URLs or an asynchronous task ID.
When to use it
- Text-to-video generation
- Image, video, and audio referenced clips
- First-and-last-frame video creation
- Short videos for multiple aspect ratios
The skill document
视频生成 Seedance 2.0
English · 中文
ByteDance's latest video generation model. Supports multi-modal reference (images, video, audio) to generate videos, as well as first/last frame and text-to-video modes.
Trigger Keywords
- seedance-2.0
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:
Execute dlazy seedance-2.0 to get the result.
dlazy seedance-2.0 -h
Options:
--prompt [prompt] Prompt
--generation_mode [generation_mode] Generation Mode(components=Components; frames=Frames) [default: components] (choices: "components", "frames")
--images [images...] Images [image: url or local path] (max 9) [only when !(generation_mode="frames")]
--videos [videos...] Videos [video: url or local path] (max 3) [only when !(generation_mode="frames")]
--audios [audios...] Audios [audio: url or local path] (max 3) [only when !(generation_mode="frames")]
--firstFrame [firstFrame] First Frame [image: url or local path] [only when generation_mode="frames"]
--lastFrame [lastFrame] Last Frame [image: url or local path] [only when generation_mode="frames"]
--resolution [resolution] Resolution [default: 720p] (choices: "480p", "720p", "1080p")
--ratio [ratio] Aspect Ratio [default: 16:9] (choices: "21:9", "16:9", "4:3", "1:1", "3:4", "9:16")
--duration [duration] Duration (s) [default: 5] (choices: "4", "5", "6", "7", "8", "9", "10", "11", "12", "13", "14", "15")
--generate_audio [generate_audio] Generate Audio [default: true]
--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": "seedance-2.0",
"modelId": "seedance-2.0",
"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.
Examples
dlazy seedance-2.0 --prompt 'prompt content'
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
- Which generation modes and references are supported?
- Components mode accepts up to 9 images, 3 videos, and 3 audio files alongside a prompt. Frames mode instead accepts a first frame and last frame; references may be URLs or local paths.
- What video settings can I control?
- Choose 480p, 720p, or 1080p resolution; 21:9, 16:9, 4:3, 1:1, 3:4, or 9:16 aspect ratio; and a duration from 4 to 15 seconds. Audio generation is enabled by default and can be configured.
- How are authentication and asynchronous jobs handled?
- A dLazy API key is required and can be saved with `dlazy login` or `dlazy auth set`. Use `--no-wait` to receive a generation ID immediately, then poll it with `dlazy status --wait`.
Related skills
Create multi-minute, scripted 720p videos with voices, music, lip sync, and editing from one prompt.
Generate images from text or up to 10 reference images with Doubao Seedream 5.0 Lite.
Generate videos from prompts and media with automatic selection among supported dLazy CLI models.
Generate Wan 2.7 videos from text, reference media, or specified first and last frames.
Turn a single first-frame image and prompt into a 5- or 10-second Jimeng-generated video.