Agent Skills › opensquilla/opensquilla › seedance-2-prompt

seedance-2-prompt

GitHub

基于Seedance 2.0的AI视频生成技能，支持OpenRouter、火山引擎和BytePlus后端。接受结构化英文提示词及可选参考图，生成3-15秒MP4短视频，适用于分镜制作或 cinematic shot 需求。

src/opensquilla/skills/bundled/seedance-2-prompt/SKILL.md opensquilla/opensquilla

Trigger Scenarios

用户请求生成AI视频片段提及分镜视频提及seedance 要求从提示词+帧生成短电影镜头

Install

npx skills add opensquilla/opensquilla --skill seedance-2-prompt -g -y

More Options

Non-standard path

npx skills add https://github.com/opensquilla/opensquilla/tree/main/src/opensquilla/skills/bundled/seedance-2-prompt -g -y

Use without installing

npx skills use opensquilla/opensquilla@seedance-2-prompt

指定 Agent (Claude Code)

npx skills add opensquilla/opensquilla --skill seedance-2-prompt -a claude-code -g -y

安装 repo 全部 skill

npx skills add opensquilla/opensquilla --all -g -y

预览 repo 内 skill

npx skills add opensquilla/opensquilla --list

SKILL.md

Frontmatter

{
    "name": "seedance-2-prompt",
    "metadata": {
        "opensquilla": {
            "risk": "medium",
            "requires": {
                "envAny": [
                    "OPENROUTER_API_KEY",
                    "ARK_API_KEY"
                ],
                "anyBins": [
                    "python",
                    "python3"
                ]
            },
            "capabilities": [
                "network-read",
                "filesystem-write"
            ]
        }
    },
    "entrypoint": {
        "args": [
            "--prompt",
            "{{ with.prompt }}",
            "--filename",
            "{{ with.filename }}",
            "--provider",
            "{{ with.provider | default('openrouter') }}",
            "--aspect-ratio",
            "{{ with.aspect_ratio | default('9:16') }}",
            "--duration",
            "{{ with.duration | default(5) }}",
            "--resolution",
            "{{ with.resolution | default('720p') }}",
            "--model",
            "{{ with.model | default('') }}",
            "--input-image",
            "{{ with.input_image | default('') }}",
            "--input-reference",
            "{{ with.input_reference | default('') }}",
            "--input-reference",
            "{{ with.input_reference_2 | default('') }}",
            "--max-retries",
            "{{ with.max_retries | default(0) }}"
        ],
        "parse": "text",
        "command": "python {baseDir}\/scripts\/generate_video.py",
        "timeout": 1500
    },
    "provenance": {
        "origin": "clawhub-mit0",
        "license": "MIT-0",
        "upstream_url": "https:\/\/clawhub.ai\/dandysuper\/seedance-2-prompt-engineering-skill",
        "maintained_by": "OpenSquilla",
        "modifications": "Added scripts\/generate_video.py with dual-provider support: OpenRouter async \/videos API and Volcengine ARK \/ BytePlus ModelArk \/contents\/generations\/tasks. References kept from upstream.",
        "upstream_version": "2.0.0"
    },
    "description": "Render a single 3-15s video clip via Seedance 2.0. Supports two backends: OpenRouter (default, model bytedance\/seedance-2.0) and the official Volcengine ARK \/ BytePlus ModelArk endpoint (model doubao-seedance-2-0-260128 \/ dreamina-seedance-2-0-260128). Accepts a structured English video prompt, optional first-frame image, and optional identity\/style reference image. Trigger when the user asks for AI video clip generation, 分镜视频, seedance, or wants a short cinematic shot from a prompt + frame."
}

seedance-2-prompt — Seedance 2.0 video clip generator (dual backend)

Submits a Seedance 2.0 generation job and downloads the resulting MP4. Two backends share one CLI, picked via with.provider:

`with.provider`	Endpoint	Auth env	Default model
`openrouter` (default)	`https://openrouter.ai/api/v1/videos`	`OPENROUTER_API_KEY`	`bytedance/seedance-2.0`
`volcengine` (CN)	`https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks`	`ARK_API_KEY` (or `VOLC_ARK_API_KEY`)	`doubao-seedance-2-0-260128`
`byteplus` (intl)	`https://ark.ap-southeast.bytepluses.com/api/v3/contents/generations/tasks`	`ARK_API_KEY` (or `BYTEPLUS_API_KEY`)	`dreamina-seedance-2-0-260128`

Both flavours follow submit-then-poll, but differ in request shape (OpenRouter uses a flat prompt field; ARK packs everything into a content[] array), polling URL (OpenRouter returns polling_url; ARK gets id and you construct /contents/generations/tasks/{id}), the terminal-success status (completed vs succeeded), and where the final MP4 URL sits (top-level unsigned_urls[0] vs content.video_url). This script normalises both into a single Python contract.

Inputs (`with:`)

key	required	default	notes
`prompt`	yes	—	Structured English video prompt (use this skill's recipes).
`filename`	yes	—	Output `.mp4` path.
`provider`	no	`openrouter`	`openrouter`, `volcengine`, or `byteplus`.
`aspect_ratio`	no	`9:16`	`9:16`, `16:9`, `1:1`, `4:3`, `3:4`, `21:9`.
`duration`	no	`5`	Seconds, 3-15. Provider enforces 4-15 typically.
`resolution`	no	`720p`	`480p`, `720p`, `1080p`. Ignored by OpenRouter.
`model`	no	provider default	Override model id. Empty means use provider default.
`input_image`	no	`""`	Strict first-frame path. If set, video starts from this image.
`input_reference`	no	`""`	Primary soft identity/style anchor path. Used only when `input_image` is empty. Same anchor passed across shots locks the character.
`input_reference_2`	no	`""`	Optional second reference (e.g. per-shot scene composition). Forwarded as a second `--input-reference` so the underlying provider sees both. Empty strings are filtered out before the API call.
`max_retries`	no	`0`	Extra retries on transient submit/poll/download failures or non-success terminal status. `0` = single attempt; `2` = up to 3 total attempts with exponential backoff (2s, 4s, 8s capped at 15s). Set this on flows that fall back to a still-image animator on final failure.

input_image vs input_reference — input_image becomes the literal first frame. input_reference is a softer style + identity hint the model uses without locking the frame. For multi-shot drama, pass the same input_reference to every shot; pass input_image only when you want a specific opening frame.

Prompt rules (from upstream + OpenSquilla tightening)

One major action per 3-5s segment. Don't pack multiple motions.
Identity continuity — repeat the main character's full description in every shot's prompt.
Specific over poetic — "a young woman in a red trench coat walks through rain-soaked neon streets" >> "a woman walking".
Negative constraints inline — append no watermark, no logo, no subtitles, no on-screen text.
IP-safe — invent original character/brand names.
Aspect ratio explicit — append aspect_ratio: 9:16.

See references/recipes.md, references/modes-and-recipes.md, references/camera-and-styles.md for the upstream playbook.

Auth

openrouter provider API-key resolution order:
1. --api-key CLI argument
2. OPENROUTER_API_KEY env var
3. OPENSQUILLA_LLM_API_KEY env var, only when the effective OpenSquilla LLM provider resolves to openrouter
4. llm.api_key or llm.api_key_env from the selected OpenSquilla TOML config. Config discovery matches GatewayConfig.load: explicit OPENSQUILLA_GATEWAY_CONFIG_PATH first; otherwise ./opensquilla.toml, then default_opensquilla_home()/config.toml. OPENSQUILLA_STATE_DIR changes default_opensquilla_home(), so a state-dir profile does not fall through to ~/.opensquilla. Config-file credentials are consumed only when the selected config's llm.provider is openrouter or omitted.
volcengine / byteplus provider reads ARK_API_KEY (with provider- specific fallbacks VOLC_ARK_API_KEY / BYTEPLUS_API_KEY). No config-file fallback for these — the OpenSquilla [llm] config describes the agent's selected LLM provider, not ARK / BytePlus video credentials.
All three send the key as Authorization: Bearer <key>.
For OpenRouter the same bearer is also added when downloading the resulting unsigned_urls[0]. Volcengine returns pre-signed object store URLs that reject extra headers, so the downloader strips Authorization for non-OpenRouter hosts.

Output

Prints the absolute path of the saved .mp4 on stdout. Non-zero exit on any error; stderr carries the diagnostic.

Cost / latency

OpenRouter bytedance/seedance-2.0 5s @ 9:16 720p: ≈30-90s wall, ≈$0.76.
Volcengine official 5s 1080p: ≈30-120s wall, ≈$0.93.
Volcengine doubao-seedance-2-0-fast-260128: roughly half cost and faster.
The returned unsigned_urls / content.video_url expire 24 hours after success on the Volcengine path — this script downloads them before that window so the local mp4 is durable.

Multi-segment workflows (>15s)

Generate segments individually with duration ≤ 15, ending each on a stable hand-off frame. Stitch with the video-merger skill. See references/modes-and-recipes.md § "Multi-Segment Stitching".

Version History

7f72a32 Current 2026-07-05 18:39

Metadata

Files: 0
Version: 7f72a32
Hash: 42c46d1b
Indexed: 2026-07-05 18:39

seedance-2-prompt