Seedance 2 Prompt logo

Seedance 2 Prompt

OrganizationPopular
TokenRhythm
seedance-2-prompt

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.

Overview

PublisherTokenRhythm
Repositoryopensquilla
Skill nameseedance-2-prompt
Stars
7K
Forks
566
Bundled files
4
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by TokenRhythm on GitHub. Read the source before you install it.

Installation

Install the Seedance 2 Prompt AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/TokenRhythm/opensquilla.git /tmp/opensquilla
mkdir -p .claude/skills
cp -r /tmp/opensquilla/src/opensquilla/skills/bundled/seedance-2-prompt .claude/skills/seedance-2-prompt
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Seedance 2 Prompt in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Seedance 2 Prompt on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Seedance 2 Prompt is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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.providerEndpointAuth envDefault model
openrouter (default)https://openrouter.ai/api/v1/videosOPENROUTER_API_KEYbytedance/seedance-2.0
volcengine (CN)https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasksARK_API_KEY (or VOLC_ARK_API_KEY)doubao-seedance-2-0-260128
byteplus (intl)https://ark.ap-southeast.bytepluses.com/api/v3/contents/generations/tasksARK_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:)

keyrequireddefaultnotes
promptyesStructured English video prompt (use this skill's recipes).
filenameyesOutput .mp4 path.
providernoopenrouteropenrouter, volcengine, or byteplus.
aspect_rationo9:169:16, 16:9, 1:1, 4:3, 3:4, 21:9.
durationno5Seconds, 3-15. OpenRouter Seedance accepts 4-15; a 3-second request generates a real 4-second provider clip and is trimmed locally to exactly 3 seconds.
resolutionno720p480p, 720p, 1080p. Ignored by OpenRouter.
modelnoprovider defaultOverride model id. Empty means use provider default.
input_imageno""Strict first-frame path. If set, video starts from this image.
input_referenceno""Primary soft identity/style anchor path. Used only when input_image is empty. Same anchor passed across shots locks the character.
input_reference_2no""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_retriesno0Extra retries for transient polling HTTP 429/5xx or transport failures after a job id is issued, capped at 5; every retry stays on that same job. A paid POST submit is never retried automatically, including an ambiguous 429/5xx or transport failure, because the provider may already have accepted and billed it. HTTP 401/403/other 4xx, terminal policy failures, and invalid downloaded media also stop immediately. 0 = no extra polling retry.

input_image vs input_referenceinput_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)

  1. One major action per 3-5s segment. Don't pack multiple motions.
  2. Identity continuity — repeat the main character's full description in every shot's prompt.
  3. Specific over poetic"a young woman in a red trench coat walks through rain-soaked neon streets" >> "a woman walking".
  4. Negative constraints inline — append no watermark, no logo, no subtitles, no on-screen text.
  5. IP-safe — invent original character/brand names.
  6. 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. The parent-injected atomic tuple OPENSQUILLA_META_CAPABILITY_PROVIDER, OPENSQUILLA_META_CAPABILITY_API_KEY, and OPENSQUILLA_META_CAPABILITY_BASE_URL; optional OPENSQUILLA_META_CAPABILITY_PROXY is used only for the matching provider's authenticated API requests
    3. OPENSQUILLA_META_OPENROUTER_API_KEY, retained for older parent runtimes and bound to OpenRouter's official origin
    4. OPENROUTER_API_KEY for direct CLI use, also bound to the official origin
  • The generic parent key is accepted only with its matching provider and base URL. Parent and canonical environment credentials allow same-origin path changes through --base-url, but never a scheme, hostname, or effective-port change. Direct CLI users who intentionally select a different origin must pass both --api-key and --base-url.
  • The child never discovers or parses opensquilla.toml from its workspace and never honors a workspace-selected arbitrary llm.api_key_env. Configure the active Gateway normally; its parent runtime performs that resolution.
  • When a parent-resolved profile-pool credential receives an authentication, credit, or rate-limit failure, OpenSquilla parks that key for the next explicitly authorized run. It never repeats the current paid generation automatically.
  • 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> only to an API URL whose scheme, hostname, and effective port exactly match the configured provider base. Authenticated redirects are not followed. A provider-supplied cross-origin polling URL is ignored in favour of the canonical job URL under the trusted base. A parent-injected proxy is used for these matching provider API requests only and never for anonymous media downloads.
  • Media downloads are always anonymous, including URLs hosted by OpenRouter. Download URLs and every redirect must use HTTPS, contain no userinfo, and resolve exclusively to public addresses; localhost, private, loopback, link-local, reserved, unspecified, and multicast targets are rejected. Each connection is pinned to the address that passed validation while retaining the original TLS SNI/hostname, eliminating DNS-rebinding between validation and connection.

Output

Prints the absolute path of the saved .mp4, then a VIDEO_GENERATION_RECEIPT: {...} line on stdout. A matching sanitized receipt is saved as <filename>.receipt.json; it records provider, model, safe job id, and ffprobe verification metadata for both the provider clip and final clip. Downloads first land in a private same-directory candidate file. The script requires a real video stream, positive duration, reasonable dimensions, and duration within tolerance; 3-second requests are probed both before and after the local trim. Only a verified candidate is atomically published with os.replace, so an HTML error page, truncated download, or failed trim cannot overwrite an existing output. The receipt never contains the API key, prompt, raw provider response, request/generation metadata, usage payload, or signed download URL. Logs omit URL queries/fragments and raw provider messages. Non-zero exit on any error; stderr carries a sanitized status/code summary when available.

On a recognized provider-policy rejection, the script stops immediately and persists a failure sidecar instead of fabricating API success. That sidecar is strictly limited to status=policy_rejected, provider/model, reason=provider_policy_rejected, and the allowlisted policy_code; it never contains raw provider text, signed URLs, request/job IDs, prompts, or secrets. Meta workflows can then run their local fallback while preserving an honest, user-visible degraded reason for the delivery audit.

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".

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Seedance 2 Prompt AI skill do?

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.

Why use Seedance 2 Prompt on TypingMind?

Because you install it once and use it with any model. Seedance 2 Prompt is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Seedance 2 Prompt in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/TokenRhythm/opensquilla/tree/main/src/opensquilla/skills/bundled/seedance-2-prompt. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Seedance 2 Prompt?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Seedance 2 Prompt?

As many as you like. As long as a model supports skills, you can use Seedance 2 Prompt with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Seedance 2 Prompt AI skill free?

Yes. It is published on GitHub by TokenRhythm under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇