Seedance logo

Seedance

Organization
okou-ai
seedance

Seedance video generation API by ByteDance. Use when user mentions "Seedance", "ByteDance video AI", "text-to-video", "image-to-video", or wants to generate AI videos using Seedance models.

Overview

Publisherokou-ai
Repositoryokou-skills
Skill nameseedance
Stars
81
Forks
19
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by okou-ai on GitHub. Read the source before you install it.

Installation

Install the Seedance 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.
    https://github.com/okou-ai/okou-skills/tree/main/seedance
  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/okou-ai/okou-skills.git /tmp/okou-skills
mkdir -p .claude/skills
cp -r /tmp/okou-skills/seedance .claude/skills/seedance
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Seedance 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 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 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.

Troubleshooting

If requests fail, run okou doctor check-connector --env-name SEEDANCE_TOKEN or okou doctor check-connector --url https://ark.ap-southeast.bytepluses.com/api/v3/contents/generations/tasks --method POST

Video preview

  1. Before generating a video, prepare a few keyframes matching the user's subject, style, and aspect ratio. Reuse suitable supplied or already approved images.
  2. Show the actual images through accessible links, briefly describe the intended motion, and ask the user to confirm. End the turn and wait; do not start a video job before confirmation. Revise the preview if requested.
  3. After confirmation, generate the video. Use the approved images as first/last frames or references when supported by the selected model; otherwise follow the approved visual direction in the prompt. Reuse existing confirmation for an unchanged preview.

Keep the preview message short: the images, a brief motion description, and one confirmation question.

How to Use

Video generation is asynchronous: submit a task → get a task ID → poll until succeeded → use the video URL (valid for 24 hours).

1. Text-to-Video (Standard — 1080p)

Write to /tmp/seedance_request.json:

json
{
  "model": "dreamina-seedance-2-0-260128",
  "content": [
    { "type": "text", "text": "A golden retriever puppy playing in autumn leaves, cinematic slow motion" }
  ],
  "resolution": "1080p",
  "ratio": "16:9",
  "duration": 5
}
bash
curl -s -X POST "https://ark.ap-southeast.bytepluses.com/api/v3/contents/generations/tasks" --header "Authorization: Bearer $SEEDANCE_TOKEN" --header "Content-Type: application/json" -d @/tmp/seedance_request.json | jq -r '.id'

2. Text-to-Video (Fast — 720p, lower cost)

Write to /tmp/seedance_request.json:

json
{
  "model": "dreamina-seedance-2-0-fast-260128",
  "content": [
    { "type": "text", "text": "A timelapse of clouds rolling over mountain peaks, epic wide angle" }
  ],
  "resolution": "720p",
  "ratio": "16:9",
  "duration": 5
}
bash
curl -s -X POST "https://ark.ap-southeast.bytepluses.com/api/v3/contents/generations/tasks" --header "Authorization: Bearer $SEEDANCE_TOKEN" --header "Content-Type: application/json" -d @/tmp/seedance_request.json | jq -r '.id'

3. Poll for Task Status

Replace <task-id> with the ID returned from the create call above.

bash
curl -s "https://ark.ap-southeast.bytepluses.com/api/v3/contents/generations/tasks/<task-id>" --header "Authorization: Bearer $SEEDANCE_TOKEN" | jq '{status: .status, video_url: .content.video_url, duration: .duration, resolution: .resolution}'

Poll until status is succeeded. Terminal states: succeeded, failed, expired, cancelled.

4. Image-to-Video (Animate a First Frame)

Write to /tmp/seedance_request.json:

json
{
  "model": "dreamina-seedance-2-0-260128",
  "content": [
    {
      "type": "image_url",
      "image_url": { "url": "https://example.com/your-image.jpg" },
      "role": "first_frame"
    },
    { "type": "text", "text": "The camera slowly zooms in on the subject" }
  ],
  "resolution": "1080p",
  "ratio": "16:9",
  "duration": 5
}
bash
curl -s -X POST "https://ark.ap-southeast.bytepluses.com/api/v3/contents/generations/tasks" --header "Authorization: Bearer $SEEDANCE_TOKEN" --header "Content-Type: application/json" -d @/tmp/seedance_request.json | jq -r '.id'

5. Reference-to-Video (Character/Style Reference)

Write to /tmp/seedance_request.json:

json
{
  "model": "dreamina-seedance-2-0-260128",
  "content": [
    {
      "type": "image_url",
      "image_url": { "url": "https://example.com/character.jpg" },
      "role": "reference_image"
    },
    { "type": "text", "text": "The character walks forward confidently in an urban environment" }
  ],
  "resolution": "1080p",
  "ratio": "9:16",
  "duration": 5
}
bash
curl -s -X POST "https://ark.ap-southeast.bytepluses.com/api/v3/contents/generations/tasks" --header "Authorization: Bearer $SEEDANCE_TOKEN" --header "Content-Type: application/json" -d @/tmp/seedance_request.json | jq -r '.id'

6. Download Generated Video

Replace <video-url> with the content.video_url from the completed task.

bash
curl -sL "<video-url>" -o /tmp/seedance_output.mp4

Model Reference

Model IDTierMax ResolutionDuration
dreamina-seedance-2-0-260128Standard1080p4–15s or -1 (smart)
dreamina-seedance-2-0-fast-260128Fast720p4–15s or -1 (smart)

Key Parameters

ParameterValuesDefaultDescription
resolution480p, 720p, 1080p720pOutput resolution
ratio16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptiveadaptiveAspect ratio
duration4–15 or -15Duration in seconds; -1 = smart auto
generate_audiotrue/falsetrueInclude AI-generated audio
seedinteger-1Fixed seed for reproducibility; -1 = random
watermarktrue/falsefalseAdd watermark to output
return_last_frametrue/falsefalseAlso return the last frame as a PNG URL

Image Role Values

RoleDescription
first_frameImage used as the first frame of the video
last_frameImage used as the last frame of the video
reference_imageCharacter/style reference (up to 9 images)
reference_videoVideo style reference (up to 3 videos, URL only — no Base64)
reference_audioAudio reference (up to 3 clips)

Guidelines

  1. Video URLs expire in 24 hours — download immediately after status: succeeded
  2. Async flow — always poll GET after POST; do not re-submit the same task
  3. Rate limits — 3 concurrent tasks and 180 RPM for individual accounts
  4. Image input — supports public URLs or Base64 (data:image/jpeg;base64,...); video input is URL only
  5. No flex tier — Seedance only supports service_tier: "default"
  6. Task records expire — task IDs are deleted after 7 days

Frequently asked questions

What does the Seedance AI skill do?

Seedance video generation API by ByteDance. Use when user mentions "Seedance", "ByteDance video AI", "text-to-video", "image-to-video", or wants to generate AI videos using Seedance models.

Why use Seedance on TypingMind?

Because you install it once and use it with any model. Seedance 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 in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/okou-ai/okou-skills/tree/main/seedance. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Seedance?

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?

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

Is the Seedance AI skill free?

It is published on GitHub by okou-ai. Check the repository for licensing terms. 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 👇