跳到主内容
智客 ZICQ

技能库 智客分类:媒体内容 seedance2-api

Seedance2 Api

从故事板概念到最终输出的端到端的AI视频生成. 支持MCP和独立的Python脚本模式;如果MCP不可用,则自动检测可用性和优雅的切换. 以Seedream 4.5(文本对图像和图像编辑)生成参考图像,然后向Seedance 2.0提交视频任务,并带有可配置的侧面比率和持续时间.

11965 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

从故事板概念到最终输出的端到端的AI视频生成. 支持MCP和独立的Python脚本模式;如果MCP不可用,则自动检测可用性和优雅的切换. 以Seedream 4.5(文本对图像和图像编辑)生成参考图像,然后向Seedance 2.0提交视频任务,并带有可配置的侧面比率和持续时间.

何时用

官方 description 未单独写出 Use when。按规范,代理会在用户任务与这段 description 的关键词匹配时激活本技能。

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Seedance 2.0 Storyboard & Video Generation、Step 0: Determine Execution Mode (MCP or Script)、Find via Glob tool、Step 1: Understand the User's Idea、Step 2: Deep Dive (5 Dimensions)、Step 3: Build Storyboard Structure。 其中含规范建议的小节:分步指令。

文件分析

文件分析:除 SKILL.md 外,正文引用了 scripts/seedance_api.py,属于带资源的技能包,这些文件按需再读。

官方 description(原文)

End-to-end AI video generation from storyboard concept to final output. Supports both MCP and standalone Python script modes; automatically detects availability and switches gracefully if MCP is unavailable. Generates reference images with Seedream 4.5 (text-to-image and image editing), then submits video tasks to Seedance 2.0 with configurable aspect ratios and durations.

Seedance 2.0 Storyboard & Video GenerationStep 0: Determine Execution Mode (MCP or Script)Find via Glob toolStep 1: Understand the User's IdeaStep 2: Deep Dive (5 Dimensions)Step 3: Build Storyboard StructureStep 4: Generate Reference Images (If Needed)Text-to-ImageImage Editing (Modify Existing Images)Poll Image Results`image_size` ReferenceStep 5: Compose the Final Prompt

· 许可:MIT

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
seedance2-api
description
End-to-end AI video generation from storyboard concept to final output. Supports both MCP and standalone Python script modes; automatically detects availability and switches gracefully if MCP is unavailable. Generates reference images with Seedream 4.5 (text-to-image and image editing), then submits video tasks to Seedance 2.0 with configurable aspect ratios and durations.
许可
MIT
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。
指令中引用的文件 · 1
  • scripts/seedance_api.py

以下路径提取自原文;文件是否齐全请以来源仓库中的完整目录为准。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

该技能引用了附属文件,请从来源获取完整目录;仅复制 SKILL.md 可能缺少依赖。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「seedance2-api」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-67e9c849808b3352-Seedance2-Api.html
请存为 .cursor/skills/seedance2-api/SKILL.md 或 .claude/skills/seedance2-api/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
该技能还带 scripts/、references/、assets/ 等文件,请从 https://github.com/hexiaochun/seedance2-api 取完整目录,不要只建一个 SKILL.md。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/hexiaochun/seedance2-api' --list

npx skills add 'https://github.com/hexiaochun/seedance2-api' --skill 'seedance2-api'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版

name: seedance2-api description: End-to-end AI video generation from storyboard concept to final output. Supports both MCP and standalone Python script modes; automatically detects availability and switches gracefully if MCP is unavailable. Generates reference images with Seedream 4.5 (text-to-image and image editing), then submits video tasks to Seedance 2.0 with configurable aspect ratios and durations. license: MIT

Seedance 2.0 Storyboard & Video Generation

End-to-end workflow from concept to final video: Storyboard → Reference images → Submit video task → Get results.

Step 0: Determine Execution Mode (MCP or Script)

Check MCP availability first:

  • Check xskill-ai MCP service status (read mcps/user-xskill-ai/STATUS.md)
  • If MCP is available → use submit_task / get_task and other MCP tools
  • If MCP is unavailable or returns errors → switch to Script Mode

Script mode prerequisites:

  • Verify XSKILL_API_KEY environment variable is set (run echo $XSKILL_API_KEY | head -c 10)
  • If not set, prompt the user:
    export XSKILL_API_KEY=sk-your-api-key
    
    Get your API Key: https://www.xskill.ai/#/v2/api-keys
  • Verify requests is installed (pip install requests)

Script path: Located under this skill's directory at scripts/seedance_api.py:

# Find via Glob tool
glob: .cursor/skills/seedance2-api/scripts/seedance_api.py

In the following steps, each API call provides both MCP method and Script method. Choose one based on the Step 0 result.

Step 1: Understand the User's Idea

Collect the following information (proactively ask if anything is missing):

  • Story concept: one-sentence summary of the video
  • Duration: 4–15 seconds
  • Aspect ratio: 16:9 / 9:16 / 1:1 / 21:9 / 4:3 / 3:4
  • Visual style: realistic / animation / ink wash / sci-fi / cyberpunk, etc.
  • Assets: existing images/videos/audio, or need AI generation
  • Function mode: first & last frame control (first_last_frames) or default omni mode (omni_reference)

Step 2: Deep Dive (5 Dimensions)

Guide the user through each dimension for richer detail:

  • Content – Who is the subject? What are they doing? Where?
  • Visuals – Lighting, color palette, texture, mood
  • Camera – Push in / pull out / pan / tilt / track / orbit / crane
  • Motion – Subject actions and pacing
  • Audio – Music style, sound effects, dialogue

Step 3: Build Storyboard Structure

Break down shots along the timeline using this formula:

[Style] _____ style, _____ seconds, _____ ratio, _____ mood

0-Xs: [Camera movement] + [Visual content] + [Action description]
X-Ys: [Camera movement] + [Visual content] + [Action description]
...

[Audio] _____ music + _____ SFX + _____ dialogue
[References] @image_file_1 _____, @video_file_1 _____

See reference.md for detailed templates and examples.

Step 4: Generate Reference Images (If Needed)

If the user has no existing assets, use Seedream 4.5 to generate character art, scenes, first/last frames, etc.

Text-to-Image

Call submit_task tool:

  • model_id: fal-ai/bytedance/seedream/v4.5/text-to-image
  • parameters:
    • prompt: detailed image description (English works best)
    • image_size: choose based on video aspect ratio
    • num_images: number needed (1–6)
python .cursor/skills/seedance2-api/scripts/seedance_api.py submit \
  --model "fal-ai/bytedance/seedream/v4.5/text-to-image" \
  --params '{"prompt":"An astronaut in a white spacesuit...","image_size":"landscape_16_9","num_images":1}'

Image Editing (Modify Existing Images)

Call submit_task tool:

  • model_id: fal-ai/bytedance/seedream/v4.5/edit
  • parameters:
    • prompt: editing instructions (use Figure 1/2/3 to reference images)
    • image_urls: array of input image URLs
    • image_size: output size
python .cursor/skills/seedance2-api/scripts/seedance_api.py submit \
  --model "fal-ai/bytedance/seedream/v4.5/edit" \
  --params '{"prompt":"Change the background to a forest","image_urls":["https://..."],"image_size":"landscape_16_9"}'

Poll Image Results

Images typically complete in 1–2 minutes.

Call get_task tool to check status:

  • First query after 30 seconds
  • Then every 30 seconds
  • Extract image URL when status is completed

Single query:

python .cursor/skills/seedance2-api/scripts/seedance_api.py query \
  --task-id "TASK_ID_HERE"

Auto-poll (recommended for images, interval 10s, timeout 180s):

python .cursor/skills/seedance2-api/scripts/seedance_api.py poll \
  --task-id "TASK_ID_HERE" --interval 10 --timeout 180

image_size Reference

| Aspect Ratio | Recommended image_size | Note | |---|---|---| | 16:9 | landscape_16_9 | Landscape | | 9:16 | portrait_16_9 | Portrait | | 4:3 | landscape_4_3 | Landscape | | 3:4 | portrait_4_3 | Portrait | | 1:1 | square_hd | Square | | 21:9 | landscape_16_9 | Approximate ultrawide |

Step 5: Compose the Final Prompt

Merge the storyboard structure and reference images into the final prompt:

  • Use @image_file_1, @image_file_2, etc. to reference images in the image_files array
  • Use @video_file_1, etc. to reference videos in the video_files array
  • Use @audio_file_1, etc. to reference audio in the audio_files array

Reference syntax example:

@image_file_1 as character reference, follow @video_file_1 camera movement, with @audio_file_1 as background music

Important: The Nth URL in image_files maps to @image_file_N. video_files and audio_files are independently numbered.

Step 6: Submit Video Task

Handle asset URLs:

  • Seedream-generated images: URL already available, use directly
  • User-provided web images: use directly
  • User-provided local images: upload first to get URL (see upload methods below)

Upload Local Images

Call upload_image tool: image_url or image_data

# Upload from URL
python .cursor/skills/seedance2-api/scripts/seedance_api.py upload \
  --image-url "https://example.com/image.png"

# Upload local file
python .cursor/skills/seedance2-api/scripts/seedance_api.py upload \
  --image-path "/path/to/local/image.png"

Submit Seedance 2.0 Task (Omni Reference Mode)

Call submit_task tool:

  • model_id: st-ai/super-seed2
  • parameters:
    • prompt: the full prompt from Step 5
    • functionMode: omni_reference (default, can be omitted)
    • image_files: reference image URL array (up to 9, order matches @image_file_1/2/3...)
    • video_files: reference video URL array (up to 3, total duration ≤ 15s)
    • audio_files: reference audio URL array (up to 3)
    • ratio: aspect ratio (16:9 / 9:16 / 1:1 / 21:9 / 4:3 / 3:4)
    • duration: integer length (4–15)
    • model: seedance_2.0_fast (default, faster) or seedance_2.0 (standard quality)
python .cursor/skills/seedance2-api/scripts/seedance_api.py submit \
  --model "st-ai/super-seed2" \
  --params '{
    "prompt": "Cinematic realistic sci-fi style, 15 seconds, 16:9...",
    "functionMode": "omni_reference",
    "image_files": ["https://img1.png", "https://img2.png"],
    "ratio": "16:9",
    "duration": 15,
    "model": "seedance_2.0_fast"
  }'

Submit Seedance 2.0 Task (First & Last Frames Mode)

Call submit_task tool:

  • model_id: st-ai/super-seed2
  • parameters:
    • prompt: video description prompt
    • functionMode: first_last_frames
    • filePaths: image URL array (0 = text-to-video, 1 = first frame, 2 = first & last frames)
    • ratio: aspect ratio
    • duration: integer length
    • model: seedance_2.0_fast or seedance_2.0
python .cursor/skills/seedance2-api/scripts/seedance_api.py submit \
  --model "st-ai/super-seed2" \
  --params '{
    "prompt": "Camera smoothly transitions from first frame to last frame, fluid motion",
    "functionMode": "first_last_frames",
    "filePaths": ["https://first-frame.png", "https://last-frame.png"],
    "ratio": "16:9",
    "duration": 5,
    "model": "seedance_2.0_fast"
  }'

Step 7: Poll for Video Results

Video generation takes approximately 10 minutes.

Polling strategy:

  • After submission, inform the user: "Video is generating, estimated ~10 minutes"
  • First query after 60 seconds via get_task
  • Then every 90 seconds
  • Report status to the user after each query

Recommended: auto-poll (runs in foreground, interval 30s, timeout 600s):

python .cursor/skills/seedance2-api/scripts/seedance_api.py poll \
  --task-id "TASK_ID_HERE" --interval 30 --timeout 600

Progress is printed to stderr; final JSON result is printed to stdout when complete.

Manual single query:

python .cursor/skills/seedance2-api/scripts/seedance_api.py query \
  --task-id "TASK_ID_HERE"

Status reference:

  • pending → "Queued..."
  • processing → "Generating..."
  • completed → Extract the video URL and present to the user
  • failed → Report the error; suggest adjusting the prompt and retrying

Full Workflow Example

User says: "Make a video of an astronaut walking on Mars"

When MCP Is Available

1. Gather info → 15s, 16:9, cinematic sci-fi style, no existing assets

2. Generate astronaut + Mars scene images with Seedream 4.5
   submit_task("fal-ai/bytedance/seedream/v4.5/text-to-image", {...})
   → poll get_task → get image URLs

3. Compose prompt → submit video task
   submit_task("st-ai/super-seed2", {...})

4. Poll get_task, ~10 min later → get video URL

When MCP Is Unavailable (Script Mode)

1. Gather info → 15s, 16:9, cinematic sci-fi style

2. Generate reference images:
   python scripts/seedance_api.py submit \
     --model "fal-ai/bytedance/seedream/v4.5/text-to-image" \
     --params '{"prompt":"An astronaut in white spacesuit on Mars...","image_size":"landscape_16_9"}'
   → get task_id

3. Poll for image results:
   python scripts/seedance_api.py poll --task-id "xxx" --interval 10 --timeout 180
   → get image URL

4. Submit video task:
   python scripts/seedance_api.py submit \
     --model "st-ai/super-seed2" \
     --params '{"prompt":"...storyboard prompt...","functionMode":"omni_reference","image_files":["IMAGE_URL"],"ratio":"16:9","duration":15,"model":"seedance_2.0_fast"}'
   → get task_id

5. Poll for video results:
   python scripts/seedance_api.py poll --task-id "xxx" --interval 30 --timeout 600
   → get video URL

Model Parameters Quick Reference

Seedream 4.5 Text-to-Image

| Parameter | Type | Required | Description | |---|---|---|---| | prompt | string | Yes | Image description | | image_size | string | No | auto_2K / auto_4K / square_hd / portrait_4_3 / portrait_16_9 / landscape_4_3 / landscape_16_9 | | num_images | int | No | 1–6, default 1 |

Seedream 4.5 Image Editing

| Parameter | Type | Required | Description | |---|---|---|---| | prompt | string | Yes | Editing instructions, reference images as Figure 1/2/3 | | image_urls | array | Yes | Input image URL list | | image_size | string | No | Same as above | | num_images | int | No | 1–6, default 1 |

Seedance 2.0 Video (Omni Reference Mode)

| Parameter | Type | Required | Description | |---|---|---|---| | prompt | string | Yes | Storyboard prompt, use @image_file_N / @video_file_N / @audio_file_N | | functionMode | string | No | omni_reference (default) | | image_files | array | No | Reference image URL array (up to 9) | | video_files | array | No | Reference video URL array (up to 3, total ≤ 15s) | | audio_files | array | No | Reference audio URL array (up to 3) | | ratio | string | No | 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 | | duration | integer | No | 4–15, default 5 | | model | string | No | seedance_2.0_fast (default) / seedance_2.0 |

Seedance 2.0 Video (First & Last Frames Mode)

| Parameter | Type | Required | Description | |---|---|---|---| | prompt | string | Yes | Video description prompt | | functionMode | string | Yes | first_last_frames | | filePaths | array | No | Image URL array (0 = text-to-video, 1 = first frame, 2 = first & last) | | ratio | string | No | 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 | | duration | integer | No | 4–15, default 5 | | model | string | No | seedance_2.0_fast (default) / seedance_2.0 |

Tools Quick Reference

MCP Tools

| Action | Tool | Key Parameters | |---|---|---| | Submit task | submit_task | model_id, parameters | | Query result | get_task | task_id | | Upload image | upload_image | image_url or image_data | | Check balance | get_balance | (none) |

Script Commands (When MCP Is Unavailable)

| Action | Command | Description | |---|---|---| | Submit task | python scripts/seedance_api.py submit --model MODEL --params '{...}' | Returns task_id | | Single query | python scripts/seedance_api.py query --task-id ID | Returns current status | | Auto-poll | python scripts/seedance_api.py poll --task-id ID --interval N --timeout N | Blocks until done | | Check balance | python scripts/seedance_api.py balance | Returns account balance | | Upload image | python scripts/seedance_api.py upload --image-url URL or --image-path PATH | Returns image URL |

Script path note: The scripts/seedance_api.py path above is relative to .cursor/skills/seedance2-api/. Use the full path .cursor/skills/seedance2-api/scripts/seedance_api.py when executing, or cd into the skill directory first.

Seedance 2.0 Limitations

  • Realistic human face uploads are not supported
  • Maximum 12 files: images ≤ 9 + videos ≤ 3 + audio ≤ 3
  • Total video/audio reference duration ≤ 15 seconds
  • Video references consume more credits

More Resources

See reference.md for detailed storyboard templates, full examples, and camera movement glossary.

相关技能

媒体内容

Nano Banana Pro

以纳米·香蕉Pro(Gemini 3 Pro Image)来生成/编辑图像. 用于创建/修改请求,包括编辑。 支持文本到图像+图像到图像; 1K/2K/4K; 使用 -- input-image.

媒体内容

Youtube Watcher

从YouTube视频中获取并读取文字记录. 需要汇总视频时使用,回答有关视频内容的问题,或者从中提取信息.

媒体内容

Atxp

Access ATXP支付API工具用于网页搜索,AI图像生成,音乐创建,视频生成,X/Twitter搜索,电子邮件,代理账户管理. 当用户需要实时网络搜索时使用,AI生成的媒体(图像,音乐,视频),X/Twitter搜索,发送/接收电子邮件,或创建和资助代理账户. 需要通过“ …

媒体内容

Youtube

YouTube Data API与管理的OAuth的集成. 搜索视频,管理播放列表,访问频道数据,并与评论互动. 用户想与YouTube互动时使用此技能. 对于其他第三方应用,使用api-gateway技能(https://clawhub.ai/byungkyu/api-gate…