seedance-video

ClawSkills 作者 clawskills v1.0.0

Generate AI videos using ByteDance Seedance. Use when the user wants to: (1) generate videos from text prompts, (2) generate videos from images (first frame, first+last frame, reference images), or (3) query/manage video generation tasks. Supports Seedance 1.5 Pro (with audio), 1.0 Pro, 1.0 Pro Fast, and 1.0 Lite models.

安装 / 下载方式

TotalClaw CLI推荐

totalclaw install clawskills:clawskills~jackycser-seedance-video-generation

cURL直接下载，无需登录

curl -fsSL https://skills.taituai.com/api/skills/clawskills%3Aclawskills~jackycser-seedance-video-generation/file -o jackycser-seedance-video-generation.md

# Seedance Video Generation

Generate AI videos using ByteDance Seedance models via the Volcengine Ark API.

## Prerequisites

The user must set the `ARK_API_KEY` environment variable. You can set it by running:

```bash
export ARK_API_KEY="your-api-key-here"
```

**Base URL**: `https://ark.cn-beijing.volces.com/api/v3`

## Supported Models

| Model | Model ID | Capabilities |
|-------|----------|-------------|
| Seedance 1.5 Pro | `doubao-seedance-1-5-pro-251215` | Text-to-video, Image-to-video (first frame, first+last frame), Audio support, Draft mode |
| Seedance 1.0 Pro | `doubao-seedance-1-0-pro-250428` | Text-to-video, Image-to-video (first frame, first+last frame) |
| Seedance 1.0 Pro Fast | `doubao-seedance-1-0-pro-fast-250528` | Text-to-video, Image-to-video (first frame only) |
| Seedance 1.0 Lite T2V | `doubao-seedance-1-0-lite-t2v-250219` | Text-to-video only |
| Seedance 1.0 Lite I2V | `doubao-seedance-1-0-lite-i2v-250219` | Image-to-video (first frame, first+last frame, reference images 1-4) |

**Default model**: `doubao-seedance-1-5-pro-251215` (latest, supports audio)

## Execution (Recommended: Python CLI Tool)

A Python CLI tool is provided at `~/.claude/skills/seedance-video/seedance.py` for robust execution with proper error handling, automatic retries, and local image base64 conversion. **Prefer using this tool over raw curl commands.**

### Quick Examples with Python CLI

```bash
# Text-to-video (create + wait + download)
python3 ~/.claude/skills/seedance-video/seedance.py create --prompt "小猫对着镜头打哈欠" --wait --download ~/Desktop

# Image-to-video from local file
python3 ~/.claude/skills/seedance-video/seedance.py create --prompt "人物缓缓转头微笑" --image /path/to/photo.jpg --wait --download ~/Desktop

# Image-to-video from URL
python3 ~/.claude/skills/seedance-video/seedance.py create --prompt "风景画面缓缓推进" --image "https://example.com/image.jpg" --wait --download ~/Desktop

# First + last frame
python3 ~/.claude/skills/seedance-video/seedance.py create --prompt "花朵从含苞到盛开" --image first.jpg --last-frame last.jpg --wait --download ~/Desktop

# Reference images (Lite I2V)
python3 ~/.claude/skills/seedance-video/seedance.py create --prompt "[图1]的人物在跳舞" --ref-images ref1.jpg ref2.jpg --model doubao-seedance-1-0-lite-i2v-250219 --wait --download ~/Desktop

# Custom parameters
python3 ~/.claude/skills/seedance-video/seedance.py create --prompt "城市夜景延时摄影" --ratio 21:9 --duration 8 --resolution 1080p --generate-audio false --wait --download ~/Desktop

# Draft mode (cheaper preview)
python3 ~/.claude/skills/seedance-video/seedance.py create --prompt "海浪拍打沙滩" --draft true --wait --download ~/Desktop

# Generate final video from draft
python3 ~/.claude/skills/seedance-video/seedance.py create --draft-task-id <DRAFT_TASK_ID> --resolution 720p --wait --download ~/Desktop

# Query task status
python3 ~/.claude/skills/seedance-video/seedance.py status <TASK_ID>

# Wait for an existing task
python3 ~/.claude/skills/seedance-video/seedance.py wait <TASK_ID> --download ~/Desktop

# List tasks
python3 ~/.claude/skills/seedance-video/seedance.py list --status succeeded

# Delete/cancel task
python3 ~/.claude/skills/seedance-video/seedance.py delete <TASK_ID>
```

## Alternative: Raw curl Commands

### Step 1: Create Video Generation Task

Determine the generation mode based on user input, then call the API.

#### Mode A: Text-to-Video

```bash
TASK_RESULT=$(curl -s -X POST "https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ARK_API_KEY" \
  -d '{
    "model": "doubao-seedance-1-5-pro-251215",
    "content": [
      {
        "type": "text",
        "text": "YOUR_PROMPT_HERE"
      }
    ],
    "ratio": "16:9",
    "duration": 5,
    "resolution": "720p",
    "generate_audio": true
  }')

TASK_ID=$(echo "$TASK_RESULT" | python3 -c "import sys,json; print(json.load(sys.stdin)['id'])")
echo "Task created: $TASK_ID"
```

#### Mode B: Image-to-Video (First Frame)

The user provides one image as the first frame. The image can be a URL or local file path (convert to base64).

**With image URL:**
```bash
TASK_RESULT=$(curl -s -X POST "https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ARK_API_KEY" \
  -d '{
    "model": "doubao-seedance-1-5-pro-251215",
    "content": [
      {
        "type": "text",
        "text": "YOUR_PROMPT_HERE"
      },
      {
        "type": "image_url",
        "image_url": { "url": "IMAGE_URL_HERE" },
        "role": "first_frame"
      }
    ],
    "ratio": "adaptive",
    "duration": 5,
    "resolution": "720p",
    "generate_audio": true
  }')

TASK_ID=$(echo "$TASK_RESULT" | python3 -c "import sys,json; print(json.load(sys.stdin)['id'])")
echo "Task created: $TASK_ID"
```

**With local image file (convert to base64):**
```bash
IMG_PATH="/path/to/image.png"
IMG_EXT="${IMG_PATH##*.}"
IMG_EXT_LOWER=$(echo "$IMG_EXT" | tr '[:upper:]' '[:lower:]')
IMG_BASE64=$(base64 < "$IMG_PATH" | tr -d '\n')
IMG_DATA_URL="data:image/${IMG_EXT_LOWER};base64,${IMG_BASE64}"

TASK_RESULT=$(curl -s -X POST "https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ARK_API_KEY" \
  -d '{
    "model": "doubao-seedance-1-5-pro-251215",
    "content": [
      {
        "type": "text",
        "text": "YOUR_PROMPT_HERE"
      },
      {
        "type": "image_url",
        "image_url": { "url": "'"$IMG_DATA_URL"'" },
        "role": "first_frame"
      }
    ],
    "ratio": "adaptive",
    "duration": 5,
    "resolution": "720p",
    "generate_audio": true
  }')

TASK_ID=$(echo "$TASK_RESULT" | python3 -c "import sys,json; print(json.load(sys.stdin)['id'])")
echo "Task created: $TASK_ID"
```

#### Mode C: Image-to-Video (First + Last Frame)

Requires two images. Supported by: Seedance 1.5 Pro, 1.0 Pro, 1.0 Lite I2V.

```bash
TASK_RESULT=$(curl -s -X POST "https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ARK_API_KEY" \
  -d '{
    "model": "doubao-seedance-1-5-pro-251215",
    "content": [
      {
        "type": "text",
        "text": "YOUR_PROMPT_HERE"
      },
      {
        "type": "image_url",
        "image_url": { "url": "FIRST_FRAME_IMAGE_URL" },
        "role": "first_frame"
      },
      {
        "type": "image_url",
        "image_url": { "url": "LAST_FRAME_IMAGE_URL" },
        "role": "last_frame"
      }
    ],
    "ratio": "adaptive",
    "duration": 5,
    "resolution": "720p",
    "generate_audio": true
  }')

TASK_ID=$(echo "$TASK_RESULT" | python3 -c "import sys,json; print(json.load(sys.stdin)['id'])")
echo "Task created: $TASK_ID"
```

#### Mode D: Reference Image-to-Video (Seedance 1.0 Lite I2V only)

Provide 1-4 reference images. Use `[图1]`, `[图2]` in prompt to reference specific images.

```bash
TASK_RESULT=$(curl -s -X POST "https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $ARK_API_KEY" \
  -d '{
    "model": "doubao-seedance-1-0-lite-i2v-250219",
    "content": [
      {
        "type": "text",
        "text": "[图1]的人物在跳舞"
      },
      {
        "type": "image_url",
        "image_url": { "url": "REF_IMAGE_URL_1" },
        "role": "reference_image"
      }
    ],
    "ratio": "16:9",
    "duration": 5,
    "resolution": "720p"
  }')

TASK_ID=$(echo "$TASK_RESULT" | python3 -c "import sys,json; print(json.load(sys.stdin)['id'])")
echo "Task created: $TASK_ID"
```

### Step 2: Poll for Task Completion

Video generation is asynchronous. Poll the task status until it completes.

```bash
echo "Waiting for video generation to complete..."
while true; do
  STATUS_RESULT=$(curl -s -X GET "https://ark.cn-beijing.volces.com/api/v3/contents/generations/tasks/${TASK_ID}" \
    -H "Authorization: Bearer $ARK_A