toby-video-generation（托比视频一代）

Seedance Video Generation

Generate AI videos via SkillBoss API Hub's unified video generation capability.

Prerequisites

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

export SKILLBOSS_API_KEY="your-api-key-here"

Base URL: https://api.skillbossai.com/v1/pilot

Supported Models

SkillBoss API Hub automatically routes to the optimal video generation model. Model hints are passed via the inputs field and honored when available.

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 and local image base64 conversion. Prefer using this tool over raw curl commands.

Quick Examples with Python CLI

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

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

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

Alternative: Raw curl Commands

Text-to-Video

[ -z "$SKILLBOSS_API_KEY" ] && echo "Error: SKILLBOSS_API_KEY not set" && exit 1

RESULT=$(curl -s -X POST "https://api.skillbossai.com/v1/pilot" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -d '{
    "type": "video",
    "inputs": {
      "prompt": "YOUR_PROMPT_HERE",
      "ratio": "16:9",
      "duration": 5,
      "resolution": "720p",
      "generate_audio": true
    },
    "prefer": "balanced"
  }')

VIDEO_URL=$(echo "$RESULT" | python3 -c "import sys,json; print(json.load(sys.stdin)['result']['video_url'])")
echo "Video URL: $VIDEO_URL"

Image-to-Video (First Frame, URL)

[ -z "$SKILLBOSS_API_KEY" ] && echo "Error: SKILLBOSS_API_KEY not set" && exit 1

RESULT=$(curl -s -X POST "https://api.skillbossai.com/v1/pilot" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -d '{
    "type": "video",
    "inputs": {
      "prompt": "YOUR_PROMPT_HERE",
      "image": "IMAGE_URL_HERE",
      "ratio": "adaptive",
      "duration": 5,
      "resolution": "720p",
      "generate_audio": true
    },
    "prefer": "balanced"
  }')

VIDEO_URL=$(echo "$RESULT" | python3 -c "import sys,json; print(json.load(sys.stdin)['result']['video_url'])")
echo "Video URL: $VIDEO_URL"

Image-to-Video (First Frame, Local File)

[ -z "$SKILLBOSS_API_KEY" ] && echo "Error: SKILLBOSS_API_KEY not set" && exit 1

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

RESULT=$(curl -s -X POST "https://api.skillbossai.com/v1/pilot" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -d "{
    \"type\": \"video\",
    \"inputs\": {
      \"prompt\": \"YOUR_PROMPT_HERE\",
      \"image\": \"${IMG_DATA_URL}\",
      \"ratio\": \"adaptive\",
      \"duration\": 5,
      \"resolution\": \"720p\",
      \"generate_audio\": true
    },
    \"prefer\": \"balanced\"
  }")

VIDEO_URL=$(echo "$RESULT" | python3 -c "import sys,json; print(json.load(sys.stdin)['result']['video_url'])")
echo "Video URL: $VIDEO_URL"

Image-to-Video (First + Last Frame)

[ -z "$SKILLBOSS_API_KEY" ] && echo "Error: SKILLBOSS_API_KEY not set" && exit 1

RESULT=$(curl -s -X POST "https://api.skillbossai.com/v1/pilot" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -d '{
    "type": "video",
    "inputs": {
      "prompt": "YOUR_PROMPT_HERE",
      "image": "FIRST_FRAME_IMAGE_URL",
      "last_frame": "LAST_FRAME_IMAGE_URL",
      "ratio": "adaptive",
      "duration": 5,
      "resolution": "720p",
      "generate_audio": true
    },
    "prefer": "balanced"
  }')

VIDEO_URL=$(echo "$RESULT" | python3 -c "import sys,json; print(json.load(sys.stdin)['result']['video_url'])")
echo "Video URL: $VIDEO_URL"

Reference Image-to-Video

[ -z "$SKILLBOSS_API_KEY" ] && echo "Error: SKILLBOSS_API_KEY not set" && exit 1

RESULT=$(curl -s -X POST "https://api.skillbossai.com/v1/pilot" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $SKILLBOSS_API_KEY" \
  -d '{
    "type": "video",
    "inputs": {
      "prompt": "[图1]的人物在跳舞",
      "ref_images": ["REF_IMAGE_URL_1"],
      "ratio": "16:9",
      "duration": 5,
      "resolution": "720p"
    },
    "prefer": "balanced"
  }')

VIDEO_URL=$(echo "$RESULT" | python3 -c "import sys,json; print(json.load(sys.stdin)['result']['video_url'])")
echo "Video URL: $VIDEO_URL"

Download and Open Video

OUTPUT_PATH="$HOME/Desktop/seedance_video_$(date +%Y%m%d_%H%M%S).mp4"
curl -s -o "$OUTPUT_PATH" "$VIDEO_URL"
echo "Video saved to: $OUTPUT_PATH"
open "$OUTPUT_PATH"

Optional Parameters Reference

Image Requirements

• Formats: jpeg, png, webp, bmp, tiff, gif (1.5 Pro also supports heic, heif)
• Aspect ratio (width/height): between 0.4 and 2.5
• Dimensions: 300-6000 px per side
• Max file size: 30 MB

通过飞书发送视频文件（OpenClaw）

详见 how_to_send_video_via_feishu_app.md

Rules

1. Always check that SKILLBOSS_API_KEY is set before making API calls: [ -z "$SKILLBOSS_API_KEY" ] && echo "Error: SKILLBOSS_API_KEY not set" && exit 1
2. Default to Seedance 1.5 Pro hint (doubao-seedance-1-5-pro-251215) unless user requests a specific model.
3. Default to 720p, 16:9, 5 seconds, with audio for text-to-video.
4. Default to adaptive ratio for image-to-video (auto-adapts to the input image).
5. Video URLs expire in 24 hours - always download immediately after generation.
6. For local image files, convert to base64 data URL format before sending.
7. Always show the user the video URL so they can access the result.
8. When generation fails, display the error message clearly and suggest possible fixes.