Back to Details

kling-video

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Kling Video

Kling视频

Generate AI videos using Kling video generation models. Use when you need to: (1) create videos from text prompts, (2) animate images into videos, (3) transform existing videos with AI, or (4) create AI avatar videos with speech.
使用Kling视频生成模型制作AI视频。适用于以下场景：(1) 根据文本提示生成视频，(2) 将图片动化为视频，(3) 用AI改造现有视频，(4) 制作带语音的AI数字人视频。

Input

输入

Provide input as JSON:
json
{
  "video_prompt": "Text description for the video you want to generate (e.g., 'A cat walking in a futuristic city at sunset')",
  "image_url": "<file-id>",
  "video_url": "<file-id>",
  "model_version": "Kling model to use: 'o1' for advanced reasoning or 'v2.6' for premium visuals",
  "duration": "Video duration in seconds (5-10s supported)",
  "aspect_ratio": "Video aspect ratio: '16:9' (landscape), '9:16' (portrait), or '1:1' (square)"
}
Note on File Inputs:
  • image_url
    and 
    video_url
    require a file ID (format: 
    df-xxxxx
    )
  • How to get file ID:
    1. Upload your file to Refly using 
      refly file upload <file-path>
    2. Copy the returned file ID from the upload response
    3. Use this file ID in the input JSON
  • For text-to-video mode, omit both 
    image_url
    and 
    video_url
  • For image-to-video mode, provide 
    image_url
  • For video-to-video mode, provide 
    video_url
请以JSON格式提供输入：
json
{
  "video_prompt": "你想要生成的视频的文本描述（例如：'一只猫在日落时分的未来城市中行走'）",
  "image_url": "<file-id>",
  "video_url": "<file-id>",
  "model_version": "要使用的Kling模型：'o1'用于高级推理，'v2.6'用于优质视觉效果",
  "duration": "视频时长（支持5-10秒）",
  "aspect_ratio": "视频宽高比：'16:9'（横屏）、'9:16'（竖屏）或'1:1'（正方形）"
}
文件输入说明：
  • image_url
    和
    video_url
    需要文件ID（格式：
    df-xxxxx
    ）
  • 如何获取文件ID：
    1. 使用
      refly file upload <file-path>
      将文件上传到Refly
    2. 从上传响应中复制返回的文件ID
    3. 在输入JSON中使用该文件ID
  • 文本转视频模式下，省略
    image_url
    和
    video_url
  • 图片转视频模式下，提供
    image_url
  • 视频转视频模式下，提供
    video_url

Execution (Pattern A: File Generation)

执行流程（模式A：文件生成）

Step 0 (Optional): Upload Files for Image/Video-to-Video Modes

步骤0（可选）：为图片/视频转视频模式上传文件

bash
undefined
bash
undefined

Upload an image for image-to-video

上传图片用于图片转视频

IMAGE_RESULT=$(refly file upload /path/to/your/image.jpg) IMAGE_FILE_ID=$(echo "$IMAGE_RESULT" | jq -r '.payload.fileId') echo "Image file ID: $IMAGE_FILE_ID"
IMAGE_RESULT=$(refly file upload /path/to/your/image.jpg) IMAGE_FILE_ID=$(echo "$IMAGE_RESULT" | jq -r '.payload.fileId') echo "图片文件ID：$IMAGE_FILE_ID"

Or upload a video for video-to-video

或上传视频用于视频转视频

VIDEO_RESULT=$(refly file upload /path/to/your/video.mp4) VIDEO_FILE_ID=$(echo "$VIDEO_RESULT" | jq -r '.payload.fileId') echo "Video file ID: $VIDEO_FILE_ID"
undefined
VIDEO_RESULT=$(refly file upload /path/to/your/video.mp4) VIDEO_FILE_ID=$(echo "$VIDEO_RESULT" | jq -r '.payload.fileId') echo "视频文件ID：$VIDEO_FILE_ID"
undefined

Step 1: Run the Skill and Get Run ID

步骤1：运行技能并获取运行ID

Example 1: Text-to-Video
bash
RESULT=$(refly skill run --id skpi-rzakvguz9m7memgp3o6dokta --input '{
  "video_prompt": "A cat walking through a futuristic city at sunset",
  "duration": "5",
  "aspect_ratio": "16:9",
  "model_version": "v2.6"
}')
RUN_ID=$(echo "$RESULT" | jq -r '.payload.workflowExecutions[0].id')
Example 2: Image-to-Video
bash
undefined
示例1：文本转视频
bash
RESULT=$(refly skill run --id skpi-rzakvguz9m7memgp3o6dokta --input '{
  "video_prompt": "一只猫在日落时分的未来城市中行走",
  "duration": "5",
  "aspect_ratio": "16:9",
  "model_version": "v2.6"
}')
RUN_ID=$(echo "$RESULT" | jq -r '.payload.workflowExecutions[0].id')
示例2：图片转视频
bash
undefined

Use the IMAGE_FILE_ID from Step 0

使用步骤0中获取的IMAGE_FILE_ID

RESULT=$(refly skill run --id skpi-rzakvguz9m7memgp3o6dokta --input '{ "video_prompt": "Camera slowly zooms in on the scene", "image_url": "'"$IMAGE_FILE_ID"'", "duration": "5", "aspect_ratio": "16:9", "model_version": "v2.6" }') RUN_ID=$(echo "$RESULT" | jq -r '.payload.workflowExecutions[0].id')
undefined
RESULT=$(refly skill run --id skpi-rzakvguz9m7memgp3o6dokta --input '{ "video_prompt": "镜头缓慢拉近场景", "image_url": "'"$IMAGE_FILE_ID"'", "duration": "5", "aspect_ratio": "16:9", "model_version": "v2.6" }') RUN_ID=$(echo "$RESULT" | jq -r '.payload.workflowExecutions[0].id')
undefined

Step 2: Open Workflow in Browser and Wait for Completion

步骤2：在浏览器中打开工作流并等待完成

bash
open "https://refly.ai/workflow/c-p3ydudm0cbdu13cmqodjqwhu"
refly workflow status "$RUN_ID" --watch --interval 30000
bash
open "https://refly.ai/workflow/c-p3ydudm0cbdu13cmqodjqwhu"
refly workflow status "$RUN_ID" --watch --interval 30000

Step 3: Download and Show Result

步骤3：下载并查看结果

bash
undefined
bash
undefined

Get files from this run

获取本次运行生成的文件

FILES=$(refly workflow toolcalls "$RUN_ID" --files --latest | jq -r '.payload.files[]')
FILES=$(refly workflow toolcalls "$RUN_ID" --files --latest | jq -r '.payload.files[]')

Download and open each file

下载并打开每个文件

echo "$FILES" | jq -c '.' | while read -r file; do FILE_ID=$(echo "$file" | jq -r '.fileId') FILE_NAME=$(echo "$file" | jq -r '.name') if [ -n "$FILE_ID" ] && [ "$FILE_ID" != "null" ]; then refly file download "$FILE_ID" -o "$HOME/Desktop/${FILE_NAME}" open "$HOME/Desktop/${FILE_NAME}" fi done
undefined
echo "$FILES" | jq -c '.' | while read -r file; do FILE_ID=$(echo "$file" | jq -r '.fileId') FILE_NAME=$(echo "$file" | jq -r '.name') if [ -n "$FILE_ID" ] && [ "$FILE_ID" != "null" ]; then refly file download "$FILE_ID" -o "$HOME/Desktop/${FILE_NAME}" open "$HOME/Desktop/${FILE_NAME}" fi done
undefined

Expected Output

预期输出

  • Type: Video
  • Format: .mp4 video file
  • Location: 
    ~/Desktop/
  • Action: Opens automatically to show user
  • 类型：视频
  • 格式：.mp4视频文件
  • 保存位置：
    ~/Desktop/
  • 操作：自动打开供用户查看

Rules

规则

Follow base skill workflow: 
~/.claude/skills/refly/SKILL.md
遵循基础技能工作流：
~/.claude/skills/refly/SKILL.md