jimeng_mcp_skill

Jimeng AI Generation Skill

Overview

The Jimeng skill enables AI-driven image and video generation through jimeng-mcp-server, an MCP (Model Context Protocol) server that integrates Jimeng AI's multimodal generation capabilities. Use this skill to create visual content directly through natural language instructions.

Core capabilities:

🎨 Text-to-image: Generate high-quality images from text descriptions
🎭 Image composition: Intelligently merge and blend multiple images
🎬 Text-to-video: Create short videos from text prompts
🎞️ Image-to-video: Add animation effects to static images

When to use this skill:

The user asks to generate, create, or produce an image or video
The user mentions "jimeng", "Jimeng", or requests AI visual content generation
The user provides a text description and wants visual output
The user wants to combine, merge, or composite multiple images
The user wants to add animation or motion effects to a static image

Prerequisites

Before using this skill, make sure jimeng-mcp-server is correctly configured:

The server must be running, through one of the following modes:
- stdio mode: Configured in an MCP client (Claude Desktop, Cherry Studio)
- SSE mode: Running as an HTTP server with SSE transport
- HTTP mode: Running as a REST API server
Environment variables are configured：
- JIMENG_API_KEY: Your Jimeng API key (obtained from Jimeng website cookies)
- JIMENG_API_URL: API endpoint (default:http://127.0.0.1:8001）
- JIMENG_MODEL: Model name (default: jimeng-4.5)
Backend API is running: The jimeng-free-api-all Docker container must be active

For detailed setup instructions, refer to references/setup_guide.md。

Quick Start

Basic Usage Pattern

When the user requests image or video generation, follow this workflow:

Identify the task type, based on the user input
Extract the required parameters, from the request
Call the corresponding jimeng-mcp-server tool
Return the generated content URL to the user

Example requests

Text-to-image:

用户："用即梦生成一张图片：樱花树下的柴犬"
→ 使用 text_to_image 工具，参数 prompt="樱花树下的柴犬"

Image composition:

用户："帮我合成这两张图片，风格偏向第一张"
→ 使用 image_composition 工具，提供图片 URL

Text-to-video:

用户："创建一个5秒视频：小马过河的故事场景"
→ 使用 text_to_video 工具，设置提示词和时长

Image-to-video:

用户："为这张图片添加动画效果"
→ 使用 image_to_video 工具，提供图片 URL

Core Capabilities

1. Text-to-image

Generate images from text descriptions using the Jimeng 4.5 engine.

Tool：text_to_image

Parameters:

prompt(required): The text description of the desired image
model(optional): Model version (default: jimeng-4.5)
ratio(optional): Image aspect ratio ("1:1", "4:3", "3:4", "16:9", "9:16")
resolution(Optional): Resolution preset ("1k", "2k", "4k", default: 2k)
negativePrompt(Optional): Elements to avoid in the generated image

Common aspect ratios:

16:9 → Landscape/widescreen (video covers, banners)
1:1 → Square (avatars, social media)
9:16 → Portrait/mobile screen (short video covers)
4:3 → Standard landscape (blog images)
3:4 → Standard portrait (portrait photos)

Usage example:

# 用户请求："生成一张图片：夕阳下的海滩，有椰子树"
{
  "model": "jimeng-4.5",
  "prompt": "夕阳下的海滩，有椰子树",
  "ratio": "16:9",
  "resolution": "2k"
}

Returned result: Returns an array containing multiple image URLs, which can be displayed or downloaded.

Tips:

Higher resolution (4k) is suitable for print materials and high-quality displays
Lower resolution (1k) is suitable for quick previews
Use descriptive prompts to get better results
Specify art style, lighting, and atmosphere to enhance control

2. Image composition

Merge and blend multiple images through intelligent fusion.

Tool：image_composition

Parameters:

prompt(Required): Description of how to compose the images
images(Required): Array of 2-5 image URLs to compose
model(Optional): Model version (default: jimeng-4.5)
ratio(Optional): Output image aspect ratio ("1:1", "4:3", "3:4", "16:9", "9:16")
resolution(Optional): Resolution preset ("1k", "2k", "4k", default: 2k)

Usage example:

# 用户请求："合成这两张图，保留第一张的风格"
{
  "model": "jimeng-4.5",
  "prompt": "将两张图片无缝融合，保持第一张图片的艺术风格",
  "images": [
    "https://example.com/image1.jpg",
    "https://example.com/image2.jpg"
  ],
  "ratio": "4:3",
  "resolution": "2k"
}

Use cases:

Blend a portrait with a background
Style transfer between images
Create artistic composite works
Merge elements from multiple photos

Tips:

Provide clear composition instructions in the prompt
Images should have compatible resolutions
Describe the desired blending style (seamless, artistic, realistic)

3. Text to video

Create short videos from text descriptions.

Tool：text_to_video

Parameters:

prompt(Required): Text description of the video scene
model(Optional): Model version (default: jimeng-video-3.0)
ratio(Optional): Video aspect ratio ("16:9", "9:16", "4:3", "3:4", "1:1")
resolution(Optional): Resolution preset ("480p", "720p", "1080p")

Resolution presets:

"480p" → Quick preview
"720p" → Balanced quality/speed (recommended)
"1080p" → High quality

Usage example:

# 用户请求："生成5秒视频：小猫在钓鱼"
{
  "model": "jimeng-video-3.0",
  "prompt": "一只橘色小猫坐在河边，手持鱼竿专注地钓鱼，阳光明媚",
  "ratio": "16:9",
  "resolution": "720p"
}

Video features:

Duration: usually 3-5 seconds
Format: MP4
Generation time: 30-60 seconds
Frame rate: 24-30 fps

Tips:

Include scene details, actions, and atmosphere
Keep the prompt focused on a single clear action
Specify the time of day, weather, or mood for better results
Start with 720p to balance quality and speed

4. Image to video animation

Add motion and animation effects to static images.

Tool：image_to_video

Parameters:

prompt(Required): Description of the desired animation effect
file_paths(Required): Array of image URLs to animate
model(Optional): Model version (default: jimeng-video-3.0)
ratio(Optional): Video aspect ratio ("16:9", "9:16", "4:3", "3:4", "1:1")
resolution(Optional): Preset resolution ("480p", "720p", "1080p")

Usage example:

# 用户请求："让这张照片动起来，添加轻柔的镜头缩放"
{
  "model": "jimeng-video-3.0",
  "prompt": "添加轻柔的运动效果和自然的镜头缩放，营造电影感",
  "file_paths": ["https://example.com/photo.jpg"],
  "ratio": "16:9",
  "resolution": "720p"
}

Animation type:

Character motion
Camera movements
Scene transitions
Environmental effects: wind, rain, etc.

Tips:

Describe the desired type of motion
Consider the image content when choosing effects
Portrait photos are suitable for subtle movements
Landscape photos are suitable for pan/zoom effects

Workflow guide

Decision tree

收到用户请求
    │
    ├─ 包含"生成图片"或"create image"？
    │   └─ 是 → 使用 text_to_image
    │
    ├─ 包含"合成"或"merge/blend images"？
    │   └─ 是 → 使用 image_composition
    │
    ├─ 包含"生成视频"或"create video"？
    │   └─ 是 → 使用 text_to_video
    │
    └─ 包含"动画"或"animate image"？
        └─ 是 → 使用 image_to_video

Parameter extraction

When handling user requests:

Extract prompt: the user's description of the desired content
Identify aspect ratio: extract the size preference (landscape/portrait/square) corresponding to the ratio parameter
Parse resolution requirements: look for quality requirements, corresponding to the resolution parameter
Collect image URLs: used for composition and animation tasks

Error handling

If tool execution fails:

Check server status: verify whether jimeng-mcp-server is running
Verify API key: ensure JIMENG_API_KEY is configured
Check parameters: confirm that all required fields are provided
Check image URLs: verify whether the URLs for composition/animation are accessible
Report errors clearly: explain the problem and suggest solutions

Common errors:

API key not configured: set JIMENG_API_KEY in the environment
Server not responding: start the jimeng-free-api-all Docker container
Invalid image URL: ensure the URL is publicly accessible
Generation timeout: large videos may take 60+ seconds

Advanced usage

Combine multiple tools

For complex creative tasks, tools can be chained:

Example: Create animated artwork

Use text_to_image to generate a base image
Use image_to_video to animate the result

Example: Composition and optimization

Use image_composition to compose images
Generate variations using the adjusted prompt

Optimization tips

Speed up generation:

Use a lower resolution (720p instead of 1080p, or 1k instead of 2k)
Keep prompts concise but descriptive

Improve quality:

Use detailed, specific prompts
Choose the appropriate ratio (aspect ratio) based on the scene
Use a higher resolution (2k or 4k)
Specify the art style and technique
Include lighting and atmosphere descriptions

Batch processing

When the user requests multiple generations:

Process requests sequentially (one at a time)
Provide progress updates for each item
Collect all results before the final response
Consider resource limits (API quota)

Troubleshooting

Server connection issues

Symptoms: The tool returns a connection error

Solution:

Check whether the jimeng-free-api-all Docker container is running:
```
docker ps | grep jimeng
```
Verify whether the server is accessible:
```
curl http://127.0.0.1:8001/health
```
Restart the Docker container if needed

API key issues

Symptoms: "Invalid API key" or authentication error

Solution:

Verify JIMENG_API_KEY in the .env file
Get a new API key (sessionid value) from the Jimeng website cookies
Make sure the key format is correct (no extra spaces or quotes)

Generation quality issues

Symptoms: Poor quality or unexpected results

Solution:

Use more specific details to refine the prompt
Adjust the ratio parameter to choose an appropriate aspect ratio
Try different resolution resolutions
Add negativePrompt to exclude unwanted elements

Timeout errors

Symptoms: Generation takes too long or times out

Solution:

Video generation usually takes 30-60 seconds - please be patient
If timeouts persist, try a lower resolution
Check server resource usage
Verify the network connection to the Jimeng API

Resources

references/

setup_guide.md: Detailed installation and configuration instructions
api_reference.md: Complete API documentation for all tools

Project links

GitHub repository：https://github.com/wwwzhouhui/jimeng-mcp-server
Backend API：https://github.com/wwwzhouhui/jimeng-free-api-all
Jimeng official website：https://jimeng.jianying.com/

Best practices

Always verify server status before attempting generation
Use an appropriate resolution based on the use case and speed requirements(ratio controls the aspect ratio, resolution controls clarity)
Provide detailed promptsfor better generation quality
Handle errors gracefullyand provide clear user feedback
Consider rate limits when handling multiple requests
Test with simple prompts before complex compositions
Cache commonly used parameters, such as the preferred ratio and resolution

Limits

Free tier limit: The official Jimeng API provides 66 credits per day
Video duration: Usually limited to 3-10 seconds
Generation time: Videos may take 30-60 seconds to generate
Image composition: 2-3 images work best, with support for up to 5
Server dependency: Requires the jimeng-free-api-all backend to be running
Network requirements: Internet access is required to call the Jimeng API

About this skill

Overview

Prerequisites

Quick Start

Basic Usage Pattern

Example requests

Core Capabilities

1. Text-to-image

2. Image composition

3. Text to video

4. Image to video animation

Workflow guide

Decision tree

Parameter extraction

Error handling

Advanced usage

Combine multiple tools

Optimization tips

Batch processing

Troubleshooting

Server connection issues

API key issues

Generation quality issues

Timeout errors

Resources

references/

Project links

Best practices

Limits