linkfox-aigc-videogen-multi

Original：🇨🇳 Chinese

Translated

2 scriptsChecked / no sensitive code detected

Multi-reference Image to Video Tool: Generate videos based on multiple reference images and prompts. Supports models KLING (Keling), SEED (Doubao), SEED_FAST, HAPPY_HORSE (Bailian). It supports controls for duration, Pro mode, audio, aspect ratio, etc. Triggered when keywords such as "generate video", "multi-image video", "multiple images to video", "multi-reference image to video", "multi image video", "multiple images to video" are used.

4installs

Sourcelinkfox-ai/linkfox-skills

Added on2026-08-15

NPX Install

npx skill4agent add linkfox-ai/linkfox-skills linkfox-aigc-videogen-multi

SKILL.md Content (Chinese)

View Translation Comparison →

Multi-reference Image to Video Generation

Generate videos based on multiple reference images and prompts, supporting 3 AI video models. Create tasks asynchronously and poll for results.

Core Features

4 Model Options: KLING/SEED/SEED_FAST/HAPPY_HORSE, covering different styles and durations.
Multi-image Reference: Pass multiple images as references, and the AI will generate videos comprehensively.
Rich Parameters: Supports Pro mode, audio generation, aspect ratio, resolution, etc.
Asynchronous Mode: Returns
```
taskId
```
immediately after task creation, and the script automatically polls until completion (timeout after 20 minutes).

Model Description

Model (videoType)	Description	Supported Duration	Max Images
KLING	Keling	5s/10s	≤7
SEED	Seedance/Doubao	5s/10s/15s	≤9
SEED_FAST	Seedance 2.0 Fast	5s/10s/15s	≤9
HAPPY_HORSE	Bailian HappyHorse	5s/10s/15s (default 15s)	≤9

Parameter Overview

Required Fields:
```
imageList
```
,
```
videoType
```
,
```
videoTime
```
Optional Core Parameters:
```
prompt
```
(within 2000 characters),
```
aspectRatio
```
,
```
resolution
```

For the complete parameter table, response field structure, and error codes, see

references/api.md

.

Calling Methods

Create Task:

POST /aigc/multiImageVideoGenAsync

→ Returns

{taskId}

Poll for Results:
```
POST /aigc/taskQuery
```
→ Pass
```
{taskId}
```
→ Returns status and results
Python Script:
```
python scripts/aigc_videogen_multi.py '<JSON parameters>'
```
(The script automatically handles creation + polling internally)

Asynchronous Flow:

The script calls
```
/aigc/multiImageVideoGenAsync
```
to create a task and obtain
```
taskId
```
Starts polling
```
/aigc/taskQuery
```
after waiting for 2 minutes, once every 10 seconds, with a maximum wait time of 20 minutes
Automatically downloads the video to the session
```
media/
```
directory upon success

Output Strategy (Default Script Behavior):

The script automatically downloads and transfers the generated video to the session
```
media/
```
directory, and outputs a line
```
Saved full response: <path array>
```
to stdout.
The original API response is silently saved to
```
data/
```
, and its path is only prompted in stdout when there is no video output.

Data Reading Suggestion: Do NOT read the content of the transferred video file. Directly provide the local path after

Saved full response:

to the user.

Resolve Authentication and Points Issues

For the following abnormal situations, guide users to resolve them using references/onboarding.md:

Abnormal Situations

API Key Not Configured: The environment variable
```
LINKFOX_AGENT_API_KEY
```
or
```
LINKFOXAGENT_API_KEY
```
is not configured.
Response with 401 or 402 Status Code
Response Indicates Insufficient Points or Balance: The message contains content like "insufficient points balance/insufficient billing/insufficient balance/quota exceeded/insufficient balance/package expired/need to recharge/please recharge" or similar meanings.

Usage Guidelines

Model Selection: Generally use
```
KLING
```
for multi-reference images; use
```
SEED
```
for high resolution; use
```
HAPPY_HORSE
```
for Bailian style.
Number of Images: KLING supports up to 7 images, SEED/HAPPY_HORSE support up to 9 images. At least 1 image must be passed.
Duration Matching: Must pass a duration value supported by the model, otherwise an error will occur.
Prompt: Optional, within 2000 characters, describing the desired dynamic effects.

Examples

1. KLING Multi-reference Images

json

{"imageList": ["https://example.com/img1.jpg", "https://example.com/img2.jpg", "https://example.com/img3.jpg"], "videoType": "KLING", "videoTime": 10, "prompt": "Multi-angle display of the product"}

2. SEED High-resolution Multi-reference Images

json

{"imageList": ["https://example.com/a.jpg", "https://example.com/b.jpg"], "videoType": "SEED", "videoTime": 15, "resolution": "1080p", "aspectRatio": "16:9"}

3. HAPPY_HORSE Multi-reference Images

json

{"imageList": ["https://example.com/p1.jpg", "https://example.com/p2.jpg", "https://example.com/p3.jpg"], "videoType": "HAPPY_HORSE", "videoTime": 15, "resolution": "1080p", "aspectRatio": "16:9"}

Display Rules

Only display the local path of the transferred video: Tell the user the local video path after
```
Saved full response:
```
, e.g., "Video saved to: xxx/a.mp4".
Do NOT read video files, do NOT display base64 content.
Do NOT directly provide the temporary URL returned by the original API to users (it is signed and will expire).

Limitations

Maximum 2000 characters for prompts.
Generation time is relatively long, usually 100-600 seconds. The script automatically polls, with a timeout of 20 minutes.
KLING supports up to 7 reference images, SEED/HAPPY_HORSE support up to 9 reference images.
HAPPY_HORSE does not support isPro.
No retries on failure (only 1 attempt).

Not Applicable Scenarios

Not Applicable:

Single image/first and last frame video generation →
```
linkfox-aigc-videogen
```
Image generation →
```
linkfox-aigc-imagegen
```
Text generation →
```
linkfox-aigc-textgen
```

Feedback

See

references/api.md

.

linkfox-aigc-videogen-multi

NPX Install

Tags

SKILL.md Content (Chinese)

Multi-reference Image to Video Generation

Core Features

Model Description

Parameter Overview

Calling Methods

Resolve Authentication and Points Issues

Abnormal Situations

Usage Guidelines

Examples

Display Rules

Limitations

Not Applicable Scenarios

Feedback