jianying-video-gen

Original：🇨🇳 Chinese
Translated
1 scripts

Automatically generate AI videos using the Seedance 2.0 model of Jianying (also called Xiaoyunque). It supports three modes: Text to Video (T2V), Image to Video (I2V) and Reference Video to Video (V2V). This skill is applicable when users need to generate AI videos, create short films with the Seedance model, or perform style conversion based on reference images/videos. Pre-configuration of the cookies.json login credential is required.

7installs
Sourcecclank/lanshu-waytovideo
Added on

NPX Install

npx skill4agent add cclank/lanshu-waytovideo jianying-video-gen

Tags

Translated version includes tags in frontmatter
ai-video-generationtext-to-videoimage-to-videovideo-to-videoplaywright-automation

SKILL.md Content (Chinese)

View Translation Comparison →

Jianying AI Video Generator

Automate operations on Jianying (xyq.jianying.com) via Playwright to generate AI videos using the Seedance 2.0 model.

Prerequisites

  1. Python 3.9+ and 
    playwright
    installed
  2. Chromium installed via 
    playwright install chromium
  3. cookies.json — Jianying login credential (exported from browser), placed in the same directory as the script
bash
pip install playwright && playwright install chromium

Core Script

scripts/jianying_worker.py
— Main automation script

Usage

Text to Video (T2V)

bash
python3 scripts/jianying_worker.py \
  --cookies /path/to/cookies.json \
  --output-dir /path/to/output \
  --prompt "赛博朋克风格的长安城，飞行汽车穿梭在霓虹灯笼之间" \
  --duration 10s \
  --model "Seedance 2.0"

Image to Video (I2V)

bash
python3 scripts/jianying_worker.py \
  --cookies /path/to/cookies.json \
  --output-dir /path/to/output \
  --ref-image /path/to/image.png \
  --prompt "将这张图片变成动画，镜头从左向右缓慢平移" \
  --duration 10s \
  --model "Seedance 2.0 Fast"

Reference Video to Video (V2V)

bash
python3 scripts/jianying_worker.py \
  --cookies /path/to/cookies.json \
  --output-dir /path/to/output \
  --ref-video /path/to/reference.mp4 \
  --prompt "画风改成宫崎骏风格，其他不变" \
  --duration 10s \
  --model "Seedance 2.0"

Dry-Run Mode (for debugging)

bash
python3 scripts/jianying_worker.py --cookies /path/to/cookies.json --prompt "测试" --dry-run
Only fill the form without submission, generate 
step_*.png
screenshots for inspection.

Parameter Description

ParameterDefault ValueOptional ValuesDescription
--prompt
"A beautiful woman is dancing"Any textVideo description
--duration
10s
5s
, 
10s
, 
15s
Video duration
--ratio
Landscape
Landscape
, 
Portrait
, 
Square
Aspect ratio
--model
Seedance 2.0
Seedance 2.0
, 
Seedance 2.0 Fast
Model selection
--ref-image
NoneLocal image pathReference image for I2V mode
--ref-video
NoneLocal video pathReference video for V2V mode
--cookies
cookies.json
File pathJianying login credential path
--output-dir
.
Directory pathOutput video saving directory
--dry-run
false-Only fill form without submission

Model and Points

ModelPoints per second5s10s15sFeatures
Seedance 2.0 Fast3153045Fast, suitable for testing
Seedance 2.05255075High quality, for formal production

Automation Process

Login(cookies) → New project → Immersive short film → Select model → [Upload reference video] → Select duration → Enter Prompt → Submit
  → Intercept thread_id → Navigate to detail page → Poll for video → curl download MP4

Prompt Writing Guide

For detailed prompt examples and writing tips, refer to 
references/prompt-guide.md
.

FAQ

Q: What to do if cookies expire? Log in to xyq.jianying.com in your browser, export cookies.json using extensions like EditThisCookie.
Q: Encounter 403 error when downloading? The script uses thread_id detail page + curl for downloading, CDN links do not require cookies. If it still fails, check your network.
Q: Is uploading reference video very slow? It is normal, an 8MB video takes about 60-90 seconds. The script will automatically wait for up to 5 minutes.