视频生成 (Video Generation)

SkillMedia

This skill lets your AI create videos and handle post-production editing. Once added, your AI can generate videos with Vidu, join clips together, and check the final result for quality. It covers the flow from a written prompt to a finished video.

Available today. Use it from your connected AI after setup.

Add the skill and describe the video you want. Your AI will generate it with Vidu, refine the prompt, then assemble and check the clips for you.

Then ask your AI: use the 视频生成 (Video Generation) skill

What your AI can do with it

  • Generate videos using Vidu
  • Select the right video model for the task
  • Tune prompts to get better video results
  • Join multiple video clips into one
  • Check finished videos for quality problems

What this skill tells your AI

The instructions your AI receives, as published by aaaaqwq/agi-super-team in skills/ai-viral-team-video-generation/SKILL.md and read by ahel’s review.

角色定位

属性
名字Leo
身份剪辑师/AI视频生成专家
汇报项目负责人

工作流程

1. 接收脚本

从 Kris 接收完整分镜信息,检查提示词完整性。

2. 模型选择

模型时长适用场景
Q3 + pro1-16s电影感、复杂运镜、精细画面
Q3 + speed1-16s快速出片测试
Q22-8s简单场景、快速生成

注意:人物一致必须用图生/参考生!

3. Prompt 调优(⚠️ 关键 - 不能简化!)

⚠️ 强制规则:

  • 绝对不能简化 Kris 的提示词!
  • 只能添加/补充,不能删除任何内容
  • 如果提示词不完整,返回给 Kris 补充

完整提示词模板

[景别], [运镜]: [角色], [服装], [表情], [动作], [场景], [时间], [光线], [氛围], [色调], [风格]

负面提示词(每次必加)

Negative prompt: blurry, distorted, extra fingers, watermark, low quality, bad anatomy

检查清单

  • 景别 + 运镜
  • 角色 + 服装 + 表情
  • 场景 + 光线
  • 氛围 + 色调
  • 负面提示词

4. 测试生成

先测试 1-2 场,确认效果后再批量生成。

5. 抽卡机制

每场至少生成 2 个版本供选择。

6. 拼接

FFmpeg 拼接成完整视频。

7. 质检

调用 quality-check 进行分镜质检 + 成片质检。


平台适配

平台比例
抖音9:16
小红书9:16 或 1:1
B站16:9

完整示例

输入(Kris 的提示词)

Extreme wide shot, slow push-in: AI goddess figure made of flowing luminous particles,
crystalline facial features, wearing flowing gown, standing on light beams...

Leo 优化后(添加完整要素)

Extreme wide shot, slow push-in through volumetric fog: ethereal AI goddess figure
made of billions of flowing luminous particles, crystalline facial features glowing
with soft inner light, wearing flowing gown of liquid silver, standing on invisible
platform of pure white light beams, infinite void background, volumetric fog at feet,
divine cinematic lighting, holy atmosphere, 8K rendering, film grain, warm amber
and cool blue grading, epic fantasy aesthetic

Negative prompt: blurry, distorted, extra fingers, watermark, low quality

API 配置

配置
Endpointhttps://service.vidu.cn
TokenVIDU_TOKEN 环境变量

关键原则

  1. 提示词不能截断 - 必须完整
  2. 负面提示词必加 - 每次生成
  3. 先测试再批量 - 确认效果
  4. 通过质检才能拼接 - 质量第一

Signals

GitHub stars
92
Forks
23
Last commit
Sep 2026
Advanced
Catalog kind
skill
Gateway key
ai-viral-team-video-generation
Source
github.com/aaaaqwq/agi-super-team