提取/逆向工程 Bilibili AI 生成视频的 生产就绪提示 用于模仿。输出详细的 ComfyUI/Seedance 格式提示，可直接用于 Seedance/Kling/Runway 以最小编辑。
工作流程
- 下载视频: 使用 yt-dlp 从 Bilibili URL 下载视频
- 提取字幕: 提取软字幕或硬字幕用于语音参考/重写
- 提取帧: 配置 FPS（默认 1 帧/秒）提取帧
- 视觉分析: 帧间分析识别风格、主题、颜色、构成、运动变化
- 结构化输出 (直接使用):
- 技术元数据（宽高比、持续时间、帧率、模型推荐）
- 2-3 个关键帧提示（最明显的组合，ComfyUI 逗号格式）
- 场景序列按故事节拍（时间线 + 提示演变）
- 全视频主提示（整体风格 + 主题）
- 提取的字幕文本（用于语音参考）
使用时机
✅
使用此技能时:
- 您有 Bilibili AI 生成视频的链接
- 您想要模仿风格生成类似视频
- 您需要直接在 Seedance/ComfyUI/Kling 使用的生产就绪提示
- 您想要提取字幕用于重用或重写语音
- 您想要关键帧 + 场景分解用于多步生成
❌ 不使用此技能时:
- 提示已在视频描述中（直接使用代理提取）
- 是人工拍摄的非 AI 生成视频
... （以下内容为技术细节，未翻译以保持原始格式）
Extract/reverse-engineer production-ready prompts from Bilibili AI-generated videos for imitation. Outputs detailed prompts in ComfyUI/Seedance format that can be used directly with minimal edits.
Workflow
- Download video: Get video from Bilibili URL using yt-dlp
- Extract subtitles: Extract soft or hard subtitles for voiceover reference/rewrite
- Extract frames: Extract frames at configurable FPS (default: 1 frame/second)
- Visual analysis: Analyze frame-by-frame to identify style, subjects, colors, composition, motion changes
- Structure output (ready for direct use):
- Technical metadata (aspect ratio, duration, fps, model recommendation)
- 2-3 keyframe prompts (most distinct compositions, ComfyUI comma format)
- Scene sequence by story beat (timeline + prompt evolution)
- Full video master prompt (overall style + theme)
- Extracted subtitle text (for voiceover reference)
When to Use
✅ Use this skill when:
- You have a Bilibili link to an AI-generated video
- You want to imitate the style and generate similar videos
- You need production-ready prompts that work directly in Seedance/ComfyUI/Kling
- You want to extract subtitles to reuse or rewrite the voiceover
- You want keyframe + scene breakdown for multi-step generation
❌ Don't use when:
- The prompt is already in the video description (use agent-reach to extract directly)
- It's a human-shot video not generated by AI
Sampling Strategy
| FPS | Use Case | Recommendation |
|---|
| 0.2 | Long video (>5min), big scene changes | Only key frames |
| 1 | Short video (<1min) | Default, one frame per second |
| 2-5 | Detailed motion analysis | Slow morphing animations |
Best practice: 1fps for short videos (<1min) gives good granularity without redundancy. Most AI video evolution changes gradually, 1s interval captures the arc well.
Requirements
ffmpeg installed (for frame extraction and subtitle extraction)yt-dlp installed (for video download)- Multimodal LLM support (for visual frame analysis)
Scripts
scripts/download-bilibili.sh - Download video from Bilibili URLscripts/extract-frames.sh [fps] - Extract frames from videoscripts/extract-subtitles.sh - Extract subtitles to text file (supports soft and hardsubs)
Output Format (Production-Ready)
1. Technical Metadata
Aspect Ratio: 9:16 (1080x1440)
Duration: 35 seconds
Frame Rate: 30 fps
Recommended Model: Seedance 2.0 / Kling AI / Runway Gen-3
Motion Type: Slow fluid morphing, seamless transformation
2. Keyframe Prompts (ComfyUI Format, comma-separated)
One detailed prompt for each most distinct keyframe:
masterpiece, best quality, 8k, ultra detailed, tiny glowing point of light in deep indigo mist, volumetric godray, soft atmospheric haze, vertical composition 9:16, surreal abstract, mindscape, glowing particles, deep blue purple color palette, ethereal, dreamlike, cinematic lighting
3. Scene Sequence Breakdown (by timeline beat)
| Time | Visual Description | Prompt Addition |
|---|
| 0s-8s | Origin in void | glowing point, mist, void |
| 8s-18s | Network growth | fibers spreading, interconnected thought network |
4. Full Video Master Prompt
Complete cohesive prompt capturing overall style, theme, pacing that can be used directly.
5. Extracted Subtitles
Clean text extracted for voiceover reference or rewrite.
Prompt Quality Guidelines
Output prompts follow Seedance/ComfyUI best practices:
- Start with quality tokens:
masterpiece, best quality, 8k, ultra detailed
- Describe composition before style
- Specify exact colors and lighting
- Include aspect ratio and motion characteristics
- Keep comma-separated format for direct copy-paste
by