FlowCutPro — AI Cinematic Video Production
Two-layer architecture:
- - Brain: OpenClaw's configured LLM — shot planning, prompt engineering, style consistency, quality evaluation
- Renderer: Google Veo 3 (
veo-3.1-generate-preview) — photorealistic, physics-accurate, cinematic camera moves, 9:16/16:9/1:1
The LLM does the creative work. Veo 3 renders. ffmpeg stitches. You get professional video from a casual prompt.
Pipeline
CODEBLOCK0
Setup
Veo 3 API Key
Get a Gemini API key from https://aistudio.google.com/apikeys
export VEO_API_KEY="your-key-here"
Or store in 1Password: INLINECODE1
Dependencies
pip install Pillow requests # optional for thumbnails
brew install ffmpeg
Usage
CODEBLOCK3
Output
CODEBLOCK4
Prompt Engineering — Veo 3 Best Practices
FlowCutPro automatically applies these rules when generating prompts:
- 1. Always specify aspect ratio at the start: "Cinematic vertical 9:16 portrait..."
- Describe camera movement explicitly: slow push-in, dolly, crane, static wide, tracking shot
- Specify lighting: golden hour, overcast, blue hour, candlelit, harsh noon
- Include motion direction: "camera slowly pushes forward", "slow pan left to right"
- Name the aesthetic: cinematic, film grain, photorealistic, documentary, editorial
- Negative elements: "no text overlays, no logos, no CGI artifacts"
- Duration awareness: 5–8s per shot is optimal; 5s for fast cuts, 8s for slow moody shots
- Style consistency prefix: Start every shot prompt with the same style fingerprint for visual coherence across cuts
Examples
See examples/ folder:
- -
hotel-commercial.py — 8-shot luxury hotel commercial (9:16) - INLINECODE4 — 6-shot product launch reel (9:16)
- INLINECODE5 — 10-shot founder story (16:9)
Technical Details
- - Model:
veo-3.1-generate-preview (Google Generative AI) - Endpoint: INLINECODE7
- Aspect ratios:
9:16, 16:9, INLINECODE10 - Duration: 5–8 seconds per shot
- Concurrent limit: 5 shots per batch (enforced automatically)
- Stitch: ffmpeg xfade crossfade (0.5s transitions)
- Output codec: H.264, CRF 18 (high quality)
- Polling: 15s intervals, 10-minute timeout per shot
Limits & Notes
- - Veo 3 API is currently in preview — requires allowlist access via Google AI Studio
- Each shot takes ~2–4 minutes to render
- 10-shot video ≈ 20–40 minutes total (parallel batches of 5)
- API key needs Gemini API enabled in Google Cloud Console
- Free tier: limited daily quota; paid tier recommended for production use
FlowCutPro — AI电影级视频制作
双层架构:
- - 大脑: OpenClaw配置的LLM — 镜头规划、提示词工程、风格一致性、质量评估
- 渲染器: Google Veo 3(veo-3.1-generate-preview)— 照片级真实感、物理精确、电影级运镜、9:16/16:9/1:1
LLM负责创意工作。Veo 3负责渲染。ffmpeg负责拼接。你只需一个随意的提示词,即可获得专业视频。
工作流程
用户概念
↓
LLM:镜头规划器 — 将概念分解为N个镜头,包含时长+运镜
↓
LLM:提示词工程师 — 将每个镜头扩展为优化的Veo 3电影级提示词
↓
Veo 3:每批5个镜头渲染(API并发限制)
↓
LLM:质量评估器 — 检查输出缩略图与需求是否匹配,标记不合格镜头
↓
Veo 3:重新渲染不合格镜头(最多重试2次)
↓
ffmpeg:拼接片段并添加交叉淡入淡出效果 → 最终视频
↓
交付
环境配置
Veo 3 API密钥
从 https://aistudio.google.com/apikeys 获取Gemini API密钥
bash
export VEO
APIKEY=你的密钥
或存储在1Password中:op://flow/gemini-api-key/key
依赖项
bash
pip install Pillow requests # 可选,用于缩略图
brew install ffmpeg
使用方法
bash
单个概念 → 完整拼接视频
python3 ~/clawd/skills/flowcutpro/scripts/flowcutpro.py \
--concept 日落时分抵达波多黎各的豪华酒店客人 \
--shots 6 \
--aspect-ratio 9:16 \
--output-dir ~/clawd/output/flowcutpro/
短视频 / TikTok
python3 ~/clawd/skills/flowcutpro/scripts/flowcutpro.py \
--concept 东京极简公寓中的晨间咖啡仪式 \
--shots 4 \
--aspect-ratio 9:16 \
--duration 5 \
--output-dir ~/clawd/output/flowcutpro/
电影级宽屏
python3 ~/clawd/skills/flowcutpro/scripts/flowcutpro.py \
--concept 创始人从车库到IPO之日的旅程 \
--shots 8 \
--aspect-ratio 16:9 \
--output-dir ~/clawd/output/flowcutpro/
预演模式(检查镜头规划,不进行渲染)
python3 ~/clawd/skills/flowcutpro/scripts/flowcutpro.py \
--concept 硅谷屋顶的产品发布会 \
--shots 5 \
--dry-run
仅渲染指定镜头(重新渲染不合格镜头)
python3 ~/clawd/skills/flowcutpro/scripts/flowcutpro.py \
--concept ... \
--shots 6 \
--only-shots 3 5
输出文件
~/clawd/output/flowcutpro/
20260329-120000-shot01-arrival.mp4
20260329-120000-shot02-lobby.mp4
...
20260329-120000-FINAL-9x16.mp4 ← 拼接完成的主文件
提示词工程 — Veo 3最佳实践
FlowCutPro在生成提示词时会自动应用以下规则:
- 1. 始终在开头指定宽高比:电影级竖屏9:16人像...
- 明确描述运镜方式:缓慢推进、推轨、升降、静态广角、跟拍
- 指定光线条件:黄金时刻、阴天、蓝色时刻、烛光、正午强光
- 包含运动方向:摄像机缓慢向前推进、从左到右缓慢平移
- 命名美学风格:电影级、胶片颗粒、照片级真实感、纪录片、时尚大片
- 排除元素:无文字叠加、无标志、无CGI伪影
- 时长意识:每个镜头5-8秒为最佳;快切用5秒,慢节奏情绪镜头用8秒
- 风格一致性前缀:每个镜头提示词以相同的风格特征开头,确保剪辑间的视觉连贯性
示例
参见 examples/ 文件夹:
- - hotel-commercial.py — 8镜头豪华酒店广告(9:16)
- product-launch.py — 6镜头产品发布短视频(9:16)
- brand-story.py — 10镜头创始人故事(16:9)
技术细节
- - 模型: veo-3.1-generate-preview(Google Generative AI)
- 端点: https://generativelanguage.googleapis.com/v1beta/models/veo-3.1-generate-preview:predictLongRunning
- 宽高比: 9:16、16:9、1:1
- 时长: 每个镜头5-8秒
- 并发限制: 每批5个镜头(自动执行)
- 拼接: ffmpeg xfade交叉淡入淡出(0.5秒过渡)
- 输出编码: H.264,CRF 18(高质量)
- 轮询: 15秒间隔,每个镜头超时10分钟
限制与说明
- - Veo 3 API目前处于预览阶段 — 需要通过Google AI Studio申请白名单访问权限
- 每个镜头渲染约需2-4分钟
- 10镜头视频约需20-40分钟(每批5个并行处理)
- API密钥需要在Google Cloud Console中启用Gemini API
- 免费套餐:每日配额有限;生产环境使用建议选择付费套餐