How vothanhtrung1404ok-ship-it/tools_create_video_grok works
Video Factory AI is a desktop tool for creating AI-generated films and product-sales videos. Users choose a workflow in the GUI, provide a script or product and visual settings, then start generation; the app produces scene clips, adds optional narration/music and assembles output videos. Film work can use parsed or ChatGPT-written scripts, alternate video engines, and batch production; sales work builds product prompts and uses Grok. The excerpts show orchestration, generation and assembly, but not all GUI-to-workflow wiring, so uncertain links are omitted.
Main entry points: orchestrator.py Film orchestrator · main.py Desktop GUI · base.py Video engine API · batch_runner.py Batch runner
Components 22
User interface
- Desktop GUI
main.py
Production workflows
- Sales prompts
services/sales_prompt.py - Film orchestrator
orchestrator.py - Script parser
script_parser.py - ChatGPT agent
agents/chatgpt_agent.py - Batch runner
batch/batch_runner.py
Media generation
- Grok browser agent
agents/grok_agent.py - Video engine API
services/video_gen/base.py - Replicate engine
services/video_gen/replicate_engine.py - Kling engine
services/video_gen/kling_engine.py - Luma engine
services/video_gen/luma_engine.py - ComfyUI engine
services/video_gen/comfyui_engine.py - TTS API
services/tts/base.py - Edge TTS
services/tts/edge_tts_service.py - ElevenLabs TTS
services/tts/elevenlabs_tts.py
Video finishing
- Video processor
video/processor.py - Rendered videos
Other components
- User
- Grok / X
- Video AI APIs
- ComfyUI server
- Speech service
Connections 28
- User → Desktop GUI: configures
- Desktop GUI → Film orchestrator: starts film runs
- Desktop GUI → Sales prompts: builds sales prompts
- Desktop GUI → Grok browser agent: starts sales clips
- Desktop GUI → Batch runner: starts batch runs
- Film orchestrator → Script parser: parses scripts
- Film orchestrator → ChatGPT agent: requests scripts
- Film orchestrator → Grok browser agent: generates scenes
- Film orchestrator → Video engine API: selects engine
- Film orchestrator → TTS API: creates narration
- Film orchestrator → Video processor: assembles clips
- Batch runner → Grok browser agent: generates clips
- Batch runner → Script parser: parses scripts
- Batch runner → Video processor: assembles videos
- Grok browser agent → Grok / X: automates browser
- Video engine API → Replicate engine: implements
- Video engine API → Kling engine: implements
- Video engine API → Luma engine: implements
- Video engine API → ComfyUI engine: implements
- Replicate engine → Video AI APIs: submits generation
- Kling engine → Video AI APIs: submits generation
- Luma engine → Video AI APIs: submits generation
- ComfyUI engine → ComfyUI server: submits jobs
- TTS API → Edge TTS: implements
- TTS API → ElevenLabs TTS: implements
- Edge TTS → Speech service: synthesizes speech
- ElevenLabs TTS → Speech service: synthesizes speech
- Video processor → Rendered videos: renders video