| 1 | # Quick Start |
| 2 | |
| 3 | Already installed and configured? Let's create your first video! |
| 4 | |
| 5 | --- |
| 6 | |
| 7 | ## Start the Web Interface |
| 8 | |
| 9 | ### Windows All-in-One Package Users |
| 10 | |
| 11 | If you're using the Windows All-in-One Package, simply: |
| 12 | 1. Double-click `start.bat` |
| 13 | 2. Your browser will automatically open `http://localhost:8501` |
| 14 | |
| 15 | ### Install from Source Users |
| 16 | |
| 17 | ```bash |
| 18 | # Using uv |
| 19 | uv run streamlit run web/app.py |
| 20 | ``` |
| 21 | |
| 22 | Your browser will automatically open `http://localhost:8501` |
| 23 | |
| 24 | --- |
| 25 | |
| 26 | ## Create Your First Video |
| 27 | |
| 28 | ### Step 1: Check Configuration |
| 29 | |
| 30 | On first use, expand the「⚙️ System Configuration」panel and confirm: |
| 31 | |
| 32 | - **LLM Configuration**: Select an AI model (e.g., Qianwen, GPT) and enter API Key |
| 33 | - **Image Configuration**: Configure ComfyUI address or RunningHub API Key |
| 34 | |
| 35 | If not yet configured, see the [Configuration Guide](configuration.md). |
| 36 | |
| 37 | Click "Save Configuration" when done. |
| 38 | |
| 39 | --- |
| 40 | |
| 41 | ### Step 2: Enter a Topic |
| 42 | |
| 43 | In the left panel's「📝 Content Input」section: |
| 44 | |
| 45 | 1. Select「**AI Generate Content**」mode |
| 46 | 2. Enter a topic in the text box, for example: |
| 47 | ``` |
| 48 | Why develop a reading habit |
| 49 | ``` |
| 50 | 3. (Optional) Set number of scenes, default is 5 frames |
| 51 | |
| 52 | !!! tip "Topic Examples" |
| 53 | - Why develop a reading habit |
| 54 | - How to improve work efficiency |
| 55 | - The importance of healthy eating |
| 56 | - The meaning of travel |
| 57 | |
| 58 | --- |
| 59 | |
| 60 | ### Step 3: Configure Voice and Visuals |
| 61 | |
| 62 | In the middle panel: |
| 63 | |
| 64 | **Voice Settings** |
| 65 | - Select TTS workflow (default Edge-TTS works well) |
| 66 | - For voice cloning, upload a reference audio file |
| 67 | |
| 68 | **Visual Settings** |
| 69 | - Select image generation workflow (default works well) |
| 70 | - Set image dimensions (default 1024x1024) |
| 71 | - Choose video template (recommend portrait 1080x1920) |
| 72 | |
| 73 | --- |
| 74 | |
| 75 | ### Step 4: Generate Video |
| 76 | |
| 77 | Click the「🎬 Generate Video」button in the right panel! |
| 78 | |
| 79 | The system will show real-time progress: |
| 80 | - Generate script |
| 81 | - Generate images (for each scene) |
| 82 | - Synthesize voice |
| 83 | - Compose video |
| 84 | |
| 85 | !!! info "Generation Time" |
| 86 | Generating a 5-scene video takes about 2-5 minutes, depending on: LLM API response speed, image generation speed, TTS workflow type, and network conditions |
| 87 | |
| 88 | --- |
| 89 | |
| 90 | ### Step 5: Preview Video |
| 91 | |
| 92 | Once complete, the video will automatically play in the right panel! |
| 93 | |
| 94 | You'll see: |
| 95 | - 📹 Video preview player |
| 96 | - ⏱️ Video duration |
| 97 | - 📦 File size |
| 98 | - 🎬 Number of scenes |
| 99 | - 📐 Video dimensions |
| 100 | |
| 101 | The video file is saved in the `output/` folder. |
| 102 | |
| 103 | --- |
| 104 | |
| 105 | ## Next Steps |
| 106 | |
| 107 | Congratulations! You've successfully created your first video 🎉 |
| 108 | |
| 109 | Next, you can: |
| 110 | |
| 111 | - **Adjust Styles** - See the [Custom Visual Style](../tutorials/custom-style.md) tutorial |
| 112 | - **Clone Voices** - See the [Voice Cloning with Reference Audio](../tutorials/voice-cloning.md) tutorial |
| 113 | - **Use API** - See the [API Usage Guide](../user-guide/api.md) |
| 114 | - **Develop Templates** - See the [Template Development Guide](../user-guide/templates.md) |
| 115 | |
| 116 |