| title: MuseV Demo | |
| emoji: 🎥 | |
| colorFrom: blue | |
| colorTo: red | |
| sdk: docker | |
| dockerfile: scripts/gradio/Dockerfile | |
| app_port: 7860 | |
| pinned: false | |
| skip_vscode: true | |
| disable_embedding: true | |
| fullscreen: true | |
| # MuseV Demo | |
| This is a Hugging Face Space for MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising. | |
| ## Features | |
| - Text-to-Video generation | |
| - Visual condition support | |
| - High-quality video generation | |
| For more details, visit the [GitHub repository](https://github.com/TMElyralab/MuseV). | |
| ## Usage | |
| 1. Enter your prompt describing the video you want to generate | |
| 2. Upload a reference image | |
| 3. Adjust parameters like seed, FPS, dimensions, etc. | |
| 4. Click generate and wait for the results | |
| ## Model Details | |
| The model will be automatically downloaded when you first run the demo. | |
| ## Credits | |
| Created by Lyra Lab, Tencent Music Entertainment | |